Descartes Systems Group Inc. Stock

Good afternoon. Welcome to The Descartes Systems Group Q2 earnings call. [Operator Instructions] I'd now like to turn the conference over to Scott Pagan. Please go ahead.

Thank you very much. Thanks, and good afternoon, everyone. Apologies for the delay in starting. There was a slight technical issue with getting the press release out on the wire. Joining me on the call today are Ed Ryan, CEO; and Ed Gardner, our CFO. And I trust that everyone has now received a copy of our financial results press release. Portions of today's call, other than historical performance, include statements of forward-looking information within the meaning of applicable securities laws. These statements are made under the safe harbor provisions of those laws. These forward-looking statements include statements related to our assessment of the current and future impact of geopolitical trade, tariff and economic uncertainty on our business and financial condition; Descartes' operating performance, financial results and condition, cash flow and use of cash, business outlook, baseline revenues, baseline operating expenses and baseline calibration, anticipated and potential revenue losses and gains, anticipated recognition of revenues and incurrence of expenses, potential acquisitions and acquisition strategy, cost reduction and integration initiatives, potential share purchases under a normal course issuer bid and other matters that may constitute forward-looking statements. .

These forward-looking statements involve known and unknown risks, uncertainties, assumptions and other factors that may cause the actual results, performance or achievements of Descartes to differ materially from the anticipated results, performance or achievements implied by such forward-looking statements. These factors are outlined in the press release and in the section entitled certain factors that may affect future results in documents filed and furnished with the SEC, the OSC and other securities commissions across Canada, including our management's discussion and analysis filed today. We provide forward-looking statements solely for the purpose of providing information about management's current expectations and plans relating to the future. You're cautioned that such information may not be appropriate for other purposes. We don't undertake or accept any obligation or undertaking to release publicly any updates or revisions to any forward-looking statements to reflect any change in our expectations or any change in events, conditions, assumptions or circumstances on which any such statement is based, except as required by law. And with that, let me turn the call over to Ed.

Thanks, Scott, and welcome, everyone, to the call. Today, we are again reporting record quarterly financial results. We're ahead of our plan in Q2, which gives us even more room to make acquisitions, investments in AI and other investments in our business. These are strong results that I'm looking forward to walking through in more detail. However, first, let me give you the road map for the call. I'll start by hitting some highlights of our last quarter, and I'll provide some comments on some investments we've been making. And then I'll hand it over to Ed Gardner, who will go over the Q2 year-to-date financial results in more detail. After that, I'll come back and provide an update on how we see the current business environment and how our business was calibrated for Q3, and then we'll open it up to the operator to coordinate the Q&A portion of the call.

So let's get into Q2. Key metrics we monitor, including revenues, profits, cash flow from operations, operating margins and returns on our investments. For this past quarter, we again had record performance in each of those areas. Total revenues were a record $201 million, up 12% from a year ago. Record high services revenues were up 13% from a year ago and our continued focus on generating recurring revenues. Record net income was up 32% from a year ago, and record income from operations was up 36% from a year ago. Record adjusted EBITDA was up 18% from a year ago, our adjusted EBITDA margin is at a record high level of 47%. We generated over $81 million in cash from our operations, up 28% from a year ago. So strong record results across all of our key metrics. At the end of the quarter, we had over $400 million in cash, and we were debt-free with an undrawn $350 million line of credit. This was before we completed some acquisitions in August, which I'll talk about shortly.

We remain well capitalized, cash generating and growing and ready to continue to invest in our business. We also have a normal course issuer bid that allows us to purchase up to 8.6 million shares before December of this year. We've made some more purchases since we last reported, and I'll allow Ed Gardner to give you those details. But especially in light of how the business performed last quarter, we remain optimistic about Descartes' future. and the normal course issuer at the tool we could use to make further purchases. I wanted to touch on a few areas that helped our business perform well this quarter. We'll notice some of them are similar themes to previous quarters.

The first is global trade Intelligence. Global Trade Intelligence remains one of the larger contributors to our services revenue. We had good growth in the quarter compared to where it was a year ago. I think it's helpful to understand what's going on with global trade to understand why we've seen more demand from customers in this part of our business. The 3 things going on in the world that are making it more challenging to move goods from point A to point B. The first is tariffs are still changing, and they're often changing rapidly. There's been a lot of active resetting international trade agreements. The setting raising or lowering of tariffs has become a common international tool in recent trade negotiations. Changes have often come with less advanced notice than industry has been used to. It's extremely challenging for businesses involved in international trade to track and manage all of these changes on their own.

More and more businesses are relying on global trade management systems powered by the kind of tariff and duty content that Descartes provides. This has been a big demand driver for us. Also, businesses that become more active in researching ways to minimize their tariff burden. They're consulting more and more with trade professionals are using research tools like Descartes state amount tools to understand what business peers are doing. So it has also influenced demand. Further, if you can't reduce tariffs, there's value in deferring your tariff burden leveraging available tariff mechanisms such as farm trade zones has been another area that has increased customer demand for Descartes. The second is customs and export control enforcement has stepped up. Governments, in particular, in the U.S. have committed additional funding to customs and export control enforcement activities.

This is in response to the perception that there is a significant noncompliance worth pursuing particularly on sanctioned parties and export controls. Sanction parties are aware of government list entities or individuals with whom it is illegal to trade. These sanctions often come about because of military conflicts, economic disputes or criminal activities. Trading with the prohibited entity can bring large penalties. For that reason, a key part of Global Trade Compliance programs should include detailed, sanction screening for shipments, Descartes sanction party screening business has seen strong demand, and we don't expect increased enforcement to lower that demand.

Export compliance is often at the commodity level of shipment prohibitions or licensing on goods exported from 1 country to another. These requirements can be because of militarily sensitive goods or dual-use goods or because of scarce valuable resources in our manufacturing process like semiconductors and ships. Our export compliance solutions, particularly in our OCR solutions have seen heightened demand as enforcement of these rules has increased. And the third is compliance and audit burden has increased hand in hand with the increase in enforcement the obligation to keep detailed after an auditable records on our global trade transactions has increased.

So for example, it's not enough to appropriately screen a transaction, but you also need the auditable proof of that screen available in the future for third-party your view. The importance of global trade management systems has shifted from transactional execution to systems of record for trade. This is particularly so with increased U.S. focus on train shipments as a mechanism that is potentially being used to avoid tariffs or sanctions. Transshipment is where goods are routed through 1 or more other countries before the final destination often to avoid tariffs or sanctions that apply to the original country of origin.

Customers are compelled to have accurate and detailed records improving country of origin and shipped goods subtle is increasingly challenging in a complex world of international supply chains and multiple internationally sourced component parts in finished goods. We have seen good demand from people seeking new and more sophisticated trade management systems with reputable stable partners that could support future audits. That's been a good demand driver for us as well. A rapidly changing tariff environment increased resources dedicated towards trade enforcement and detailed and audible record requirements extended into the future, a much more complex trade environment. is what we're in today.

With the number of changes that have happened in the trade environment over the past 2 years, we found that our customers are no longer waiting to see what's next. Many have accepted that volatility is the new baseline operating condition. Rather than accepting the stability of a trade role in building the standard operating procedure to address that role, we found that our customers are already focused on building agility, flexibility and redundancy into their supply chains. They're preparing themselves to be ready for what they don't know is going to change. That approach has necessitated a higher level of investment and executive attention to supply chain and logistics issues that we've seen historically. We've seen the same trend with shippers booking capacity. More shippers are relying on spot rates and shorter-term capacity contracts.

That investment has been supported by onetime tailwind for some in the U.S., some businesses have received sizable tariff refunds from the previous U.S. Supreme Court decision and validating the international emergency Economic Powers Act tariffs. Again, one time in nature, however, a stimulus for some supply chain investments. Second area where we've seen good growth is in our e-commerce entries. We continue to see overall growth in consumers embracing e-commerce even with the elimination of the tariff exempt type 86 de minimis program. Imports have continued to grow coming into the United States. We have a premier solution for handling e-commerce imports into the U.S. using our net CHP system with particular strength in high volume and high velocity requirements.

We're hoping key brokers meet the demands of importers and these volumes are contributing well to our revenue growth. We called this out in Q1, but we again saw strength in Q2. The third area is in transportation management. MacroPoint continues to be strong for us. MacroPoint provides real-time visibility to shipments, brokers and shippers tell us the loads they want to track. It's our job to get the tracking information from onboard systems, transportation management systems using our application or old-fashioned calls to drivers. Over past quarters, we've enhanced our system to AI agents that interact with drivers to encourage adoption of our tracking app, helping us reach a segment of the market that was previously difficult to reach the scale. These agents have helped contribute to higher percentage of shipments track than our peers, which in turn drives more people to our network. We're also competitively differentiated because we are tracking data from both phones and onboard devices.

So we're able to compare those data sets and of our customers' discrepancies that may exist as they consider which carriers they'll use in the future. One of the particular strengths of our transportation management offerings is the combined solution that we can provide. We have full enterprise grade transportation management system for shippers and brokers real-time tracking of a shipment and fraud protection/carrier screening with my carrier portal. This combination has been well received by the market, especially for brokers we need enhanced carrier screening tools in light of the U.S. Supreme Court acquisition, imposing liability on brokers for recess selection of onsacarriers.

A good growth driver for us with the potential for further growth, which was a key consideration for our recent investment in Thai, which I'll talk about later. And the last is fleet performance/management and RA. We have to help customers manage their fleets of vehicles. In particular, we have routing and scheduling solutions to help companies figure out the most efficient way to make deliveries and reduce hours and miles driven to do that. There's always good demand for these solutions. However, the demand increases in periods like now or fuel cost increase. Running your fleet becomes more expensive and customers look into solutions to reduce the amount of fuel they are using to make deliveries. Cost consciousness for fleet owners is even higher given the inflation that exists in driver wages. This wage inflation is driven in part by driver shortages, new U.S. regulations have made it more difficult to training qualified be driver.

This demand in our business was supported by 2 recent investments we made at the end of Q1. We combined with Adelic. Adelic is an AI-powered driver safety and performance management system. This was a timely investment as the U.S. court focused attention on driver safety and liability and accidents. This is our first full quarter with Ydelicand is prepared -- has paired well with our [indiscernible] solution to provide an excellent tool to enhance safety oversight of our existing traffic customers. Then in the last month of Driven joined our Descartes team. Latin America has been a key expansion target for our routing solutions. There's a lot of opportunity for growth with our existing solutions portfolio, plus access to a broad-based delivering information in the region. We're joined by a great team with experienced delivery solutions in high-density urban environments. Driven was only here for about 3 weeks of Q2. but it has met well with our team, and we're looking forward to great things to come in Q3 and beyond. So overall, these are the items that contributed strong growth and demand in Q2, that performance, we were able to continue to make investments in our business. One of our -- one of the principal areas of investment continues to be in artificial intelligence technologies -- and with that, let's talk about AI.

We're investing in AI because it enables automation as supply chains and logistics becomes more and more complex. Managing sources of data, physical resources, human resources, payments, tariffs, duties, compliance, sanctions, fuel costs, vessel capacity, warehouses. All these are becoming too complex for humans to manage on their own. In making our investments, we have some core beliefs in mind about how AI will change our business over time. Our solutions will be used by AI through APIs and agents more than by users and with rows, our solutions will be used to generate outcomes for customers rather than to be licensed for access. Our solutions will be used to identify and prevent potential problems as much as to solve existing problems. We believe that human oversight of decisions made by technology will still be critical. That the data on our network, we will provide critical context to both fuel and human and AI decisions. And finally, that our broad solution set integrate to provide our customers with a single source for unrivaled outcomes.

We've been very active in the designing our infrastructure, workflows and commercial models to adapt to these inevitable changes. We've designed our agent control plane for agents to access our products. We've made it skills from our products available to agents via MCP and the agent control panel. We're undertaking comprehensive data growth -- data graph to bring useful network effect context to decisions, and we're designing a uniform workbench, entry points for agents and humans to access the Descartes Global Logistics Network skills. We're very busy and tremendously excited by the value we can deliver to our customers using these AI capabilities. Our customers are also asking us for AI that removes work. They're more interested in outcomes than workflows.

With that in mind, we're developing and deploying AI agents, including agents that classify HS codes, model duty exposure and sourcing shifts. Agents that diagnose customs and regulatory filing rejections and suggest remediation, agents to predict late loads and proactively rebooked doc appointments, agents that rate and book across transportation modes, agents to forecast e-commerce demand, balance stock and rate shop sanctioned party screening triage to clear false positives, agents that screen for double brokering and identify fraud, agents that dynamically schedule to get delivery rates back on track. And finally, fleet safety coaching. These aren't aspirational. Our customers are seeing real benefits from AI agents already.

As I've been mentioning previously, our MacroPoint business is actively using agents to call drivers for location checks, gather proof of delivering information for billing purposes, get arrival and departure confirmation, get truck rates to help with carrier selection and get insurance certificates for carriers. This helps our customers track import or Lowe's. We have AI agents that enable tracking on 26% more loads than they did in Q1. As we deliver more value to customers, we can pay on delivering more outcomes. This has been a real benefit to us in the quarter and all due to AI. AI is an exciting part of our present and future. We're planning a comprehensive update on what we're doing with AI at our in-person innovation form to be held October 6 through the 8th in Chicago. We're planning on showing practical and real examples of how our customers will get value from outcomes leveraging AI.

This is a big event where attendees to interact with customers, partners and Descartes team members a great event to learn from the carton and others, but also to provide feedback on how we can help deliver more value. We're very excited to host everyone and share how excited we are about our future. Please see our website from our registration deals and details, and we look forward to seeing you there.

So in summary, strong Q2 with additional AI investments, 2 acquisitions that impacted Q2 and plans for more investments. I'm excited about how the business is performing and the opportunity we have in front of us. With that, I will turn the call over to Ed Gardner to go through the financial results in more detail.

Awesome. Thanks, Ed. As Ed mentioned, I'll be walking you through our key financial highlights for the second quarter and year-to-date results. We're pleased to report record quarterly revenues of $201.1 million this quarter, an increase of approximately 12% from revenues of $179.8 million in Q2 of last year. Our revenue mix in the quarter continued to be very strong, with services revenue increasing over 13% to $188.6 million from $166.8 million last year in the second quarter, with services revenue representing 94% of total revenue this quarter, removing the impact of both the recent acquisitions as well as a positive impact from changes in FX rates we would estimate that our growth in services revenue from new and existing customers that is our organic growth would have been just north of 9% this quarter when compared to the same quarter last year, which is similar to Q1 of this year. .

Professional services and other revenue, including hardware revenue, came in at $12.4 million or 6% of revenue, slightly down from $12.8 million in Q2 last year, while license revenues were minimal similarly to last year. Collectively, our professional services and other revenue, combined with our license revenues was approximately 6% of our total revenues. Gross margin came in at 78% of revenue for the second quarter, up from 77% in Q2 of last year. The increase in gross margin for the quarter was primarily due to operating leverage from our organic growth in services revenue.

Turning our attention to the bottom line. As a result of solid revenue growth, improved gross margin as well as controlled growth in operating expenses, adjusted EBITDA came in at a record $94.4 million just under 47% of revenue, up 18% from adjusted EBITDA of $80.2 million in the same quarter last year. From a GAAP earnings perspective, net income for the second quarter came in at $50 million, up 32% from last year. With these operating results and strong collections from customers, cash flow generated from operations came in at $81.3 million or 86% of adjusted EBITDA, up 28% from operating cash flow in the second quarter last year.

Looking at our operating results for the first half of the year, revenue came in at $394.7 million, an increase of 13% from revenue of $348.6 million in the first 6 months of last year. For that same period, adjusted EBITDA came in at $184.1 million or 46.6% of revenue, up 19% from last year. Net income for the first half of this year also increased, coming in at $98.5 million or $1.13 per diluted common share, up from $74.3 million or $0.85 per diluted common share in the first half of last year. So overall, a great second quarter to complete a great first half of the year. If we look at the balance sheet, our cash balances totaled $401 million at the end of July. As I just mentioned, we generated operating cash flow of just over $81 million in the quarter. Offsetting that was approximately $30 million in capital deployed on the Drive acquisition and approximately $24 million on share buybacks under our normal course issuer bid.

Also worth noting that since the quarter ended, we spent approximately $220 million on the acquisitions of Tai and extensive. And as we look ahead, we still remain well capitalized and ready to capitalize on potential M&A activities in our space. A couple more points as it relates to the remainder of fiscal 2027. Going forward, we expect to continue to see operating cash flow conversion north of 80% of our adjusted EBITDA, of course, subject to unusual events and quarterly fluctuations, including adjustments related to future earn-out payments that exceed our estimates made at the time of an acquisition. After incurring approximately $4.6 million in capital additions in the first half of the year, we expect to incur approximately $2 million to $4 million in additional capital expenditures this coming year, mainly related to IT equipment purchases. After deploying approximately $45 million on share buybacks in the first half of the year, we may see additional purchases under the NCIB program moving forward.

After incurring amortization expense of $35.4 million in the first half of this year, we expect amortization expense will come in at $37.5 million for the remainder of fiscal 2027, with this figure being subject to adjustment for foreign exchanges and any future acquisitions. We estimate that payments of contingent consideration for earn-out agreements for the balance of this year could be up to approximately $9 million, subject to any necessary adjustments resulting from the final earnout calculations. Our income tax rate in the first half of the year came in within our expected range at approximately 26% of pretax income in line with our blended statutory tax rate of approximately 26.5%. For the remainder of fiscal 2027 we're expecting the tax rate will be in the range of 25% to 30% of our pretax income, which means it will be something on either side of our blended statutory tax rate.

However, as always, we should add that our tax rate may fluctuate from quarter-to-quarter from onetime tax items that may arise as we operate internationally across multiple countries. And finally, after incurring stock-based compensation expense of $14.8 million in the first half of the year, we currently expect stock compensation to be approximately $15.5 million for the remainder of fiscal 2027, subject to any corporate stock offerings or share units. I'll now turn it back over to Ed Ryan to wrap up with some closing comments and our baseline calibration for Q3.

Thanks, Ed. It's still a challenging shipping market. International trade flows continue to adjust to a changing tariff landscape. Elevated fuel costs and driver shortages have impacted domestic trucking, continued Middle East unrest has extended sales impacted capacity and increased prices. El Nino weather events are creating transportation challenges through historical waterways. There are new restrictions on selling to the Panama Canal and there are port delays causing backups in offloading cargo. Even where the volumes of shipments are down because of the challenging regulatory and trade environment, we continue to see good demand from our customers to deal with the additional complexity and move goods. So we still see good demand in the face of pressures on volumes. This is particularly so with lower value shipments which on a country-by-country basis have moved from tariff-free, rapid process shipments to full compliance and customs authority review of shipments.

On the plus side, we've seen some tailwinds on to shipment volumes from increased movement of AI infrastructure equipment. Slightly impacted a strong month of August for ocean shipments. August ocean imports into the U.S. were the third highest month -- monthly volume ever. We've got a couple of recent acquisitions that also impact how we look at the rest of the year. The first was Tai an excellent complement to our existing transportation management business for freight brokers, Tai is leveraging AI within their broker workflows already. and consistent with our own AI investment goals as a system of record, tierings additional broker transaction data to provide context to shipments on the global logistics network. An exciting addition that complements our existing business drives our AI goals forward and brings a very talented team at Descartes.

Shortly after we bought time, we made a second investment into extensive formerly known as 3PL Central. Extensive provides warehouse management solutions to over 1,200 third-party logistics providers who are often managing fulfillment on behalf of e-commerce sellers. This fills a gap for us on what we were previously able to offer to 3PLs and is consistent with our approach to WMS where we focus on e-commerce and high-velocity warehouse movements. It also furthers our AI goal by bringing a rich set of omnichannel fulfillment data on over 150 million orders to the Global Logistics Network. We'll address this further in the next quarter, but we -- it may be worth noting that a small portion of extensive business sits outside the 3GLWMS core offering and is an area of the business where we expect some revenue attrition early next fiscal year. Our focus is on growing the 3PL WMS portion of the business, and our team is really excited about the opportunities that we'll have as a combined business.

We've already seen outreach from some of our existing 3PL Descartes customers looking to learn more about extensive, so very promising right out of the gate. So it's a challenging macro environment for shipping with new things that come in to make it an ever challenged changing landscape for our customers, also 2 new investments in the first half of the quarter that will partially contribute in Q3. So we have limited operating history with either business at this stage. We keep this in mind as we think about how our business is financially positioned and calibrate. In our quarterly report, we provided a comprehensive description of baseline revenues, baseline calibration and their limitations. As of September 1, 2026, after the Tai and extensive acquisitions and using foreign exchange rates of $0.72 to the Canadian dollar, $1.16 for the euro and $1.35 to the pound. We've estimated that our baseline revenues for the third quarter of fiscal 2017 were approximately $181 million. Our baseline operating expenses were approximately $111.5 million. We consider this to be our baseline adjusted EBITDA calibration of approximately $69.5 million for the third quarter of fiscal 2027 and or approximately 38% of our baseline revenues as at September 1, 2026.

We're currently operating above our expected adjusted EBITDA operating margin range of 40% to 45% and our margin can vary in any period, given such things as revenue mix, foreign exchange movements and the impact of acquisitions as we integrate them into our business. For now, we're keeping our target range as 40% to 45%, particularly in light of the other stages of integration for Thai and extensive. However, we'll monitor how we're performing over coming quarters to consider whether any upward adjustment is appropriate. These remain uncertain times for our customers. It's a challenge for them to know what they can rely on in this global trade environment. Our goal is to continue to show our customers and other stakeholders that 1 thing they can rely on is Descartes. Thanks to everyone for joining us on the call today. As always, we're available to talk to you about our business in whatever manner is most convenient for you. And with that, operator, I'll turn the call over to you to manage the Q&A portion of the call.

[Operator Instructions] With that, your first question comes from the line up Chris Quintero with Morgan Stanley.

Maybe first on Tai, really interesting acquisition there. I know you already have made some acquisition in this kind of broker TMS kind of space. So curious from your perspective, what about Tai is really additive and complementary to the rest of the portfolio there?

We think their software is best-in-class. We think that their AI capabilities are far ahead of their competitors. They obviously have a great growth rate -- and we thought they would be a great fit with some of the other tools that we bought in that space in the past, MacroPoint and Aljex my carrier portal, et cetera. So -- we're looking forward to it. We heard great things about them before we bought them, and those things appear to be true to us now that we have. So we're excited about that. .

And then maybe if you take a step back and look at the overall M&A philosophy. Obviously, these are some bigger deals than what you've done recently. But curious, any change around your M&A philosophy? And what gives you confidence around the integration and synergies you can get from these bigger deals here?

Well, we see less people showing up in the deal, and therefore, we see the prices coming down as they have in the public markets usually the private markets follow in turn, and we're starting to see that right now. And I think that played a role in being able to get these deals done. And I think player role in some of the future deals you see. We went through this once before in '08, '09, '10 -- and I don't know if the times are as bad right now, but there's a lack of confidence in software companies right now that's probably helping us get acquisitions done in harming all public companies and therefore, private companies in that sector. for the foreseeable future. So as 1 of the guys that's flushed with cash, we -- and also believes in our space, we look around and say, "Hey, we think we're going to be winners in AI. What are the companies out there do we believe will also be winners in AI and how can we come together with them at a reasonable price to get things done.

An attitude like that and being in a position like that back in '08, '09, '10 in we thought really benefited us in the last 10 years as we bought stuff for very reasonable prices that ended up being big contributors to our business, and we'd like to see that be repeated again here.

Your next question comes from the line of Dylan Becker with William Blair.

Appreciate it did a nice job here. Maybe, Ed, I think you had defined -- this transitioning to a system of action, and you called out a number of interesting agentive use cases, but how do you think about kind of the opportunity more broadly to pair your network data with workflows and intelligence to make those decisions actionable how that kind of drives more value for customers moving to outcome-based pricing. The kind of areas you see that first resonating maybe more broadly and obviously how that kind of supports your conviction in aggregate platform differentiation over time.

We think AI is going to change everything. And that comes from our guy if you've known me for a while that it doesn't believe that all the time. Things like blockchain, people were telling me it's going to change the world. I don't know, we didn't agree. And we're open about say-so drones, I had to answer that question for years. And AI comes along and then we go, hey, I think this is going to be everything just like in 1999, if you said, what's your Internet revenue if I've given you a number, it would have sound silly 5 years later when everything was Internet revenue. And I believe the same is going to be true here. we started to try and break out AI revenue. We talk about AI as if there was some separate thing that was going to happen in the business that we think it's going to be everything in the business 5 years from now.

We think it's going to rapidly and significantly enhance our ability to make our customers' lives easier, more efficient and as a result, help them make more money and service their customers better. And we believe it's going to be a part of everything we do very quickly. and we're headed there. And we believe we have a great shot because of the data that we have in our network and all the customers we have and all the functionality we provide them to put this together and make it work better than it does today in ways that you might not even be able to match it today as these things start to compound on each other. So we already have guys around here that are starting to see the future as we're building more things and going, oh, my god, if I put this in and this together, this could change everything for our customers. And we're starting to see that, and we're getting excited about it and trying to get there as fast as we can. Acquisitions like Tai are all part of that.

All right. That's really helpful. And then maybe 2, you called it out on kind of the tariff dynamic. You're starting to see some customers kind of get those refunds. At the same time, obviously, continues to kind of evolve. But I guess just how your conversations with customers progressing how they're thinking about deploying the refunds that they received into technology capabilities, just maybe kind of netting out some of the puts and takes and how they're helping -- or how they're thinking about navigating kind of the dynamic backdrop.

We're hoping to get it back in a lot of cases. I don't know that we've talked about what they're doing with it. The investments they're making in AI, I mean, the payback is so fast when they're doing something with us, we're giving the ROIs that are almost immediate because we charge transaction prices, right? It's charging to do something that you would add have a person spend an hour doing and I'm charging $0.25 for doing it. that's a pretty immediate payback. You don't need to be saving up to do that. And we think of it more like that. I'm not looking at the refunds like give that back to me. In fact, in a lot of cases, they're probably supposed to be giving it back to their customers. So we tend to not talk about that refund other than to help them get it back. .

And your next question comes from the line of Cole Couzens with Wolfe Research.

I saw the 9% -- or heard about the 9% services organic growth in the quarter. Can you talk about how much of that is underlying market trends versus share gains? .

I don't know if I have an exact breakdown. I mean, I can tell you that the -- there's not been a lot of growth in trucks and air volumes. There's been a little bit in ocean. So I would say we're selling a lot more stuff right now. Our sales force is doing really well, and we're selling a lot more things to customers. A lot of it AI kind of related stuff. And some of it's taking stuff from customers. I don't know. If I had to guess, I'd say it's 1/3 of its share gains from competitors and the rest is probably not so much transaction related, but just selling more of our tools to our customers, which may drive more transactions, but not necessarily becoming in the industry to have more transactions to get there. .

Sure. And then maybe looking forward, I know you've talked a lot about how the complexity of the shipping environment is kind of helping you guys at the moment. How do you foresee things playing out through the end of the year and into next year? If there is some sort of de-escalation at any point or even without it, is there any insight into how you expect things to trend talking about the worse just organic growth trends, like what's the outlook going forward? Does it seem like it's going to continue to be challenged? Did you exit in a better place -- just any insight as to I mean, look, we're real with 9%.

Thanks. We're happy with 9%. I don't know what the growth rate is going to be in the future, but I do know we -- 2 very good quarters a year ago in Q3 and Q4, so we're up against the challenge to provide the same growth rates just because the quarter really picked up. We'll see what we can do here. Lock in 9% for the rest of my life, I would take it right now. That's a great number for us, especially when we're trying to grow 15% EBITDA to have 9% organic growth in pockets great. I hope we can keep that up. Could it get better? Of course, it could. I mean we've seen it a couple of times in the last 10 years around the pandemic, get much better than that even. I don't want to count on that. And it doesn't feel like it's -- business is turning down right now, but like it's going quite well. So I don't know will that turn around 1 day, I'm sure it will, but I don't see it in sight right now.

So we're happy about that, and we're trying to continue to run a good business and not get ahead of ourselves, knowing that we don't know what's going to happen a year from now.

And your next question comes from the line of Stephanie Price with CIBC.

Congrats on the 2 big deals recently. Just curious in the current M&A environment. If you're more interested in the growth year kind of names in the pipeline or opportunities that are maybe a bit cheaper but need to be restructured. It sounds like you got 1 of each in this quarter, and just curious how you're thinking about it here?

Well, we'll do either. We certainly over the years -- 15 years ago, we used to do a lot more fixer uppers. We started to buy growth year assets and have to pay up for them, but we found a lot of success in doing that. Now in this environment, we're looking probably first and foremost, looking for stuff that we think is going to help us grow and looking to pay a better price than we may have had to pay a couple of years ago because what's happening in the market, and we see what's happening in us because of AI and see what happened to the rest of the market because of AI. I don't believe that the reaction they're having to us is indicative of what's going to happen in the long run. I think we're going to benefit from AI. And the bet right now is that us and every other software company at the time, it's going to suffer from it. And I don't know about everyone else, but I think we're in pretty good shape because of it. And in fact, I think we're going to benefit from it significantly.

So we're looking to pick up assets that we think are going to do the same. And it would be nice if they had growth, and it would be nice if I could pay a reasonable price for them because I don't like where we're trading at right now. And so I don't want to have to pay up for someone else. And the fact that we're trading at a lower multiple than we were historically helps us in making an argument someone else today, your company may not have been worth what you thought it was. And that helps us get a deal time, tie and extensive post, we probably wouldn't have been able to get done a couple of years ago because the multis they wanted we did not believe it. And because of what happened in the market in the last year, we were able to get a deal on itself from when we thought it was fair. And so we did that.

So in that kind of environment, would you be willing to take on leverage to if you continue to see compelling M&A opportunities? And what kind of -- do you have a target leverage ratio that you'd be to fill up to?

I'm sure we take on leverage to do it. It would depend on the asset. We'd have to -- obviously, we have to say on leverage do we have to factor that into the calculation and whether it's worth it. So it has to be something we think it's a good deal. But we've always been comfortable going up to 3x. We've done it a couple of times and paid it off very quickly. We make a lot of money right now, and we're making $100 million a quarter. That's -- that's a lot of money to spend on acquisitions. So if we happen to get something big enough that we needed to lever up to do it, we would go up to 3x to do it, and we'd probably spend our time paying it off pretty quickly. .

And your next question comes from the line of Lachlan Brown with Rothchild & Company.

Project the recent acquisitions will likely carry lower margins in that 40% to 45% range. Maybe just what impact should we expect these deals to have on adjusted EBITDA margin in the short term? And any color on the duration of the cost synergy ramp.

I'm going to pass this to Ed but I would just say that they don't make as much money as a percentage of revenue as we do. So it's going to take it down. I don't know how much more I want to say about it. .

Yes. Look, I think it's -- we still don't know exactly where they'll settle. That's something we'll work on as we get through the integration. But -- and there is there's always a bit of work whenever we combine with someone. It's rare that we find someone that's got the same margins in on day 1, but we look to have a path to get there as they scale. And I think the there'll likely be an impact this quarter. But as you can probably see as you take a look at the calibration compare 1 quarter to the next, it's not a massive impact.

And I thought that was an interesting comment made by expeditors recently that AI is contributing 50% of the growth in U.S. net imports. You've obviously delivered quite robust organic services growth of 9% great over the last couple of quarters. So I guess my question is, how much of a tailwind is the AI supply chain being the GLN network and if so, is there any outlook on the visibility here?.

Well, you heard me mention it in my prepared remarks, so enough to get nothing mentioned. I wouldn't go buy in the stock ever. It's -- but it's been helpful to our customers and there for help with us.

And your next question comes from the line of Kevin Krishnaratne with Scotia Bank. .

Thanks for all of that commentary on the various agent solutions sounds really interesting. I had a sort of a 2-part question on talent. As you start introducing more and more of these solutions, does that require any change in the go-to-market, maybe having more technical sales, sales engineers with AI experience. Just wondering anything to comment there on customer education. And then second part is, you yourself are a company with a wealth of knowledge and logistics and supply chain expertise, that's a hot area and companies are looking to build competencies there, whether that's forward-deployed engineers.

Let me just get to the first question as I'm not as fast as us. So as far as sales reps going, I don't think the sales reps are going to be out talking about the -- all the things that AI does at any kind of technical level. I think it's going to be delivering -- talking about delivering functionality and solutions that the customers might not have imagined were possible because we're using AI. And I don't need to explain the technology to them. I never did. And I think, no, we have salespeople that are here a long time. We go to great lengths to make sure we keep our good salespeople. And that means that there are all experience and understanding logistics and supply chain I just heard someone -- 1 of our sales managers around here saying we win most deals because we know more than the other guys about what our customers do for a living. And that's what we need to know to walk in and explain to our customer, how we're going to solve a new problem using AI and the technology behind it is it's not going to be described in any great to -- so that's the answer to the first question. Can you ask your second question again? .

Yes. No, great. That's perfect. And I think related to that then, you've got quite a bit of knowledge and the expertise in supply chain and logistics. And so I'm wondering how you think about talent retention because some of your employees are probably in pretty hot demand. So I'm just curious if you're seeing anything there, anything competitively from other companies trying to poach your employees and just what you're doing around talent retention?

I mean we're a pretty good company to work for. I mean it's been growing and growing and growing for 20 years in a row. So I'm not saying we won't lose anyone to another company that's seen as good in this space. But I think we're a pretty good company to work for, and I would hope that our employees would agree with that and want to stay here. You can see we don't have a lot of people for the revenue that we produce. We manufacture our own software. AI is giving us the by manufacturer even more. But -- we're not laying off anyone because we're just building more and more functionality with the people that we have. So we're giving everyone that we have an opportunity to get involved and learn more and become more and more valuable to our company. So I hope that makes them want to stay. And I never heard otherwise. .

Got you. Appreciate that. Maybe just on GTI, -- you called out that as a source of strength again. What are the drivers there if you look into the revenue there? Is it customers moving into higher tier packages? Or is it more net new logos? Just sort of what are the contributions there of that growth?

Well, I mean that's what I was going through on the call. And I think I think I laid it out is tariff changes, and they're changing rapidly. That's 1 of the drivers, customs and export control enforcement that's stepped up and what that causes our customers to have to deal with. And that the audit burden has increased as they have more enforcement personnel. So those are the 3 things that really pushed it out. And if you go back and listen to the beginning of the call, I'd lay out in pretty explicit terms.

But are there -- are you seeing net new customers coming on.

Always -- and there's constantly new customers coming on in that business is One of the ways we make money and then existing customers buying access to more information just the other way. People rarely leave. That's the other side of it. .

And your next question comes from the line of John Shao with TD Cowen.

I just wanted to revisit that 9% service organic growth, which is the same as last quarter. So my understanding is the freight environment is still weak, but it did get incrementally more favorable that should create a bit of growth acceleration there. Just curious what would offset is some of the organic growth numbers unchanged. Is that FX?

Well, firstly, it's not FX because...

There's a lot of in the air in that question, right? In the first example, you're comparing Q2 to Q2 and then Q1 to Q1. So that's I'm comparing to a different quarter when I'm saying what the growth was. And it's a quarter or a year ago. So you'd have to think about what has happened in each of those quarters to comment on it. Otherwise, I don't know that I agree that it's got a whole lot better for the customers, maybe in 1 area, it got better than truck and net could argue got worse. So I don't know that I agree with your initial premise. .

Okay. That makes sense. And my second question is, the platform holds a lot of proprietary data. So could you maybe talk about your strategy to monetize that data point? And can I say now it's part of your AI strategy?

Sure. We have all kinds of different data. Some of it is more something that customers hold more dear and we shouldn't release and other stuff is as long as we anonymize it, we can use it to every customer's benefit, but they all have to share their own data, right, they're all sharing the same thing. We're not going to tell someone what 1 carrier charges for something that we're not releasing anything that they hold near and dear. And that combined with a bunch of data that's publicly available data that helps us as well. And we've been taking that data experimented in a way -- use it in ways that are very helpful to customers.

So I think you're going to see us do something like that. And it's not that we're going to start arguing with customers about can we release your proprietary information. We're going to be sharing stuff that's anonymized and as we always have, really, but now with more capability to help customers more quickly. And remember, the same customer that's sharing his data anonymized is also getting access to everyone else's data anonymized to make good decisions as well. And I don't think our customers are going to pro.

And your next question comes from the line of Mark Schappel with Loop Capital Markets. .

Ed, as you build out your -- build out the LSP portfolio through acquisitions like TI and extensive. What do you see as maybe the biggest remaining product gaps in serving LSPs? And then also, should we expect future M&A to continue to prioritize LSP specific solutions versus investing in more capabilities into shippers?

No, I think you're going to see us do both. I mean, we service carriers, LSPs and big retailers, manufacturers, call them shippers. And I think you're going to see us continue to try and fill out the entire space, right? We're trying to be the global leader in logistics and supply chain technology. And to do that properly, we think we have to be exactly what we are large, global, neutral and serving all 3 of them and building out functionality for all 3 of them that makes their lives easier. And I think that's the way you'll see us handle it I don't know if we think of it like we have any gaps, areas we look to do more and I probably could take the section I had at the beginning of the call that talked about where we were doing well.

And those are my first choices combined with the network as to where to expand, but we'll look at anything that's available in our space and see if we think there will be a help. And if we can get a deal done with them, we will.

That's helpful. And then in your prepared remarks, you called out areas of your business where you saw strength in the quarter like global trade visibility routing. What parts of the business saw, let's just say, less strength in the quarter?

No, I think just some of the nodes we've talked about where you continue to see a little pressure on their space is a bit mixed. The truck volumes themselves are a bit depressed. In the face of that, we continue to do well in areas like MacroPoint because we provide a better solution than our competitors.

But we do better if they were doing well. Yes, exactly. .

And your next question comes from the line of Doug Taylor with National Bank Capital Markets. .

This is Jack turn on for Doug. Yes. I mean in the prepared remarks, you guys noted that you're seeing some good demand despite some pressure on shipment volumes. So I guess it kind of relates back to your last point, but also if volumes recover from here, I guess, should we expect that to add another leg of growth on top of the complexity driven demand? Or would that just simply replace some of the current benefit? .

No. I think the volumes inferred. -- you'll see our numbers improve our growth rates will go up in all likelihood. We're really happy we're getting 1% growth in a lackluster transportation market. .

Okay. And I guess my next 1 or whatever you guys can say, just on time extensive, can you guys give us any maybe framework for the growth profiles and then how the valuations for that would compare to, I guess, what you've historically targeted?

They're largely in range with our historic targets. So they may be adjusted a little lower for the market right now, but let Ed say anything else we're allowed to say about that.

Yes. Look, we don't comment on specific details on acquisitions. But as you know, we're disciplined buyers. We'll continue to evaluate transactions with the same guiding principles we're always conscious of the price environment and which is more favorable now than it was a year ago. So I think when you look at those 2 businesses, both have a characteristic that we look at and say, we can grow those businesses. And there is no acquisition we will do if we look at the business, and we think it's going to shrink as part of our ownership. That's a key part that we look at. I think if you're looking around, you probably hear that Tai was probably a faster grower than extensive. But other than that, any acquisition we look at, it has to be -- it has to have an attributes that we look at and say as a combined business, we can grow this business. And for both, we feel that.

And your next question comes from the line of Robert Young with Canaccord Genuity.

Ed, in the prepared comments, you said AI agents enabled tracking on 26% more loads than in Q1, a sequential growth. Is that just AI agents growing 26%? Or is that overall? I'm trying to understand that 26%. What is that growing?

It's loads that were tracked as a result of an AI agent helping initiate that load. So the loads initiated by agents, which is still a small percentage of our loads, but that grew sequentially 26% quarter from the previous quarter. So it's just a demonstration the agents are having a real impact, and we've seen that improve from last quarter to this quarter. It's still a small part of the overall volume in MacroPoint though.

Great. Great. Okay. And then second, the capacity for integration of these large acquisitions. They both overamp a bit with existing functions. And you said you had financial capacity -- but what about the operational capacity in the M&A team? Is there -- does that need to grow? Or have you got everything you have is everything in place and I'll pass line.

Yes. We've been building our team to be able to do this kind of thing for years. The beauty of our business. Both these businesses sit within there's some common attributes but sit with different, let's call it, business leaders internally that have bandwidth to help make sure that they integrate even when you look at the driving acquisition from July as well. So we're comfortable we'll be able to digest them if we did 10 at the same time, you might get a different answer from me. But we feel good about where we are now. And we've been making sure for a long time. We've got a team that's able to handle more at 1 time, and we're feeling good about it.

Well, if you continue at the current pace, you could be at 10 by the end of the fiscal year. And so is that something that's possible? .

I would say anything is possible. It's not necessarily that easy as possible. One of my favorite pass versus anything is possible. So yes. Yes, -- we certainly -- yes, we'd love to see it that way.

And I'm showing no further questions at this time. I would like to hand it back to Ed Ryan for closing remarks.

Thanks, everyone, for your time this afternoon. Hopefully, we'll get a chance to see most of you as we make the rounds this quarter and look forward to reporting back in December on Q3. Have a great night. .

Thank you, presenters. And ladies and gentlemen, this concludes today's conference call. Thank you all for joining. You may now disconnect.

Hello, and welcome to the Annual Meeting of Shareholders of the Descartes Systems Group, Inc. Please note that today's meeting is being recorded. If you participate in today's meeting and disclose personal information, you will be deemed to consent to the recording, transfer and use of same. If you disclose personal information of another person in today's meeting, you will be deemed to represent and warrant to Computershare and the corporation that you first obtained a required content of the disclosure, recording, transfer and use of such personal information from all appropriate persons before your disclosure. [Operator Instructions]

It is now my pleasure to turn today's meeting over to Eric Demirian, Chair of the Board of Directors. The floor is yours.

Good morning, everyone, and welcome to the 2026 Annual Meeting of Shareholders of the Descartes Systems Group, Inc. My name is Eric Demirian, and I'm Chair of the Board of Directors of the corporation. Also with me on the line are Ed Ryan, our CEO; and Peter Nguyen, our Corporate Secretary. The remainder of the Board of Directors is also on the line that they will not be in speaking roles today during this meeting.

This meeting will be primarily focused on the formal business required at an Annual Meeting of Shareholders as outlined in the notice of meeting. And then we will open it up for a question-and-answer session, should shareholders have any questions for myself as Chair or for Ed as CEO.

I will now ask that the Corporate Secretary provide some instructions on voting procedures, and how we will handle Q&A.

Good morning, everyone. On the virtual meeting platform, you are logged into, you should see 4 interactive tabs in the top-right corner of your screen. To vote on any matter, click on the Vote tab to submit a question, click on the Q&A tab and then use the chat feature within that screen and your question will be directed to Mr. Demirian or Mr. Ryan to answer at the appropriate time. The voting screen and the Q&A screen are not activated for any of you who are logged into the virtual meeting as a guest.

The meeting will now come to order, and I will ask Peter Nguyen to act as Secretary of the meeting. Unless there is an objection, Dale Loyol of Computershare Investor Services Inc. will act as scrutineer for the meeting.

During the question-and-answer portion following this meeting, we may make statements containing forward-looking information. Displayed on the screen is a cautionary statement regarding such forward-looking information. Please take a moment to review the statement, which is also available on our website. I have been advised by the Secretary that the notice calling this meeting, together with the further applicable documents have been properly sent or otherwise provided to each requisite recipient. These materials are also posted on the Investor Relations section of the corporation's website at www.descartes.com.

Accordingly, unless there is an objection, Dale Loyol will dispense with the reading of the notice of meeting. The scrutineers have provided me with the preliminary report regarding shareholder attendance at the meeting. And accordingly, I declare that the requisite quorum of shareholders is present and that the meeting is duly and properly constituted for the transaction of business.

I direct that the confirmation of mailing of notice of the meeting and scrutineers' complete report on attendance be attached to the minutes of the meeting. There are several matters that must be dealt with during the meeting. In order to expedite these matters, certain persons have been requested to put forward the applicable motions. Shareholders may make comments specific to these motions prior to the vote, but we will address any comments on general matters during the question period to be held following the meeting. Should you like to address the Chair on any motion, we encourage you to type in your question or comment in the chat feature under the Q&A tab now, indicating the applicable item of formal business.

If there is any discussion or question, the secretary will read the question allowed at the appropriate time. Minutes of the last meeting of shareholders of the corporation are available to all registered shareholders upon request from the Corporate Secretary. Unless there is an objection, I will dispense with the reading of the minutes of such meeting. We will conduct the votes on the matters before us by a poll. The poll will be open for all resolutions at the same time. This will allow you to choose to vote on each motion immediately or wait until conclusion of the discussion on each motion prior to casting your vote.

The first item of business is the presentation of the Corporation's consolidated financial statements for the period ended January 31, 2026, and the auditor's reports thereon. Unless there is an objection, I will dispense with the reading of the auditor's reports. The next item of business is the election of directors. The number of directors to be elected at this meeting has been set by the corporation's Board of Directors at 9. May I have the nominations?

Mr. Chair, I have received a request from Scott Pagan, a shareholder and the President and Chief Operating Officer of the corporation nominating each of the persons specified in the management information circular delivered with the notice of meeting, namely Deepak Chopra; Eric Demirian; Dennis Maple; Jane Mowat; Chris Muntwyler; Jane O’Hagan; Edward Ryan; John Walker; and Laura Wilkin each to serve as directors of the corporation to hold office until the close of the next Annual Meeting of Shareholders or until their successors are duly elected or appointed in accordance with the articles and bylaws of the corporation.

As the corporation did not previously receive timely notice of any further nominations of persons for election as directors of the corporation as required by the advanced notice provisions of the corporation's bylaws, I declare the nominations closed.

Do I have a motion for the election of the proposed nominees?

Mr. Chair, I confirm that we have received a motion from Scott Pagan that the 9 persons nominated as directors be so elected.

Thank you, Mr. Secretary. Before I call for a vote on the motion, is there any discussion of this motion?

Mr. Chair, there is no discussion at this time.

As there is no discussion, I now call for a vote on the motion before the meeting. Would all registered shareholders, duly appointed proxy holders, please enter your votes using the vote tab within the virtual meeting platform.

[Voting]

The next item of business is the appointment of the auditors of the corporation. In order that a vote may be held on the matter, I request that a motion be presented.

Mr. Chair, I confirm that we have received a motion from Scott Pagan that KPMG be appointed the auditors of the corporation until the close of the next Annual Meeting of Shareholders or until a successor is appointed.

Thank you, Mr. Secretary. Before I call for a vote on the motion, is there any discussion of this motion?

Mr. Chair, there is no discussion at this time.

As there is no discussion, I now call for a vote on the motion before the meeting. Would all registered shareholders and duly appointed proxy holders, please enter your votes within the vote tab in the virtual meeting platform.

[Voting]

The next item of business is the consideration of the proposed continuation, amendment and restatement of the corporation's shareholder rights plan. A summary of the proposed changes to the shareholder rights plan are set out starting at Page 22 of the management information circular and the proposed formal resolution to be considered at this meeting in respect of those changes is set out on Page 23 of the management information circular. In order that a vote may be held on the matter, I would request that a motion be presented.

Mr. Chair, I confirm that we have received a motion from Scott Pagan with the shareholder rights plan amendment resolution as set out on Page 23 of the management information circular be approved.

Thank you, Mr. Secretary. Before I call for a vote on the motion, is there any discussion of this motion?

Mr. Chair, there is no discussion at this time.

As there is no discussion, I now call for a vote on the motion before the meeting. Would all registered shareholders and duly appointed proxy holders, please enter your votes in the vote tab within the virtual meeting platform.

[Voting]

The next item of business is the consideration of the advisory vote on executive compensation, also known as Say-on-Pay vote. While the say-on-pay vote is nonbinding, it gives shareholders an opportunity to provide important input to the Board regarding the corporation's executive compensation practices as disclosed in the management information circular.

The proposed form of Say-on-Pay resolution to be considered at this meeting is set out on Page 25 of the Management Information Circular. In order that a vote may be held on the matter, I would request that a motion be presented.

Mr. Chair, I confirm that we have received a motion from Scott Pagan that Say-on-Pay resolution be approved.

Thank you, Mr. Secretary. Before I call for a vote on the motion, is there any discussion of this motion?

Mr. Chair, there is no discussion at this time.

As there is no discussion, I now call for a vote on the motion before the meeting with all registered shareholders and duly appointed proxy holders, please enter your votes in the vote tab within the virtual meeting platform.

[Voting]

Mr. Secretary, before I close the voting on all the motions, has there been any further discussion of any of the motions?

Mr. Chair, there is no discussion at this time.

We will now allow for a few minutes for registered shareholders and duly appointed proxy holders to submit their votes.

[Voting]

I now declare the polls closed based on preliminary voting results provided to me by the scrutineers. I declare that all motions made today at this meeting have been passed with the requisite shareholder support and that each elected director received votes in excess of the thresholds established under the Descartes majority voting policy as described in the management information circular.

A report disclosing the applicable number of votes cast in favor of, withheld from voting or voted against each item of business at this meeting will be filed on SEDAR promptly following the meeting and disclosed in a press release to be issued forthwith following the meeting. As there is no other formal business that may be properly brought before this meeting, I now declare the annual meeting terminated.

As the results of the corporation's first quarter of fiscal 2027 were recently released and there was a public conference call to discuss those results, which is recorded and available for replay on the corporation's website, we did not intend to have management do any type of formal management presentation at this meeting.

But we will open up the discussion platform for a question-and-answer session. Should there be any questions from shareholders at this time. Please submit your questions through the chat feature within the Q&A tab and the Secretary will then direct your question to either myself or Mr. Ryan.

I have received a question directed to Mr. Ryan. You've talked about artificial intelligence as a potential tailwind for your business. Can you add some color on the areas of your business where you think customers will see the most impact?

Yes. Thanks, Peter. If you listen to the call, there are a number of areas where we're already getting great results in AI, areas where -- such as our MacroPoint solution where we're giving customers the ability to add users to the trading partner relationships very quickly, add trucking companies to the trading partner relationships quickly. We're also in a situation where I think in the long run, in a number of the areas that we do business, we're going to be able to look at the shipments on our network because we have probably looking at a month worth of shipments at any point in time.

And invariably, those shipments have problems. And our network, I think, over time, we're already starting to see some of these results is able to identify problems that they might be having on those particular shipment and use the network and all of its knowledge of where everything assets are going to be over the next 30 days to try and reconnect or reset up those shipments to operate more quickly. So they might have a situation where a plane or a ship is late to port, and we need to start making changes to fix that.

And because our network knows all the things that were supposed to happen and all of the possibilities that could happen in the future, we're able to rebook those shipments and put customers in a situation where they have a mistake in a shipment, and it doesn't cost them that much time. We think in the long run, that's going to be the biggest area to help us. But I'll leave it at that.

Mr. Chair, there are no further questions at this time.

Thank you to everyone for joining us today and accommodating this online format. We wish each of you all the best.

This concludes the meeting. You may now disconnect.

Good afternoon, ladies and gentlemen, and welcome to Descartes Systems Group Quarterly Results Conference Call. [Operator Instructions]. This call is being recorded on June 3, 2026.

I would now like to turn the conference over to Scott Pagan. Please go ahead.

Thanks, and good afternoon, everyone. Joining me on the call today are Ed Ryan, CEO; and Ed Gardner, CFO. And I trust that everyone has received a copy of our financial results press release that was issued earlier today.

Portions of today's call, other than historical performance, include statements of forward-looking information within the meaning of applicable securities laws. These statements are made under the safe harbor provisions of those laws. These forward-looking statements include statements related to our assessment of the current and future impact of geopolitical, trade and tariff and economic uncertainty on our business and financial condition. Descartes' operating performance, financial results and condition, cash flow and use of cash, business outlook, baseline revenues, baseline operating expenses and baseline calibration, anticipated and potential revenue losses and gains, anticipated recognition of revenues and incurrence of expenses potential acquisitions and acquisition strategy, cost reduction and integration initiatives, the approval and potential share purchases under a normal course issuer bid and other matters that may constitute forward-looking statements.

These forward-looking statements involve known and unknown risks, uncertainties, assumptions and other factors that may cause the actual results, performance or achievements of Descartes to differ materially from the anticipated results, performance or achievements implied by such forward-looking statements. These factors are outlined in the press release and in the section entitled certain factors that may affect future results in documents filed and furnished with the SEC, the OSC and other securities commissions across Canada, including our management's discussion and analysis filed today.

We provide forward-looking statements solely for the purpose of providing information about management's current expectations and plans relating to the future. You're cautioned that such information may not be appropriate for other purposes. We don't undertake or accept any obligation or undertaking to release publicly any updates or revisions to any forward-looking statements to reflect any change in our expectations or any change in events, conditions, assumptions or circumstances on which any such statement is based, except as required by law.

And with that, let me turn the call over to Ed.

Thanks, Scott, and welcome, everyone, to the call. Today, we are again reporting record quarterly financial results coming off a strong financial year last year. In Q1, we were ahead of our plan, which gives us even more room to make AI and other investments in our business. These are great results that I'm looking forward to walking through in quarter -- however, first, let me give you a road map for the call.

I'll start by hitting some highlights of last quarter. I'll provide some comments on how the numerous events in the world are impacting our business. I'll then hand it over to Ed Gardner, who will go over the Q1 financial results in more detail. After that, I'll come back and provide an update on how we see the current business environment and how our business was calibrated for Q2. We'll then open it up to the operator to coordinate the Q&A portion of the call.

Let's get into Q1. Key metrics we monitor include revenues, profits, cash flow from operations, operating margins and returns on our investments. For this past quarter, we again had record performance in each of those areas. Total revenues were a record high $193.6 million, up 15% from a year ago. Record high services revenues were also up 15% from a year ago, with our continued focus on generating recurring revenues. Record net income was up 34% from a year ago. Record income from operations was up 35% from a year ago.

Record adjusted EBITDA was up 20% from a year ago. Our adjusted EBITDA margin is at a record level of 46%. We generated $75 million of cash from our operations, up 40% from a year ago. to strong record results across all of these key metrics. At the end of the year, we had $377 million in cash, and we were debt-free with an undrawn $350 million line of credit. We remain well capitalized, cash generating, growing and ready to continue to invest in our business. We have a normal course issue bid that allows us to purchase up to 8.6 million shares before December2026. We've made some purchases since last reported, and I'll allow Ed to give you those details in a minute. But especially in light of how the business performed last quarter, we are optimistic about the Descartes' future and the normal course issue bid is a tool we could use to make further purchases.

I want to touch on 4 areas that helped this business perform well this quarter. The first is global trade Intelligence, which is one of the largest contributors to our services revenue and had a strong growth in the quarter compared to where it was a year ago. That's pretty intuitive if you think about what's happened over the past year has become increasingly challenging and then predictable to determine how to ship goods from point A to point B, especially if they need to cross borders. We've seen strong growth across the 4 core areas of our business or of the Global Trade Intelligence business.

The first is tariff and duty content, we believe we have one of the best real-time sources of global tariff and duty information. This past year, there have been huge and frequent swings in the tariffs and duties, particularly from large shipping or importing nations like China and the United States. As we said before, if tariffs and duties are changing, that's usually a pretty good sign for this part of our business.

The second is the sanctioned party screening business, where we continue to be a leader in sanction parties, we continue to see strong growth here as we help our customers navigate an increasingly complex sanction party environment stemming from the global, the current global geopolitical landscape.

Third, we have the foreign trade zones or FTZs. These are facilities where goods can be imported and stored and processed on a tariff-free basis until they're ultimately released from the facility for consumption in the domestic market where the facility your zone is.

With all the tariff uncertainty for imports in the United States, more and more companies have been pursuing this option for their business has proven to be a particularly lucrative strategy for those who defer paying any of the recent AIFA tariffs that were invalidated by the Supreme Court. By not paying the tariffs, these importers do not now need to go through the delayed process of trying to obtain refunds.

So stronger grower so far and with continued uncertainty about the legality and amounts of tariffs, one that we expect many companies will continue to pursue with our technology leverage for the operation of the foreign trade zone.

And the last one, number four, is data mine. Companies have adopted a myriad of strategies for dealing with tariff uncertainty whether it's different sourcing strategies, consideration of classification of goods or even shipping routes, the best companies are doing as much research as they can to help guide their strategies, and that's where data mine comes in. Comprehensive research tool to see how others are dealing with importing challenges. This continues to see good traction and is a good grower.

Second area of growth for us was the e-commerce entries. We continue to see overall growth in consumers embracing e-commerce. Even with the elimination of the tariff exempt [ type 86 ] de minimis program, imports have continued to grow coming into the United States. We have a premar solution for handling e-commerce imports in the United States using our net CHP system, particular strength in high volume and high velocity requirements. We're helping key brokers meet the demands of importers and these volumes are contributing well to our revenue growth.

The third area is fleet performance management and routing. We have market-leading solutions to help customers manage their fleets of vehicles. In particular, we have running and schedule and solutions that help companies figure out the most efficient way to make deliveries and reduce hours and miles driven to do that. There's always good demand for these solutions. However, the demand increases in periods where fuel costs increased running your fleet becomes more expensive and customers look to our solutions to reduce the amount of fuel they're using to make deliveries.

Cost consciousness for fleet owners is even higher given the inflation that exists in driver wages -- this wage inflation is driven in part by driver shortages, new U.S. regulations that have made it more difficult to quantify -- qualify to be a driver. And the final one is our Transportation Management where MacroPoint continues to be strong for us. MacroPoint provides real-time visibility to shipments brokers and shippers tell us the loads they want tracked. It's our job to get tracking information from onboard systems, transportation management systems and using our application or old-fashioned calls to drivers.

Over past quarters, we've enhanced our system of AI agents to interact with drivers to encourage adoption of our tracking app, helping us reach a segment of the market that was previously difficult to reach the scale. These agents have helped contribute to a higher percentage of shipments tracked than our peers, which in turn drives more people to our network. We've also released some new agents that help brokers manage current workflows on shipments, which I'll speak to further in a few minutes.

So this is really the principal contributors to growth. We were able to help our customers in a challenging rate environment. We generally saw overall shipment volumes down in the quarter with the biggest contributor to that decline being the war in Iran. Here's a quick summary by mode of transportation.

So in Ocean, the war in Iran effectively closed TheStreet from us and shipping in the region. -- shipments of oil, fertilizer and aluminum were among the most impacted imports to the United States. This disruption has had a volatile impact on wages and shipping with many avoiding the region because of the security risk and cost of war risk insurance. This has resulted in longer sailing times, reduced schedule reliability, increased fuel usage and costs, increased insurance premiums and additional congestion at transshipment hubs. The fuel cost impact was spread beyond the Middle East with European Far East seeing 25% rate increases. Spot rates for Far East -- continues to be high, costly many shippers to rethink their strategy for balancing contract rates and spot bookings, so overall, a very challenging ocean shipping market at the moment.

Next Air cargo, which has seen some mixed impact of the war and Iran temporarily closed certain aerospaces to flights with some estimating a temporary 20% decrease in available capacity. It also presents an ongoing security risk, fuel cost and availability have also made a prior mode of shipment. However, there have been some positives with ocean shipping struggling and economic conditions of volatile. Many have leveraged their MRO to move goods quickly and/or on short notice. It continues to be strengthening the shipment of semiconductors and AI infrastructure which are more appropriate for the MRO given high-value weight ratios and time of sensitivity.

E-commerce continues to thrive and air benefits from that because of short fulfillment cycles. Some inventory restocking strategies have shifted to smaller, more frequent orders which switches inventory to air promotion. So overall, despite the volatile impact of geopolitical tensions, air cargo has been relatively strong. or transportation.

So fuel and driver costs and driver shortages are having the biggest impact on U.S. domestic trucking, smaller carriers are struggling and it's pushing some capacity out of the market, but not enough to counteract the increase to shipping rates caused by fuel costs. So overall, we saw trucking volumes down 4% year-over-year.

With that review of transportation modes, the general theme is a tough and costly market to ship in, our customers are increasingly relying on us and technology to deal with this complexity and uncertainty. A key to our one of the keys to our customers managing a more complex world and rising research costs will be leveraging artificial intelligence technology. Our customers are looking to us to be a leader in AI to help them plan for and operate the future.

I spoke about this last quarter, but here are some of the reasons they're confident in our success. We are a critical logistics network relying on better world. We connect hundreds of thousands of companies. We sell complex enterprise problems for them that they can't solve on their own within their own enterprise. We have scale to process billions of transactions in a year. We deliver a reliable and stable solution at scale. We're trusted by our customers. We help them with compliance, a function that is risky to handle solely internally without leveraging a specialist. We have workflow and domain expertise for complex logistics processes. We have unique proprietary data that can deliver fuel and fuel better answers. Better answers mean increased operational efficiencies. We have a long record of investing in new technologies and businesses to enhance our service offering. We're financially stable and operate our business for the long term, and we have a broad portfolio of solutions that are ideal for those who need integrated logistics and workflows and processes.

Every day, we're managing on our use of AI technologies for our customers. We've designed our AI agent layer that will accommodate external and to Descartes agents accessing their functions and data on the Descartes Global Logistics Network. That layer orchestrates agents and the skills they call and it forces a policy, so it says who can do what and whose data and under what approval. It captures audit and observability so that every action is traceable and explainable and it manages the economics, the usage, cost attribution and billing.

We believe there's lots of value we delivered to our customers using AI agents. I mentioned the MacroPoint engine before However, we have a whole suite of transportation management engines, including calling drivers for location checks, gathering proof of delivery information for billing purposes, arrival and departure confirmation, getting truck rates to help with carrier selection, getting insurance certificates for Descartes. We have similar agent development and agent development in other pillars, including agents gathering service time information and fleet management, research, age and data mine, enhanced -- in-part screening to manage false positive, just to name a few. These agents are automating workflow and work that are designed to automate repetitive tasks that don't mean the creativity of a human and to service new opportunities for humans to consider new strategies and opportunities.

Some of the agents are sold to our customers while others are designed to increase adoption, velocity or traffic over the Global Logistics network. We believe that AI agents, whether they're ours or third-party agents with permission to access our network will play a big role in future efficient supply chain and logistics operations.

Because of that, we anticipate we'll continue to increase our level of investment in AI technologies. Some of that will come from increased usage of existing AI tools within our business to build out our AI agent layer from building and designing new agents from enhancing the functionality that we have in our existing customer applications from rapidly accelerating the interoperability of our solutions for making our network more secure and reliable and from delivering a better customer experience. However, we also anticipate that our M&A strategy will include detailed consideration of how potential partners will enhance how we're using AI to help our customers.

This past quarter, we completed the acquisition of Idelic, which brings new AI-powered technologies to our fleet management customers. deli helps our customers with managing the safety of their drivers. They have proprietary database of over 40 billion miles of data and telemetry on hundreds of thousands of historical accidents, which can then be leveraged to identify drivers of practices that may require further training or remediation to prevent future safety issues. That data is subset -- non-Descartes systems aren't trained on and allows us to provide better safety insights to our customers. And when combined with Descartes industry-leading routing planning and execution technology, this enables us to deliver a complete cutting-edge fleet performance management solution that uniquely incorporates driver behavior and safety singles into our robust operational data set. A big welcome to the Idelic team, and we're excited about what they can do for our fleet management customers.

I provided an overview of our approach with AI technologies and some of our investments. However, we're planning a comprehensive description of everything that the car is doing with AI in our in-person innovation form to be held in Chicago, October 6 through the eighth of this year. This is a big event we invest in to provide our customers and partners access to our people, our latest developments and plans and give an opportunity to provide direct feedback on where we are and where we're going. It's been a few years since we've done an in-person event of this scale. So we're very excited to host everyone and share how excited we are about our future. Please see our website for registration details.

So in summary, a strong Q1 with additional AI investments and a new acquisition, I'm excited about how the business is performing and the opportunity we have in front of us. So with that, I'll now turn the call over to Ed Gardner to go through the financial results in more detail. Ed?

Thanks, Ed. As Ed mentioned, I'll be walking you through our key financial highlights for the first quarter of fiscal 2027. We're pleased to report record quarterly revenues of $193.6 million, an increase of approximately 15% from revenues of $168.7 million in Q1 of last year. Our revenue mix in the quarter continued to be very strong, with services revenue increasing 15% to $180.5 million from $156.6 million last year in the first quarter.

Services revenue represents 93% of total revenue this quarter, which is consistent with Q1 last year. Removing the impact of both the recent acquisitions as well as a positive impact from changes in FX rates we would estimate that our growth in services revenue from new and existing customers, that is our organic growth would have been just over 9% this quarter when compared to the same quarter last year, and this is up from approximately 8% organic growth in Q4.

Professional services revenue and other revenue, including hardware revenue, came in at $11.5 million or 6% of revenue, slightly down from $11.8 million in Q1 last year, while license revenues came in a bit higher this year at $1.6 million versus $0.3 million last year. Collectively, our professional services and other revenue, combined with our license revenues, was up 8% this year and together remain approximately 7% of our total revenues.

Gross margin came in at 78% of revenues, up from 76% in Q1 of last year. The increase in gross margin for the quarter was primarily due to operating leverage from more organic growth and services revenue.

Turning our attention to the bottom line as a result of solid revenue growth, improved gross margin as well as controlled growth in operating expenses. Adjusted EBITDA came in at a record $89.8 million in the first quarter or approximately 46% of revenue, up 20% from adjusted EBITDA of $75.1 million in the first quarter last year.

From a GAAP earnings perspective, net income for the first quarter came in at $48.5 million, up 34% from net income of $36.2 million last year. With these operating results and strong collections from customers, cash flow generated from operations came in at $75.1 million or 84% of adjusted EBITDA, up 40% from operating cash flow in the first quarter last year.

Overall, as Edward mentioned earlier, we're extremely pleased with our operating results in the quarter. If we look at the balance sheet, our cash balances totaled $377 million at the end of April. As I just mentioned, we generated operating cash flow of just over $75 million in the quarter. Offsetting that was approximately $30 million in capital deployed on 2 tuck-in acquisitions and approximately $21 million on share buybacks under our normal course issuer bid. As we look ahead, we remain well capitalized and ready to continue to work on potential M&A activities in our space.

And a couple of more points as it relates to the remainder of fiscal 2027. Going forward, we expect to continue to see strong operating cash flow conversion north of 80% of our adjusted EBITDA and of course, subject to unusual events and quarterly fluctuations, including adjustments related to future earn-out payments that exceed our estimates made at the time of an acquisition. After incurring approximately $2.6 million in capital additions in the first quarter, we expect to incur approximately $4 million to $6 million in additional capital expenditures this coming year, mainly related to IT equipment persist. after deploying approximately $21 million on share buybacks in Q1 '27. We also note in our shareholder report that we purchased an additional 196,800 shares during May 1 and June 2, and we may see additional purchases under the NCIB program moving forward.

After incurring an amortization expense of $17.3 million in Q1 this year, we expect the amortization expense will come in at $53.5 million for the remainder of fiscal 2027 with the figure being subject to adjustment for foreign exchange changes and any future acquisitions. We estimate that payments of contingent consideration for earn-out arrangements for the balance of this year could be up to approximately $9 million, subject to any necessary adjustments resulting from the final earnout calculations.

Our income tax rate in the first quarter came in within our expected range at approximately 26% of pretax income, in line with our blended statutory tax rate of approximately 26.5%. For the remainder of fiscal 2027, we're expecting the tax rate will be in the range of 25% to 30% of our pretax income, which means it will be something on either side of our blended statutory tax rate. However, we should add that our tax rate may fluctuate from quarter-to-quarter from onetime tax items that may arise as we operate internationally across multiple countries.

And finally, after incurring stock-based compensation expense of $7 million in the past quarter, we currently expect stock compensation to be approximately $24 million for the remainder of fiscal 2027, subject to any forfeitures of stock options or share units.

I'll now turn it back over to Ryan to wrap up with some closing comments and our baseline calibration for Q2.

Thanks, Ed. As I mentioned earlier, it continues to be a challenging shipping market in large part because of the war in Iran impact on moving goods and tariff uncertainty that is ongoing. We expect that to be challenged throughout our Q2. There are also 3 new things impacting the market that I thought it should flag.

First is tariff refunds. Earlier in the year, the Supreme Court invalidated the EPA tariffs that had previously been imposed by the U.S. administration and required the tariffs that have been paid be refunded. That refund process is now in progress with some customers reporting that they're in partial receipt of funds where their businesses received these funds directly depending on whether they were paid directly or via broker, they may very much provide money for investments that weren't contemplated when the tariffs were in place. So there may be the potential for new technology investment opportunities for us with U.S. importers.

The second is broker liability. The U.S. Supreme Court has been unusually active in things that impact shipping. Recently, they determined that a freight broker may have liability for the negligent selection of unsafe carriers. This makes it very important for freight brokers and others selecting carriers to ensure that they're doing due diligence while hiring trucks to drive loads for them. We're able to help our customers with that using our transportation management systems and more specifically, our my carrier portal solution that performs checks on the suitability of potential carriers.

Separately, we expect that there will be pressure on smaller brokers in the market as they consider the cost of performing auditable diligence and increased insurance requirements to something that may ultimately impact the number of brokers that are in the market going forward.

And the third is new China regulations. There's new regulations from China designed to counteract what they consider to be proper territorial jurisdiction of the regulations of other countries. For international shippers with supply chain operations with ties to China, this could mean needing to navigate a web of conflicting regulations between China and other countries.

For example, a U.S. regulation against forced labor may prohibit U.S. entities from doing business with certain entities while a Chinese regulation may prohibit a Chinese organization from complying with the U.S. regulation that China considers to be extra territorial. So just flagging an area of increased complexity for our customers going forward and one that will require even more attention to the importance of global trade compliance solutions.

So it's a challenging macro environment for shipping with new things that come in to make it even ever-changing landscape for our customers, we keep this in mind as we think about how our business is financially positioned and calibrated. In our quarterly report, we've provided a comprehensive description of baseline revenues, based on calibration and their limitations.

As of May 1, 2026, using foreign exchange rates of $0.74 to the Canadian dollar. $1.17 to the euro and a $1.36 to the pound. We estimate that our baseline revenues for the second quarter of fiscal 2027 were approximately $169 million. Our baseline operating expenses were approximately $102 million. We consider this to be our adjusted -- our baseline adjusted EBITDA calibration of approximately $66.5 million for the second quarter of fiscal 2027 or approximately 39% of our baseline revenues as at May 1, 2026.

We're currently operating above our expected adjusted EBITDA operating margin range of 40% to 45%. Our margins can vary in any period, given such things as revenue mix, foreign exchange movements and the impact of acquisitions as we integrate them into our business. For now, we're keeping our target range as 40% to 45%. However, we'll monitor how we're performing over the coming quarters to consider whether any upward adjustment is appropriate.

These remain uncertain times for our customers. It's a challenge for them to know what they can rely on in this global trade environment. Our goal is to continue to show our customers and other stakeholders that one thing they can rely on is Descartes.

Thanks to everyone for joining us on the call today. And as always, we're available to talk to you about our business and whatever matter is most convenient for you. With that, operator, I'll now turn the call over to you for the Q&A portion of the call.

[Operator Instructions]. And your first question comes from the line of Dylan Becker with William Blair.

This is Jackson Bogli on for Dylan Becker. Ed Ryan, I think what's interesting is we've got so many different things going on with geopolitics, excuse me, and just changing supply chains overall. I mean, could you maybe try to contextualize at what point would that actually turn into a headwind for Descartes instead of it really driving interest on the platform? Just anything you could say about -- is there a point where the complexity gets too much and it starts to become a headwind for your business?

Well, I think it's not so much that the complexity gets to be too much. Most of the complexity helps us regardless of how much there is. where there is -- tends to be the more they use our software. What we've seen in the past and probably see as well, if you look back, if the complexity gets so much that it starts to harm the economy, we go right along with the economy pretty well. I mean -- ones down, people are shifting us stuff, and we don't do as well. And you saw that with the tariffs last year. I mean the U.S. put a whole bunch of tariffs in place. They were surprising to everyone, no one knew was going to happen next. There's a lot of uncertainty day-to-day and what was going to happen and it caused people to freeze.

And I think with everything that was going with AI at the time and today, we didn't end up in a recession because there were lots of good things going on in the economy as well. But make no mistake, people weren't shipping stuff as fast as they could have because they want sure what to do about these tariffs that were now subsequently invalidated and all are not in effect when we ended up having the -- clearer in theory, no one will end up having to pay them.

And at the same time, that complexity caused them to slow down their shipping decisions. And while we were benefiting on the one side from tariffs and duty rate provision, we were suffering along with everybody else when there weren't as many shipments moving around the world. So that's where it hits us. I don't think it's increased complexity doesn't necessarily -- generally keeps helping us to meter how much there is. But if it leads to a depressed economy, it hurts us and everyone else.

Got it. I think that makes total sense. Maybe for Ed Gardner, you guys have a really good capital position. You have the line of credit, really good cash position. it seems like there's multiple areas you could focus on for investment in the business and capital deployment. I'm just curious how you're thinking about the M&A landscape with the depressed valuations we're seeing as well as continuing to invest in the platform. Just curious to get any thoughts on how you're thinking about capital deployment going forward this year.

Yes. I think it's -- I don't think it changes that much from other years. Obviously, with the ability to build more faster with AI that changes the calculus somewhat, absolutely when we're looking at our buy versus build decisions. But the framework remains similar, right? We're still looking for great businesses that have some sort of proprietary unique data and deep domain expertise and very sticky customer base. So we're looking at capital allocation.

Now I think we see the opportunity to build more, build faster, produce more for our customers. And that changes how we look at some of the acquisitions, but there's still a lot of great targets out there. And I'd say we're very busy and active engaged looking at them from a value -- maybe just a comment on the valuation side from a valuation perspective, it's quite not unusual for the private markets who not necessarily go completely in sync and not necessarily as quickly as the public markets. So as the prices come down, it's not necessarily at the same pace, but we are certainly seeing them come down a bit, and we remain engaged in a lot of opportunities right now and lots of discussions.

The next question comes from the line of Chris Quintero with Morgan Stanley.

I wanted to ask about the quarter here, third consecutive quarter of organic growth acceleration, really great to see. But you all called out some challenges here, specifically called out Q2. So could you help clarify like do you expect some of the challenges that you've highlighted to impact the growth rate? Or are these really more opportunities for you to leverage your network to address some of these additional complexity that your customers are seeing?

If you know us, we're pretty cautious. We probably spend more time telling investors about the risks than most companies do in the software space. But you're right, things are going well right now, and I see a lot of potential for them to continue to go well in the future.

But still, I mean, even in this past quarter, I mean, this is not -- this is a great quarter for us. We were 9.5%, something like that organic growth on services. That's great. And we were doing that in a down freight market. And so [ 1.5 ] for the future quarters, I'm pointing out that, hey, we're still down freight market. And I don't know what's going to happen exactly either. But we're doing okay considering, and we're happy about that, but it'd be nice if everything is coming up roses. So just know enough to we always quick to point out the risks and stuff and make sure that we're always doing what we said we would do. We see that in the number of the way -- many of the ways that we produce our numbers, we're pretty conservative. So I think that's what you're seeing.

Got it. Okay. So mostly just conservatism here having some of the risks, but obviously, the business is doing pretty well here. as a follow-up, really great to kind of hear more of the momentum around your AI and agents. How are you thinking about the go-to-market motion as we start to grow some of these solutions out? It seems like a lot more software vendors are starting to pursue more of a forward deployed engineer type of model to help sell some of these solutions to customers. So curious kind of how you're thinking about that on the go-to-market side.

Well, I mean, we think we have a lot of solutions that we can go out and sell to customers and we are starting to get traction doing that. We have a lot of solutions that improve things for our customers internally without them really haven't signed up for anything new. If they're paying me to process a shipment, and they have some tool that figures they need to process a new shipment here because they had a problem with an existing shipment. I don't have a contract in place to do it. I don't have to sell them anything now.

The agent that we -- that I mentioned in this -- earlier in the prepared comments, I just get more -- that agent's job is to get more truckers online. Each truck where I get online is going to pay -- is going to be able to help me track a shipment that's going to get me a couple of bucks a shipment. And now that he signed up every time he gets a shipment I'm going to be able to track it. So is the gift that keeps on giving. We have agents calling these truck drivers. And you have to call them at the beginning of the call, at the beginning of the move, you can't call them with 20 minutes to go and move and start asking to download the mobile app. You have to get to them quickly.

And frankly, [ 4 ] years ago, we just want to be able to keep up and at least not cost effectively. And now all of a sudden, we can call the guy within minutes of them taking off, picks up a load and we're calling them right away, going, hey, kind of track that load for you. You want to download the app, and I don't have to call you anymore. I supposed to call you every hour and if you download this mobile app, I never call you again. And that's a pretty compelling argument for the truck driver, especially when he knows his contracted by MacroPoint in the past, I mean it's a no need for it. And we're logging the industry. And that alone has moved our track rates from 87% at 6 months ago to 93% and moving higher percent. Well, that's -- each one of those percentage points is a lot of $2 shipments that end up producing revenue for us. And so that's great. I don't know if I do anything and I'm just helping our customers and they're paying more and they're happy about it because they're going to attract more shipments.

And then finally, there's stuff internally, right? Where we will to build stuff faster than the ideas come out, and you heard us talk about this whole AI layer where we can more closely pull people into the network in an organized way do that. And that saves us money. It saves our customers money. It makes it easier for them to use our network. It makes it easier for us to provision services to them that they pay for. And I know the market thinks it's going to harm software companies that I don't know if I'm a software company. I mean, we have software, but I don't know if I'm quite the software company, the way everyone else is, we think of ourselves as more of a network data content provisions type of business. And that means we have a lot of proprietary data that can help customers make good decisions in the future. And frankly, if you look at our network, I know where all the shipments are supposed to be over the next month.

So that's pretty valuable information when things start getting master screen up in the supply chain and the decisions need to be made quickly that can save a customer a lot of money, and I can use AI to do that because I have all the data and no one else does. And I go -- I don't know what people think it's going to happen to everyone else, but I'm pretty sure we're going to benefit from that, and we're excited about it -- I'll leave it at that.

And the next question comes from the line of Lachlan Brown with Rothschild & Company Redburn.

You mentioned that the Q1 came in ahead of plan, noting the robust organic services revenue growth of greater than 9%. Could you just dive into the drivers in the quarter that led to the delivery above your prior expectations?

Well, and I covered it pretty well in the case. Global Trade Intelligence business did very well, as you might have expected. Our e-commerce shipment business -- what was formerly [ 536 ] filing has been booming lately, I mentioned on previous calls. We had a lot of -- we had [ 40%, 50% ] of that market. And when it switched from Type 26 to Type 1, a lot of our competitors couldn't handle the the speed with which those transactions had to be filed, they just -- they weren't really networks. They were software companies that were making these filings and when they had to do it in a different way, their networks fell apart and had a lot of those customers switch over to us so that we get a lot more market share out of it, and it's been a great business for us in the last year, and I suspect for a long time to come.

Our fleet management business has been doing well as it has for many quarters now and transportation management business led by MacroPoint has been doing great. In a down market, they were still picking up a lot of momentum and a lot of new shipments. Both signing customers and that agent that I talked about is that move from 87% to 93% is significant. That's a lot of money. And even in a down market, we were able to pick up more revenue than ever. So all that's added up to pretty good news for us.

That's helpful. I wanted to ask, in recent months, we've seen a few of the larger global logistics players doubled down on their technology investments and their longer-term AR strategies. I was wondering if you could provide some color on what you're seeing in the mid-market in terms of their pace of AI adoption. How are they responding to these larger players? And just any color on -- you're having on how Descartes can sort them.

As you might expect, it's very helpful to us, right? We help the bigger players in a lot of ways, they oftentimes the biggest customers, but then the midsize and smaller players have to keep up. And while the big players can't build some of the stuff themselves like the back office systems, the medium and small time guys really can't do that, and they need tools from people like us that help them keep up and I would always say to people, customers would say, I want a strategic advantage in my using software in my company, and I go, okay, great, here's a bunch of stuff you can use to do that.

But bear in mind, this isn't going to last forever, right? Every -- it used to be 7 years ago, if you had MacroPoint, you had a big selling advantage against the broker that didn't. Well, you don't have that advantage anymore. You have to have it now. right? Everybody has his ability to track a truck. And they're on to the next thing, right? And that's good for us, right? And we can kind of keep building tools that help people service the customers properly. And when everyone has those tools, it becomes table stakes to a certain extent, and then we have to go give them new tools to help them make the next advancement. I don't know that we're driven that way by big forwarders all the time. And we probably drive the advancements as much as anyone.

But sometimes people can build it themselves. It depends on what we're talking about. If you're talking about network service, they don't and they can't really build it themselves. If you're talking about a back-office system, sure, they can. They buy some stuff from us. They buy some stuff from other people, and they put it together and they have their whole back office infrastructure. As soon as they get out to need to communicate with other people, all bets are off, right? But they have to use a network like ours, they'll never be able to replicate our network.

I think are the big guys that the UBS, the DHL even the Amazons, they like to build a lot of stuff themselves. Well, they always end up in a situation where like, yes, sure, but you can't do it with the network, right? The number of actions you need to maintain it is not feasible. It's much more cost effective for someone who's neutral like us to do it for everybody and charge everyone a low rate to do it as a result. And that's -- that advantage has been the case for 25, 30 years. And I think with AI, it's even going to be more so, right. Most of the small AI players that we talk to that seem to be more or like features than companies they're coming to us going, hey, can I join your network? And I'm like, well, I mean not really have a customer that a customer needs to join the network. If they're using your software and they want to do it a new problem. But I'm not going to -- just helping you guys get business prices, giving you access to our network, it doesn't work that well.

So the whole thing is interesting. And I think it's says going to even further separate things to our advantage, but that's how we see the playing field playing out with regard to your question.

The next question comes from the line of Stephanie Price with CIBC.

Sam Schmidt on for Stephanie Price. EBITDA margins have been tracking towards top end of Descartes target range for several quarters. How do you think about this going forward? And can you talk a bit about high leveraging AI internally and how you're tracking progress on those initiatives?

Sure. Yes, I mean, we're up at 46% right how, we kind of -- we said the range 40% to 45%. And you at us do this in the past, we usually book through a number a couple of quarters before we start to move it up, just do the same here.

The other things that kind of affected the big things are FX and acquisitions, and we're up at a pretty lofty EBITDA margin now we're not going to find many acquisitions that will be accretive to our EBITDA margin, not that that's a problem. It's just that if I buy some company that makes 25% EBITDA margin and with plans to increase it? That's great for our shareholders as long as they pay the 25% price for it. But it also drags by 46% or a decent size company down at 44%. And I don't want to offer to a number that we're going to miss. And we want to provide consistent answers to our shareholders. And if we tell a number, we were either in that range or beat that range. And I'm not -- I apologize too much for -- we're only being about a point right now anyway. But I don't want to miss the people.

With regard to AI in relation to this, yes, we're seeing -- we're way more efficient or let's just say, we can produce a lot more stuff with the people we have. And we'll see how this plays out. But I think right now, we're going while I see other people laying employees off us, hey, I mean, you use an AI and now, I don't need as many player. I think we're inclined to go the other way right now and saying I'm using AI, and it's producing a lot of productivity enhancements and I'm using that to produce more software. And we have that luxury goods were in the 45% range of 46% range right now. If someone is in the 25% range and competing with us, there is a significant disadvantage, especially if they're trying to deal the same thing we are, which is use our profits to buy more companies. Well, if you're making half of my profit, you're not going able to do that as effectively as we are.

And we're inclined to take the extra right now and produce more software for our customers to make sure that we continue to be a leader in this space as a result. And I don't know if that changes in the future, maybe I have to take a look at it over time. But right now, I think we have a lot of good ideas and more good ideas than we have time to produce them. So why do I use it to cut any cost, I think I'm using it to produce more stuff because I think that stuff is going to produce more revenue for us in the future, and we're excited about that.

That's good color. And then maybe 1 more for me on market share gains in the quarter. Can you comment on how those contributed to organic growth and how you're thinking about opportunities to take share at this point?

Yes. I mean -- mentioned this in previous calls, I don't want to get into maybe competitors and stuff like that. But we -- certainly in the TMS space, in the routing space, some of the things where we're the market leader, and times have been tough over the last year for a lot of companies. I have 300 and 400 products that spread it out over and we're not materially harmed even when things got tough. I mean maybe things were tough a year going. I went -- they were tough but we're still making something in $90 million a quarter. So let's not get ourselves, we're doing okay.

We have competitors out there that when we take business around -- I mean they only have 1 product. I mean that's their stuff. And a lot of these guys are high flyers that have never seen a situation where they were shrinking. And all of a sudden, they are, and it causes real problems inside the company. The stock is not worth what it was. The shareholders are furious and the shareholders overpaid to be in the business and their employee stock is not worth in anymore. And they can't believe that they were worth $2 billion at one point. And all that happened was the growth rate went from 30% down to almost 0 but everything else was still fine.

But when it went down, they had to stop growing stuff growing, stuff having the money to buy more buying them more stuff they had to start cutting costs. And usually, the guys that are high flyers are not good at cutting costs, and they really struggle to do it, and they just can't imagine. And all those things add up to help us quite a bit. That whole company gets to more or less when that happens.

And fortunately for us, we're not in a situation where we're facing anything like that. Even when times were tough last year, they weren't that tough for us. Most of the business was still looking up. And I think it's a testament to the things that our guys have built. They've built something big to solve a lot of problems. And has a chance to succeed in many areas even when times are pass some of our businesses are doing great. So not everyone has that luxury.

The next question comes from the line of Mark Schappel with Luke Capital Market.

I was wondering if you could just walk us through the key puts and takes you observed in the air cargo business this quarter that you referenced in your prepared remarks. And then also with respect to that, you also noted that your trucking business is down about 4% year-over-year. And what would that decline translate to in your ocean shipping business?

Okay. I got you. All right. So let's talk about the -- one first. The Iran war, especially in the beginning, had a lot of flights not being a lot of fly over a rand and -- or the, let's say, anywhere over that area. Well, you've got Emirates there. You've got at the -- had, you've got several of the biggest air cargo carriers in that region, and there's like 1/3 of the map that can't fly in that direction when they're right there. I mean they're an Abu Dhabi or Dubai or whatever. So it's tough for them. And they had a lot of late cancellations as a result. And they started moving planes around and trying to get -- but that's tough, right? It doesn't happen right away, and you have passengers that are expected to be on one type of flight and all a sudden that flies not available anymore. And the cargo goes along with it.

So that was a headwind for Air business. At the same time, some of the stuff that we mentioned in ocean. People get into these situations or companies getting to situations and they go, there's a lot of cargo system in the middle, right, I could fly at air or I can move an ocean depending on what's going on. And I think for a while, people started gravitating towards there in that situation because if I was just describing, the air carrier is in a bit of a pickle. The ocean carriers were in a much worse pickle. We have to avoid that entire region. Okay. Great. Well, the option then is to go around the -- keep on. Well, that's 10 more days. And then they start charging more for the stuff. And then if you're the shipper, you're thinking what's easier, the air shipment is usually way more expensive, and now it's not that much more expensive because the ocean carriers take a lot of money.

And so that ended up being a little bit of a -- carriage and but also took some capacity out of the ocean space and help them raise prices that maybe they didn't suffer as much. And the other carriers, we're able to pick up some business, which is great for that.

On the truck side, probably to answer your question, that 4% down. It probably doesn't translate that much in the arenas mostly probably related to domestic shipping. I already guess some if I told you, but I had to guess, I'd say something like [ 100% ] nothing big.

Yes. And just to clarify on that, we were talking about the truck market in the U.S., not the daycare truck market or transportation management business.

And the next question comes from the line of Kevin Krishnaratne with Scotia Bank.

This is Richard on for Kevin. So Amazon, they launched Amazon supply chain services earlier in May. I was wondering, does this more fragmentation and multi-carrier complexity drive more demand for your solutions? Or do you see any risk of potentially displacing parts of your value chain?

No. I mean they're a big customer of ours, and we don't compete with any forward fledging management capability. We don't -- we purposely don't do anything to compete with it. We're trying to help them. And we've seen over the years, we've got competitors many times say that they're going to do something that their customers do the right -- does in the [ 3PL dev ] and they get killed for it. And we have very aggressively stayed out of that, trying to remain neutral. And we're trying to help them all -- and Amazon is a big customer of ours, and we do business with just about every freight forwarder in the world.

So -- that to me is -- was on giving into this business to already do a lot of stuff with them. I suspect we'll end up doing more because we do a lot, especially with the bigger freight orders we tend to get big relationships with them. And we'll see how they get into it. Do they buy someone along the way that oftentimes helps them get going, all that with Uber. And over when they started as like , we're going to do all this stuff ourselves, and then year-end by one of the bigger players in the industry. And here we are today, 4, 5 years later, and they're one of our biggest customers. And if you had listened to them 7, 8 years ago, you would have thought they would never do business with something like that ever. And of course, they would. The reason they do it is because there are certain things we do better, faster and cheaper than they'll ever do. So they would be smart to do it with us. And I think you'll see the same with Amazon.

Okay. And can you also unpack a little more about what's driving some of this strong GTI growth? So how much of the growth is from new customer wins versus existing customers accessing more databases versus prices?

I don't -- it's not pricing stuff. Pricing is largely the same. I don't know if I know the exact breakdown, but it's customers saying I need more information. I need more countries, they need more commodities and I want to search more stuff. And that's largely they're doing that because the tariffs are coming in. your tariff changes are coming in, as I would always say from we actually joked about it today before the call. If they never changed, we'd be selling a book. And because they change every day, we're selling access to a database.

And when -- comes in with this value to move and changes everything and then people tend to go into that database a lot more and start looking around and go, what do I do about this? And how do I plan to save myself money and that's how it goes for us. And sometimes they're new customers, a lot of times they're existing customers that are buying access to more of the database. We sell it in chunks to them by country, by commodity. And so they buy more, and we give them access to more so that they can make better decisions.

The next question comes from the line of Jan Shao with TD Cowen.

I understand GTI has been a strong growth driver this quarter. But earlier this year, key investor concern is your customer might use AI to replicate the same GTI database. So do you think this quarter's growth effectively derisk that concern? Yes. I didn't have a concern about it in the first place.

We heard that and said I don't think the people that are saying and understand how this works. It's -- and I went over on the last call in some detail. But we have a massive amount of data that we have to collect and it's from all different countries. And it's not that easy even to train an AI agent to do it. If you look at the way that we've done it, it is using AR strategies that we built ourselves over the last 15 years.

Maybe office shelf tools would help us do it today, but it doesn't matter. We've built them already. and that's how we grab the data, then we have to put the data into a database in a similar format for everyone. We have to make Belgium look the same as the Netherlands look the same as Japan, et cetera. And that's hard -- then we have to build ways to disperse it to the customers. And you could just say here's the data, but it's much more convenient for them is if we say, oh, here it is in the Oracle format, so you can about throw it right into your database over there 7 times a day, and that's the whole set of things.

And then you have maybe one of the more compelling arguments, which is we don't charge that much because we do it for everyone, the price per customer is pretty cheap -- so there's no one customer that's like for the 50,000 I pay you a year, I'm going to do this myself. Well, that math doesn't work. I mean you're not going to be able to do a better faster cheaper than us and even close if you I could just give you a little -- like Amazon uses this. Trust me, if they could replicate it themselves, they would anything they've ever been able to replicate themselves with us they do. This is not one of them. It's just not feasible.

And then finally, if you get it wrong, it's a real payment and have to get your money back. And if you got it wrong because you touch around AI system, the government is taking out like that. They want to hear that you were trying to do it properly. And I build my own AI tool when I was wrong. It's not a compelling argument. And it's not a compelling argument with the tariff stuff, and it's really a bad argument with the sanction party stuff.

So people tend to do those things together with us to make their global trade management system work. And if you add all that stuff up, one people said that to us and I kind of laughed, I intrinsically knew that wasn't what's going to happen because what I just described to you, it's just too much to come. And if someone -- if my best friend hold, maybe that he was going to do that, I would say, don't do that, you're wasting your time. You go with someone. So if Descartes is going to be better, faster, cheaper. And you should get focused on your core business, not on building your own tariff database. It's not going to be worth it.

The next question comes from the line of Robert Young with Canaccord Genuity.

In, just a couple of questions on the AI agent layer you're highlighting. I'm trying to understand One, how an external party would access that. Is that like a model context protocol to use through like 1 of the like Claude or something like that? Or is it something that you're setting up specifically for your larger customers to access your data.

And any ways for our customer -- yes, sorry, it is that. It is a our tools and our customers to say, I want some information out of here. It's a set of protocols that you would use to make calls to RAI tools to disperse data to you quickly and efficiently. For use in an application, you use to answer customers who might be on automated phone call or coming into your website, you got to quickly call us. And I give you an answer that fits right after your customer in a split second and you pay for that.

Great. And you said that you've put a policy in place that determines what these parties can access, how they access it and your audit -- so there's a monetization strategy. That sounds like a foundation for monetization. So is there any additional detail you can provide around that?

Well, think of it like it's our network has these tools, they're just getting -- they're going to get a hell of a lot better with a whole a lot more stuff you can request from them. Our network already does this conceptually. And it lets you get access to a bunch of things to be able to get tracking messages the ability to make a booking to get a booking confirmation back to make a filing to a government to get a final confirmation so that you're playing can take off. I imagine if I add 1,000 more things to that, that I can serve up the people and they each cost $0.25 or whatever. That's how we imagine it.

Okay. And then last question. Just you said that there were some strategies to increase adoption and velocity on the GLN with the layer maybe bring new customers into that work. It feels though you've got most of the large customers. And so I'm just curious what types of strategies -- how...

Getting them to do more with us, right? I mean AI is going to bring -- and we see this is easy for us to see because we do business with all of them. It's going to bring a huge opportunity for them to better service their customers and charge them more. And hand-in-hand was that same for us. I go, our customers could be providing much more information to their customers about what's going on in their shipments and get more money from doing it. And because they're saving them money and finding them more efficient ways to operate.

And as a guidance service that I may be charging $0.25 for giving this out. They may be charge $10, right? And their customer goes, wow, that was really worth it. And I go, wow, I made a lot of money at $0.25 and our customer goes I just made 925 on this idea that kind of the car at me. And now my customer is happy and they're paying more money. I like, I think we're going to see more and more of this all over the place. And because of our network, I think we're in a very, very good position to do it, and we're excited about that.

Okay. Great taking questions. Thank you, have a good day.

I'm showing no further questions at this time. I would like to turn it back to Ed Ryan for closing remarks.

Thanks, everyone, for your time today, and we look forward to reporting back to you in September. I appreciate your time today, and we'll talk to you soon.

Thank you. And ladies and gentlemen, this concludes today's conference call. Thank you all for joining. You may now disconnect.

Hi, everybody. I'm Bob Bowman, Editor-in-Chief of SupplyChainBrain. Welcome to the special presentation, The AI Exchange Inside the Last Mile, AI delivery, engagement and the new standard for on-time and in full. First of 4 webinars on the theme of the AI Exchange to be presented by Descartes this year. [Operator Instructions]

So what if your routes could learn from every delivery. In this AI Exchange session today, we're going to explore how moving beyond static service time assumptions leads to a new level of fleet performance. Traditional routing treats each stop as predictable, but in reality, each one is shaped by order size, product mix, site conditions, unloading requirements and crew readiness. AI and machine learning changed the model by learning from actual delivery behavior and continuously applying that intelligence to future routes.

So let's see what our experts have to say about it. I'd like to introduce our speakers for today. Sergio Torres is Senior Vice President of Product Management with Descartes. He's responsible for managing strategy and vision for the company's entire portfolio of routing, mobile and telematics solutions. Prior to joining Descartes, Sergio worked as a Director of Business Development and consulting in Europe for CAPS Logistics; and Cyndi Brandt, who's Vice President, Fleet Solutions with Descartes. Cyndi has deep expertise across product management, product marketing, sales enablement solutions, engineering and marketing communications. At Descartes, she leads strategic efforts to bridge customer needs, with innovative solutions for last and final mile operations. Welcome to both of you. Welcome audience.

With that, I'd like to turn it over to Cyndi for a brief presentation. Cyndi, take it away.

Thank you Bob for that great introduction for both of us. At Descartes, we're all about technology that moves the world. We're a global leader in logistics technology that really helps over about 26,000 customers completely around the world, help get things from point A to point B, and we want to help do that in a smarter, faster, more efficient way. So for me, it doesn't matter whether it's raw materials that are into your factory or finished products that land at your door, our technologies behind the scenes, making all of that happen seamlessly. But it's a very, very heart of it at all. We are a talented team of 2,200-plus logistics pros who love, love, love solving tough problems and working side by side with our customers to help them succeed.

And then lastly, as a company, we've had about 20 straight years of record performance, and we consistently reinvest about 15% of our revenue back into R&D because we want to keep that innovation flowing.

In our particular pillar, which is Fleet Solutions, we have a delivery and performance management platform. It optimizes wholesale distributors to optimize routes, streamline dispatch, execute daily operations with precision and confidence. And we do that while making sure that there's real-time driver and customer engagement happening out in the field as well. We want to make sure that we're capturing valuable feedback, fuel continuous improvement, and power that improvement through AI. So it's a great topic for us to talk about today. The way I look at it is every route, every driver, every delivery. It's optimized, connected and built to exceed expectations.

Thank you, Cyndi, and thank you, Bob, for that wonderful introduction. So artificial intelligence as they cart, this is a good representation of what it is. But Look, it starts with a very simple idea, using data to make smarter decisions and automate complex logistics workings. So at the broadest level here in this picture, you can see AI is the overall field. So within that, we have machine learning that focuses more on systems that learn from data, improve over time. So this is where we start to see the real operational impact, especially in areas like route optimization, real-time optimization and continuously improve ETA predictions. We'll be talking about more than this during this session. So going deeper, deep learning uses neural networks to handle more complex patterns. This enables capabilities like OCR, image recognition and predictive modeling, turning unstructured data into actionable insights. On top of that, you have generative AI that introduces a new layer of value. It can create content, summarize information for us, and power conversational experience. At Descartes, this shows up in things like text classification, customer insights and chatbot interactions that enhance our user engagement.

And finally, you see at the very bottom, agenetic AI, which represents the next evolution. These are autonomous systems that don't just analyze, they actually observe, plan, and act. The idea here is to -- we will be orchestrating multiple tools and leveraging Gen AI that they can execute workflows end-to-end with minimal human intervention. And as you can see here, the power of this is basically the data that we are collecting. So combining all these comprehensive data, name it, route planning, route execution again. Drive -- how the drivers are actually doing when they are delivering a service to your customers, driver safety or driver behavior when they're actually driving a truck and we want to know if they are actually doing harsh-braking or speeding, solid acceleration. All this data combined in something we call the fleet date intelligence, actually allows us to provide data insights to our customers, provide analytics and also provide Gen AI agents. Now this is important because the Gen AI agent is what makes it actually the smart part of it. It actually looks into insight, summarizes this, it actually suggests and also it provides the ability to execute tasks. So we're kind of closing the loop and we call that René agent. So from fleet intelligence, basically getting all that data close in the loop to make improvements. So think about this example. If you're actually receiving your planning and your execution data, and you want to see how your plan compares to your actual execution data, René will be looking into your data to figure out where are the opportunities for -- to improve efficiencies and to improve the utilization of your fleet. So René will not only say, "Hey, by the way, it looks like you're actually overestimating your service time durations. You should probably look into that. Would you like me to do that for you"? And that will basically enable René to activate machine learning for service time predictions and that is executing an automated task for you. And at the same time, to be able to say, no, I want you to utilize these service time predictions at the moment of the optimization of a route. And that will trigger the configuration of your route planning solution to start consuming the service time predictions, and that is closed in the loop. And little by little, closing that gap between planning and execution.

Thank you very much, Sergio, and bringing Cyndi back at this point as well. We now move into the panel discussion portion of our presentation in which I have the privilege of asking Sergio and Cyndi to help us dive deeper into this whole question of AI. [Operator Instructions]

So let's start out here, guys. Let's start with kind of a discussion of AI in real world delivery. Cyndi, AI is becoming embedded in day-to-day delivery operations, not just long-term strategy. What do you see as the most immediate challenges that fleet leaders face today? And how have those pressures evolved over, say, past 2 or 3 years as expectations are on time and in full delivery continue to rise.

Sure. I mean that's a really interesting question because what we're seeing right now is that AI is really landing kind of right in the middle of some very, very real operational pressures, right, not just these long-term transformational goals. People can't wait that long to kind of have a real impact. But when I look at whatever fleet leaders dealing with today, it's is just really a tough combination, right, rising costs, unplanned rising costs at an exponentially fast rate. A lot of labor challenges right now. Customer expectations continue to change every single day. But we see over the last couple of years and even in the last couple of months, right, fuel, insurance, equipment, wages, everything has increased. So these inefficiencies now are really starting to double up. Some little things that might have gone unnoticed, they're now really getting your margins almost immediately. And at the same time, expectations around delivery have completely changed again, right? 2 or 3 years ago, customers were okay with a nice broad time window. Today because of the B2B expectations or B2C expectations have been set rather, they expect precise super accurate ETAs, a lot of real-time visibility to what's happening with their order and a seamless experience, right? And again, they wanted to mirror that home delivery they're getting from a retailer.

I think the biggest true shift is how last mile delivery is starting to be perceived, right? It's no longer just a function, get the trucks out the door, make the customers happy, right, not just the simple logistics function. It's become a mission-critical part of the customer experience as well as the cost structure of the business. It's forcing different fleet operators to really try to strike a better balance, if you will, between the efficiency and service quality than they've ever had to look at before.

You remember, 2 or 3 years ago, we said things like customer demand is greater than ever before. Little did we know what it was going to be like today. So you really got to step up and AI is just absolutely essential to that capability, obviously. But let me ask you to drill down a little bit further, Cyndi. Many fleets, they're still experiencing a 10% to 20% gap between plan routes and actual execution. Again, this real world kind of thing. Where are these breakdowns happening most often? And what does that mean for service reliability and customer experience?

Sure. I mean, that's still a pretty big gap, right? I mean we can all do that [ in full attire ], but we do consistently see that 10%, 20%. To us, it really comes down to the planning system is still operating on assumptions. The real world is more dynamic and far more precise, right? The breakdown really tends to happen when there's a disconnect between what was planned based on all those assumptions, right, those educated guesses and what actually unfolds in real time on the road. Think about traffic variability, service time inconsistencies, service time estimates, block dock, even last-minute order changes or driver behaviors. They all introduce friction into that deliberate process that you can never really fully capture in planning especially when you're making generalized assumptions. Fleets have to start to feed execution data. So what actually happened, explain to that planning process. If they don't, those same inaccuracies are going to continue day after day. Routes might look optimal on a piece of paper, but they really don't reflect those real world conditions, and that's why you consistently see that 10% to 20% gap.

When we dig into what this really means for surface reliability, it becomes super significant. The plan ungrounded in reality, routes aren't realistic, ETAs become less accurate, on-time performance starts to suffer. Your customers start to feel it, and that just makes your dispatch teams, so your employees and start to become firefighters and feel that pain as well throughout the day. Mistime windows, poor communication and consistent delivery experience, these are absolute no-gos for customers these days. There's an opportunity here, right? There's an opportunity to use AI to really make an impact on this and close that loop and pull the data in so that you can continually learn from that execution piece, and make your planning more adaptive and realistic over a longer time set.

2

Okay? So a real need for better planning and operational precision. Sergio, with that in mind, these traditional routing models, they rely on static service time assumptions, always have up to this point. So why has that approach persisted, however? And how does it fall short when it's applied to real world, again, that phrase real-world delivery conditions like job site variability, product mix and unloading requirements?

Yes. static service times really persist because it's very simple and easy to put in operation. I mean if you just take averages and fit them into your day integration into your routing system, that's a simple way to actually get everything going, right? The problem is that your plans may not really reflect the reality. So if every stop is assumed to take roughly the same time. It's very straightforward to build routes and standardize your planning. But the problem is that, that worked reasonably well when delivering environments where there is no complexity. However, our deliveries are not complexity, right? We all know that. And so today, that simplicity on the data really becomes a limitation. And we have always said it in systems, garbage in, garbage out. So the quality of data is super important. Now where you get that data is also super important. So think of this, if a delivery to a retail location is fundamentally different from a construction side, why would you use the same service times or for a multi-drop in a commercial center, right? So when those differences really are not captured, then you're actually introducing a systematic error into every single route. And what happens is that you're going to have very low compliance from your drivers to actually execute the routes that you plan. So over time, this will be leading to miss delivery windows or inefficient use of your fleet, and a lot of mid-day adjustments that you're actually always reacting to what is really happening in -- with your drivers. And sometimes you really have to be almost like a firefighter looking into every single route to see where you can actually avoid any or propagate more exceptions. So look, so while these static models are convenient, they really no longer match the complexity of modern delivery operations because now we have data that we can take advantage of that we -- before we didn't have. We were just working on statistics. Now we can learn from it. That's where the AI and machine learning comes into play.

Okay. So what are the results though. When -- we're talking here about fleet shifting to machine-learn service time predictions. They continuously learn from actual delivery durations. So again, real world. What changes in planning accuracy. And how does that enable improvements like up to, what, 30% greater route density without adding trucks or drivers. Sergio?

Yes, roughly. That's -- I mean, that's a great question because, look, the -- you'll see that's kind of the low-hanging fruit. Let's look at our service times, how they are actually represented in our planning system so that we can actually give routes that are actually feasible or they actually are close to what the reality is. So when fleets are actually shifting to a machine learned service time predictions based on the actual data, the biggest change is planning accuracy, basically it's grounded more in a real-world behavior. So now you have a closing relationship between planning and execution. So instead of relying on the static assumptions now the model will continually be learning about what the driver is actually doing when he's delivering, delivering the -- your goods. And that data factors many variables like, I'm assuming you're talking about order size, you mentioned it earlier, prototypes, customer location, geographies, equipment requirements. And you know the same historical patterns that you have every time you deliver to a given customer. So that comes into play as well. So that allows us to produce routes that are much closer to what actually happens in execution. So you will see very quickly that drivers stay on schedule more consistently. And then your dispatchers, your people that are actually managing operations will spend less time reacting to issues and overall operations will become more stable. So -- and importantly, very importantly, the accuracy -- this accuracy actually translate into better utilization. That's where the 30% comes into place. And in some cases, improving route density significantly without adding any trucks or drivers. You see that right away. The data insights and the machine learning will tell you, hey, actually, you're actually closer to your execution and you will be probably saving time or maybe you're overestimating, your drivers are going to be closer to the SLAs that you have promised to your customers. So it's both a service improvement and an efficiency gain in my opinion.

And you're making life better for your drivers, too. What about the human element of that? I mean, obviously, the customers are experiencing better service. You're doing more efficient operations from your end. But all of this running around and firefighting could drive these drivers crazy. And so it sounds like this is really helping in the way of making the driving experience better, especially at a time when it's so hard to find good drivers. So yes, thanks for that.

Okay. One of the big thing, one of the big truths about this whole world, you said many, many times, "you cannot manage what you cannot measure". Cyndi, there's an awful lot of noise around AI these days. But where are you seeing a measurable impact today in delivery operations, whether that is fewer missed delivery windows, reduced idle time, improved asset utilization like we were talking about. Tell me about that.

Bob, I think you just used my favorite term, which is there's so much noise in the market about AI. And most of it's -- people talk a lot about AI-based routing, what they're really talking about is AI-based execution, where I'm going to move stops around as the route transpires. They're really not talking about using AI and planning. At Descartes, we've taken a different position and saying, "Hey, look, we've got to close the gap in a way that's unique and different". And we think the gap exists today, again, between the planning and execution, we've talked about this, both Sergio and I earlier, right? When you apply AI to the execution data, what really happened throughout the day, things like your actual route service times, driver behavior, it becomes much more grounded in reality. And if it's the plan that's much more grounded in reality, than the execution and comparing the execution to the plan becomes more interesting, right? So if I have a bad plan and I compare execution to it, I'm not showing where I can really improve because I had a bad plan. When you have a precise plan and I can show what I did, I now have the ability to isolate where I can make those improvements, which leads to here's how you get to the very measurable, if you will, outcomes. So first, a couple of real easy things, right? More accurate ETAs, more accurate communications, less missed delivery windows, less extended route run time, less over time. These are things that are very clear that we can execute on from a metrics standpoint. But we shouldn't let this kind of real-time decision through the day of operations get away either. Dispatches teams are constantly re-racking manually disruptions, right? AI can dramatically adjust the routes to do what's safe based on what's actually happened, right, traffic delays, exceptions, I note that the dock door has been blocked. But we're going to try to reduce the idle time, so the wait time of drivers, improve that route adherence and keep drivers just moving along the road more efficiently throughout the day. We also see a lot of measurable gains in the categories of asset labor utilization, right? When I learn from that historical real-time data, I can better sequence stops, reduce the unnecessary miles. It makes smarter use of the available capacity, whether it's vehicles or human beings. And this becomes really important because of the cost pressure, right? How do I use my people and my equipment more efficiently?

And then just to put a bow on it and tie it all together, the customer experience is also going to improve. So your customer satisfaction rates, your customer retention rates. When they get better ETAs, less surprises and better communication, magical things happen and it becomes a real competitive advantage. So it's not 1 or 2 metrics. There's a broad swath of metrics, but it take work to get there.

And Sergio, service times, they can vary by 20% to 40% based on factors like customer type, order size, geography, vehicle constraints and the like. So how does machine learning account for that variability in a way that static models cannot. And how does that translate into more predictable delivery performance?

Yes. It's very interesting. From all the data we have analyzed how much discrepancy you can have by having the static service times. And really, you come to realize that the service times are not depending only on 1 or 2 factors. They actually can be variable. So this is where it becomes really relevant. So look, service time variability is probably one of the biggest challenges in any delivery operation. And you see that because of the percentages that you were just mentioning, Bob. And it's exactly where we can actually use machine learning to understand. What are the factors that are actually affecting that delivery time? Like we said, we were talking about prototypes, we were talking about order sizes, we're talking about the location that you're delivering. Again, the accessibility that you may have to that location? And if you're visiting that customer constantly and you realize that, that customer always gives you extra -- basically introduces extra service, you need to take that into account and the machine learning will learn from that. Even instructions that you may have on a shipment will definitely affect your service time. And the beauty of artificial intelligence is not like you actually prescribe and say, this is with the way you have to actually predict service times. The beauty of it is that it's actually learning based on the context of what is actually happening in operations with the actual documentation and data that you're sending into a routing system. So this -- all this combined is basically allowing us to have a prediction of service time that reflects more accurately and account for variability across our different types of deliveries that you're executing. So the net-net is, look, the result is a plan will -- a plan that has a built-in uncertainty in it, basically will lead you to better predictability execution. And this will basically reduce your downstream disruptions. Why? Because now your people are actually going to be working on a more proactive mode rather than a reactive mode. And that's the whole idea. And it unleashes a lot of benefits. Like we said, one of them is basically a better utilization of your fleet. Your drivers, as we mentioned earlier, they're going to be happier because they're actually getting routes that are actually realistic. Instead of getting the routes that they may not realistic, you see drivers coming back to the depot talking to their dispatchers. I can do this route in more time because you're actually underestimating the service times or vice versa, I can do it in a faster way. And now your SLAs that you're actually committed to your customers will be actually better mapped by having better predictable routes that look more like an execution. So machine learning is definitely making a difference in this case, Bob.

Thanks for helping to understand the whole concept of machine learning versus AI, that could be very difficult to parse those different terms. But I guess we're learning that real world, the term real world equals unpredictability. They're almost interchangeable words, are they not? I want to talk to you about the whole concept of connected operations because so many of this stuff has been fragmented up to this point. Sergio, many fleets are still operating across this disconnected systems for routing, for dispatch, for customer communication. What does a more connected data-driven delivery environment look like? And how does that improve decision-making across the day?

Yes, that's a very good question. I'm actually privileged to have -- to participate on these products that we have at Descartes. It allows us to basically have that fully integrated solution footprint, and that -- that's critical that this division between system is nonexistent at all. So a connected delivery environment is really about bringing, obviously, your planning, which before it was actually separate, your execution, that again, it used to be separate and the communication into a single operational flow, communication to your customers as well. So when something happens here, you basically need to make sure that those 3 systems stay connected and the propagation of data works seamlessly. So look, again, historically, they used to be separate. They were managing different systems. We used to have routing in one place and dispatching another, and then customer communication somewhere else. And you're probably sending data between systems that is probably stale or it's actually old or it's not real time. So that really creates a lot of gaps in visibility and it slows down the decision-making that you need to have in the real-time environment. So when these systems are integrated, now the data is actually flowing seamlessly across the operation, fleets can see what is actually happening in real time and respond quickly to any exceptions. So that level of connectivity basically allows them to manage the entire delivery process for -- again, and I mentioned this earlier, from a more proactively and consistently manner. And the fact that you have this data flowing consistently and being able to react -- to send proactively notifications to your customers if there is a delay or they could be basically -- or you actually -- may be actually arriving earlier, this actually improves the efficiency of your fleet, avoiding any delays or avoiding any miss deliveries because the customer is not available, et cetera, et cetera. It's just a cascade of benefit that comes with it.

I'm glad you brought up the idea of responding because a lot of this conversation up to this point has been about how you can better predict what's going to happen, but not the most sophisticated AI model in the world, let alone the most intelligent human being, can 100% predict what is actually going to happen because real world is unpredictable, real world, there's a certain element of chaos. Let's face it. You have to be able to respond accordingly. So Sergio, as plans inevitably change in the process of execution, how does combining planning data with real-time visibility let fleets adjust routes dynamically, while maintaining service commitments?

Sergio, I can't hear you all of a sudden. Are you -- I think we've lost your -- no. Cyndi, can we hear you?

I'm here.

Okay. You sound like you're muted, but I don't see a mute form. Let me see what we could do here real quick or we can turn to Cyndi for that if we can't hear Sergio anymore. Sergio, you might try muting and unmuting on your audio there to see if that brings it back.

All right. How about now? Can you hear me.

There we go. There we go.

Probably my audio switched to something [indiscernible].

Yes. No, did I say about unpredictability. Okay, folks. Here we go. A real-world demonstration of what we're talking about today. So Again, let's talk about the whole idea of response, real-time visibility, planning data combining with that, respond to that.

Thank you, Bob. Yes. So look, in any delivery operation, we know plans will be changing during the day, right? That's just unavoidable. This is the nature of the beast. The key is how we effectively respond to those changes. So when you see planning the data that is connected to real-time through facility, fleets can actually make informed adjustments as conditions are changing, right? So that might mean rerouting or updating ETAs, as we mentioned earlier, or even reallocating resources to work on any exceptions. So for example, if you most resequence a route to minimize the risk of missing time windows, you must know where your drivers are at any point in time. You don't want to be resequencing and driving them crazy when they are probably en route to a delivery. And then at that point, you can decide what and what cannot be changed. And the changes that you're actually making to your delivery plan have to be communicated obviously to your drivers in real time and also to your customers to avoid any future exceptions. So having that planning data connected to the real-time visibility is what enables you to make a dedicate and effective systematic decisions. So instead of reacting after service levels are impacted, okay, they can make control adjustments that help you maintain the performance that you're expecting. That's the real shift. And it's from -- like I said, it's actually for moving from this react to firefighting to a more proactive -- and it's important, data-driven decision management. This is where the power of data coming from planning, coming from execution is actually collaborating to make sure that you have that at your fingertips in real time so that you can actually do proactive decisions and educated decisions.

Yet another truth, it's all about the data. So we hear that in any technology initiative and especially when it comes to AI applications and the like. So I want to talk now though, about what it really is all about, and that is the customer experience. Cyndi, once the route is in motion, delivery becomes the customer experience. So how are leading fleets using real-time visibility and predictive insights to manage the full delivery journey from dispatch through final confirmation rather than just through a series of individual stops.

You're right, Bob. It's not a series of individual stops anymore, and it was for a very long time. It is really a continuous customer journey, full of expectations that continue to change that we talked about earlier, right? What this looks like in real practice, though, is leveraging a customer experience or a customer engagement platform. This platform has to work in conjunction with your plan and real-time execution. So there's 2 pieces to this. It's pulling in information about the plan, but also pulling in live route data and tracking progress throughout the day, right? And then it's going to give us some predictive insights to understand not only where is my driver, but how is the rest of that day actually unlikely to unfold. So that might be sending of notification instead of saying, I plan to be there at 2:00 and sending a notification at 1:50 that says I'm 10 minutes away. Well, now I'm not going to arrive till 02:05. So I might [indiscernible] that notification to 1:50, arrive with 10 minutes here, right? So it's being a little bit more precise there. When I look at how do companies create a competitive advantage today, it really is communication via customer notifications, right? That's the way to create that competitive advantage. It's really the crux of everything. If you're trying to find that advantage where margins continue to get smaller as costs increase, you have to have to, have to, have to provide kind of these dynamic event-driven communications around the entire order journey from the minute I've taken the order to the moment that it's delivered to the final moment where I provide feedback on that delivery or that driver. Leaders in the space are going to be adapting technology that's not just where is my truck, but where's my truck with context.

Right. Every time you make a communication with the customer, you are, in fact, raising a customer expectation to meet that promise of that communication. So you better be right about what you're telling them, what time you're going to show up or you're going to have some very angry customers.

Sergio, I apologize if I'm sounding a little bit obsessed about this whole concept of response because that is really what we're talking about here today, more -- even more of the prediction of how you actually respond to, again, to the real world. Sorry about keep saying that. But as plans change throughout the day, and of course, they do. How does connecting routing, execution and customer communication in 1 platform help fleets to manage exceptions in real time while still protecting service commitments.

Yes. I mean again, this is where the pressure comes. I mean you guys have all used Uber and the ability to actually see real time what is happening with the driver, when it's coming to you, allows you to make decisions as a passenger. Even if you -- for whatever reason you need to do relocations or maybe you don't want it anymore, you can actually do that in real time. And that's exactly what we're talking about here because exceptions are definitely going to happen no matter what, in every delivery operations, talk it -- you name it, delays changes, unexpected conditions, new orders coming in, new pickups that you need to do and you need to accommodate. These type of things basically change your plan. But the good news is if you have real-time communication end-to-end from the planning all the way to execution and to the end customer, it allows you to actually be more efficient and advise people ahead of time to actually remove that noise and avoid any inefficiency that actually may actually be generated from it. So the difference now is the ability to manage those exceptions in real time. That's the reality. So when route execution again and the communication to the customer are fully connected, fleets can quickly adjust to changes, update ETAs and notify our customers if there is any exceptions like, hey, I'm probably going to be -- we're going to be 30 minutes late from the ETA. And if the customer basically tells you, hey, I'm not going to be there and don't even show up then you know that immediately you have to adjust your plan or vice versa. I'd like actually now to move my delivery to the afternoon because we're not going to be present that day. That actually -- that information that comes back. And the moment that the customer actually does that. And if it is connected to your planning and execution, systematically, you can make a decision that is based on the data that you have received up to that point in real time. So this is just basically a way of minimizing the impact on any disruptions or delays, missing deliveries, no shows, et cetera. So it does help us maintain service commitments even when things don't really go as expected.

It's funny because we talk about how demanding customers are, but at the same time, they're kind of forgiving if you level with them. If you tell them what's really happening. If you don't, that -- the worst thing you can do is not communicate, have something show up late and you didn't tell them it was going to be late. That real -- speaking as -- we've all been customers in that area and we don't like it. So it's a good point to make.

Okay. Cyndi, we were just talking about what's happened with our customer expectations in the last 2 or 3 years to the point now where on-time delivery is no longer enough. Customers also want full transparency and coordination. So how do capabilities like dynamic ETAs, estimated time of arrival, proactive notifications like you were saying, and centralized communication, how do these things reduce friction, improved job site planning and enable faster service recovery when issues actually do arise.

No. Like you said, customer expectations really and truly have evolved because we have so much access to data, right? It's gone from simply being "on time" to a fully informed, fully coordinated and predictable experience, right? I want to have the same experience every time. I want to know all the information that I can about that delivery piece. But if I can coordinate all this, that's where all these capabilities can really start to make a significant and meaningful difference within organizations. When I think about dynamic ETAs and productive notifications and centralized communication, fleets have the ability now to kind of stop reacting to managing that entire delivery journey in real time. In the past, we get a phone call, where is my truck, and we would just immediately drop everything and react and make 7 phone calls. Now I'm pulling all the friction out of that by allowing the data to work for us, right? So if something changes super early in the route, I'm getting data information in about that. The system can start to really anticipate what's that downstream impact. There was a traffic jam. It slowed things down by 10 minutes. Nobody is going to be upset if your ETA is impacted by 10 minutes as long as you know about it. Adjust the ETAs, notify those customers, I'd like to say, trigger operational interventions before they happen or escalate within there. By reducing the friction and with all this transparency, right? When you think about job site coordination, specifically like freeing up people to meet the truck, making sure you have enough labor to meet the truck, making sure that your workers get to a building site to meet the truck that has a tremendous amount of expensive materials on it, right? I can plan and anticipate better. And customers know when to expect deliveries, they can make adjustments to their day so that they can take those deliveries? Because remember, if they don't have the right people waiting around -- well, first of all, it's expensive that people waiting around for delivery. But if they don't have the right people, ultimately, you as the delivery company is going to be delayed, and it's going to impact other customers down the road.

The last thing I would say to you is that it doesn't really stop the delivery itself. When you connect a proof of delivery with feedback capture, you're also closing that loop, and then you turn your execution piece, not only into insight for planning, but insight into your customer that feeds continuous improvement, right? Does cities restaurant always reject half of the fresh vegetables that are delivered, right? There's all kinds of things that you can start to look at to create insights, to create insights into ordering patterns. That's a whole another way to apply AI. But at the end of the day, let's work on creating a controlled, consistent customer experience with fewer surprises for those customers, less firefighting internally for our dispatch and operations team and a delivery journey that's really more managed as opposed to kind of going back to that one stop at a time.

No. Okay. Sergio, I do want to quickly touch on this thing that any time technology comes into play and you have humans using it. The systems become more intelligent. But how do you ensure that planners, dispatchers and drivers actually trust the outputs and use them consistently in day-to-day operations?

Yes. Look, a successful adoption comes down to making this part of how the operation runs every day. It's not just about -- technology is an enabler, Bob, and we humans make it happen if we actually run in every single day during our operations activities. So the fleets in my opinion, that see the most value, they really don't treat it -- these type of things as a technology project. It should be aligned with operational objectives, goals, such as -- I mean Cyndi has been talking about it in her responses, like improving on-time performance, increasing route efficiency enhancing your customer experience. And that's how we want to see it. So we're going to be using machine learning for those purposes. And also, we have to involve the people that are going to be using on a daily basis, such as your planners, your dispatchers, your drivers, feedback is super important, right? As long as you actually involve them early in the process, the system will fit naturally into their workflow. So when that happens, technology really becomes a tool for better decision maker, it's just not just another system you're going to be actually managing. It's actually giving you the freedom and the knowledge and the foundation to actually base your decisions on and be more effective when this happens. And it actually creates confidence at the same time. So it creates confidence on your planners, dispatchers and drivers, but also on your customer base as well that you know that you're going to be compliant with their SLAs that you have promised in the past. So that's where the really -- real successful adoption comes from.

We're short on time, but I just want to get a quick answer from you Cyndi on this one. Over the next, over the next 12 to 8 months, what capabilities will define high-performing delivery fleets?

On the planning side, let's get away from static optimization. Let's get the plans that are informed by historical execution data and become more dynamic, right? Customer engagement, you've got to fully integrate that process into what you're doing. It can't just be notifications. It's really got to be information about the entire order journey. If you bring these 2 things together well, you're going to get better route adherence, so better rep run times, more reliable ETAs and better asset utilization.

Well, thank you very much for that, and thank you, guys, for your great answers and this great panel. I've learned a lot myself in the last hour about the applying AI and machine learning to this whole issue. It's now time as I promised to bring the audience in. We do have some audience questions already submitted. And if -- we'll get to as many of those as we can time permitting, but please do continue to submit your questions by clicking on that Q&A icon at the bottom of your screen. So I'm just going to throw these out and see who wants to take them.

This question is what's the most practical first step for a fleet that wants to move from static planning to more data-driven service time predictions? I see you nodding Cyndi, so I'm going to throw this one in your direction.

Well, I think the practical for first step is to start capturing and using actual service time data that's coming in from the field. A lot of fleets have the data. They can pull it in from telematics, cameras, other driver apps, but it's not systematically being used. If you aggregate that data and apply to planning, even in a super simple way, you don't even have to use machine learning, although it's better. You can start to replace assumptions.

Okay. Now this question says, do you need a large amount of historical delivery data to benefit from machine learning? Or can smaller fleets still see value? Sergio, why don't you take that one?

Yes. Sure. Thank you, Bob. You don't really need that much amount of data. Even smaller fleets can benefit from this. You can see that the models are going to be improving over time. So look, what -- we're always talking to our customers, we say, look, let's start securing your routes. And we're going to learn a wealth of information that we can actually utilize to improve your -- to improve basically your route planning. And that's where the value starts. Cyndi mentioned it, measuring the actual service times. You cannot improve what you don't understand. So by starting to capture and using the data that you already have, it's probably the best source of wealth that you can have to actually improve your operations. So let's start there. And even -- like I said, even it doesn't matter what fleet size you have. It is important that you actually start capturing that data to learn from it and use it in your planning operations.

Questioner wants to know what is the most common mistake that fleets make when they're trying to modernize delivery operations with AI? Sergio, you look like you're ready to answer that question.

Sure, sure. I'll jump in. Look, trying to do too much at once. That's the biggest problem and trying to actually boil the ocean. The best approach, in my opinion, is to start with a focused use case. And that -- once you actually have that case defined, now you move on to prove the value and scale from there. So you can actually start with a small operation in a few vehicles to figure out, okay, this is what I'm going to be doing. I'm going to be learning from these drivers. I'm actually going to start communicating with customers to see what the value of doing such action will actually bring to my business. Is it actually reducing time? Is it actually improving the fleet utilization? Is it actually improving our customer satisfaction? And then once you have actually that proof, then you have a platform to actually scale from there.

This question says, how can drivers get involved with how their data capture is being made and used? I like that question. We have to keep bringing drivers back into the picture. We can't forget them. Cyndi, why don't you take that one?

I think people do forget that drivers was such a critical piece of this, right, involving them in the conversation first and foremost. These are the people driving the trucks and quite frankly, sometimes they have the best ideas. Again, what looks good on paper may not be practical in execution. But one, explain to them what you're doing; two, ask them what the barriers are to collecting the data; and three, ask them if there's a better way to do it, right? They may say, you know what, pushing buttons this really hard, could you turn on auto arrive, auto to park? And they may say, if you collected this metric or this piece of information, while I was at a customer, I can reduce the amount of tribal knowledge that's needed to be able to service customers. So have -- just [indiscernible] and have the conversations with them. We don't do that often enough and so many great ideas come from drivers.

Okay. A real quick one on this one. Maybe I'll give this 1 to Sergio, just very quickly. How will machine learning continue to evolve in this context?

Well, it helps tremendously because it helps us actually learn from what actually the driver is doing. So in that context, as Cyndi was explaining, look, if you involve the drivers right from the beginning and you tell them why you're actually collecting data when he's utilizing a mobile device and you're telling him, hey, it is important that why we're actually measuring when you arrive versus when you complete your services is actually to provide you with better routes and that will basically improve your driver satisfaction in a long shot. So -- and at the same time, that data will be basically used and the driver will be able to see how that actually affect is impacting the routes. And if you actually, with data -- again, with data visibility, hey, Mr. Driver, look at this, this is actually the way you're actually executing, this is the way we planned it. It's actually very close. So we're actually doing well, and the driver can come back and say, you know what, now that you're actually coming back with that. I told you I can do this route in 6.5 hours instead of the 8 hours that you gave me. Let's put on more because probably that improves also the driver satisfaction to actually do more work and maybe you can incentivize driver to be more efficient in that manner.

Regrettably, I must cut us off at this point. It's such a fascinating discussion. I wish we had another hour to talk, but we don't. Thank you for that answer, Cyndi, as well. Thank you, both of you guys for these -- your great participation. We do have time for just 1 final question. And here it is. We know the delivery teams are being asked to improve stop density, on time and in full performance, customer visibility without adding cost or complexity. We know that. What is the one shift, though, that leaders need to make now to move from reactive execution to more precise data-driven operations and what is the one action they should take in the next 90 days. Cyndi, why don't you go first on that one.

See Bob, that's a pretty tough question, a lot there -- right there. I think here's the reality. You have to make a shift from kind of these strategic static plans to continuous data-driven operations. You have to use the real execution data to improve decisions not only in real time, but in planning time. And the next 90 days, focus on a single use case, something -- I'm going to say simple, but it's not simple, like ETA accuracy, right? Start turning that execution data into action. If you focus on one, that's how you can get impact fast.

Sergio, what do you think?

Again, as Cyndi mentioned, planning -- your shift is planning from assumptions instead of planning on assumptions, you actually plan on actual delivery behavior. That's the #1 shift that I will mention. If you have something to do, and I'm going to give you an action item in the next 90 days, it's time to start capturing and using that real delivery data. That's it. capture it. And that's the very first foundation to actually start looking into service time predictability and execution variability. So that's the foundation for improving your planning accuracy, Bob.

Well, again, guys, this has been a great discussion. Thank you so much, Sergio and Cyndi for this excellent presentation, for your answers to my questions as well as those in the audience and thank you, audience, for posing them. This has been wonderful. Thank you so much. We have for you an interactive demo, real-time visibility that drives delivery performance. You can access it by taking a quick shot of that QR code. You'll be able to see deliveries in action. Scan that to explore the experience in real-time. And we also want to bring to your attention this Episode 2 in this 4 webinar series this year from Descartes under the common theme of AI Exchange. This time, it will be about AI Agents for Fleet Performance Management. The date is June 23, the time is 11 a.m. Eastern. Again, there's a QR code for you to take a shot of if you want more information to save your spot. However, if you don't have time to take that QR code or the one before, which has already disappeared, obviously, don't worry about it. All that will be provided to you attendees at the conclusion of this webinar, which, of course, is right now. Thanks again, Cyndi. Thanks again, Sergio. Thank you so much, audience. Everybody, have a great day.

Appreciate it Bob. Thank you.

Good afternoon, ladies and gentlemen, and welcome to The Descartes Systems Group Quarterly Results Conference Call. [Operator Instructions]. This call is being recorded on Wednesday, March 11, of 2026.

I would now like to turn the conference over to Mr. Scott Pagan. Please go ahead, sir.

Thanks, and good afternoon, everyone. Joining me in person on the call today are Ed Ryan, CEO; Allan Brett, CFO; and Ed Gardner, EVP, Corporate Development. And I trust that everyone has received a copy of our financial results press release that was issued earlier today. Portions of today's call, other than historical performance, include statements of forward-looking information within the meaning of applicable securities laws.

These statements are made under the safe harbor provisions of those laws. These forward-looking statements include statements related to our assessment of the current and future impact of geopolitical, trade, tariff and economic uncertainty on our business and financial condition; Descartes' operating performance, financial results and condition, cash flow and use of cash, business outlook, baseline revenues, baseline operating expenses and baseline calibration, anticipated and potential revenue losses and gains, anticipated recognition of revenues and incurrence of expenses, potential acquisitions and acquisition strategy, cost reduction and integration initiatives, timing of management changes, the approval and potential share purchase under a normal course issuer bid and other matters that may constitute forward-looking statements.

These forward-looking statements involve known and unknown risks, uncertainties, assumptions and other factors that may cause the actual results, performance or achievements of Descartes to differ materially from the anticipated results, performance or achievements implied by such forward-looking statements.

These factors are outlined in the press release and in the section entitled certain factors that may affect future results in documents filed and furnished with the Securities and Exchange Commission, the Ontario Securities Commission and other securities commissions across Canada, including our management's discussion and analysis and annual information form filed today.

We provide forward-looking statements solely for the purpose of providing information about management's current expectations and plans relating to the future. You're cautioned that such information may not be appropriate for other purposes. We don't undertake or accept any obligation or undertaking to release publicly any updates or revisions to any forward-looking statements to reflect any change in our expectations or any change in events, conditions, assumptions or circumstances on which any such statement is based, except as required by law.

And with that, let me turn the call over to Ed.

Thanks, Scott, and welcome, everyone, to the call. Today, we're reporting quarter -- record quarterly and annual financial results across the board. We're ahead of our annual plans and finished the year extremely strong. These are great results that I'm looking forward to walking through in more detail. However, first, let me give you a road map for this call.

First, I'll start by hitting some highlights of last quarter, provide some comments on how artificial intelligence impacts our sector and business. I'll then hand it over to Allan and Ed Gardner, who will go over the Q4 annual financial results in more detail. After that, I'll come back and provide an update on how we see the current business environment and how our business was calibrated for Q1, and then we'll open it up to the operator to coordinate the Q&A portion of the call.

So let's start with the fourth quarter and year that ended January 31. Key metrics we monitor include revenues, profits, cash flow from operations, operating margins and returns on our investment. For this past quarter, we again had record performance in each of those areas. Total revenues were at a record high of $192.8 million, up 15% from a year ago. Record high services revenues were also up 15% from a year ago, with our continued focus on generating recurring revenues. Record net income was up 22% from a year ago. Record income from operations was up 25% from a year ago. Record adjusted EBITDA was up 18% from a year ago.

Our adjusted EBITDA margin is at a record high level of 46%. We generated a record high of $76 million in cash from our operations, up 25% from a year ago. So strong record results across all these key metrics.

For the year, the results are equally impressive. Record revenues up 12% with service revenues up 15%. Record net income up 14%, record income from operations up 16%, record adjusted EBITDA up 16% and record cash from operations up 21%. As I said, all results for the year were ahead of our plans. At the end of the year, we had $356 million in cash, and we were debt-free with an undrawn $350 million line of credit. We remain well capitalized, cash generating, growing and ready to continue to invest in our business.

We also have a normal course issuer bid that allows us to purchase up to 8.6 million shares before December of 2026. We made some small initial purchases before we went into a trading blackout in January. So a tool that we have that we've already used and that may be used again as we monitor rather volatile recent market conditions.

I'm not going to spend much time talking about the operating results for the quarter or year. As I said, they were very strong. The reasons why are similar to what we've done in the past in the previous 2 quarters, First, we saw strength in the global trade data and intelligence from a chaotic tariff and sanctions environment. Second, we saw strength in real-time visibility and shipment tracking as we continue to leverage AI tools and agents to have the industry's leading shipment tracking rates. And third, we saw strong e-commerce imports in the United States, which was good for us as we have the market's leading solutions for helping with high-volume rapid customer clearances.

We also completed a tuck-in acquisition in our e-commerce pillar earlier today. U.K.-based order Mine is a current partner of Descartes with its solutions already working alongside our People box, e-commerce, WMS for U.K. customers. We're particularly excited to introduce Order mine's core product Forecast mine to our e-commerce customers around the world. Forecast mine is a strategic step forward in our e-commerce AI investments accelerating our AI-powered forecast and demand planning, particularly for e-commerce sellers using Shopify.

E-commerce sellers are focused on freeing up cash, protecting margin and scaling without operational drag. We've got a huge pool of rich inventory, order, supplier, fulfillment and returns data that forecast mine can train on to help sellers do this. Specifically, it helps convert e-commerce signals into clear, actionable insights that reduce excess inventory, prevent stockouts, improve forecast accuracy across channels and seasonality, automate purchasing and shortened planning cycles from days to minutes.

I'd like to welcome the order mine team to Descartes. I'm happy to answer questions on any aspect of our operations or the acquisition later in the call or afterwards. However, I wanted to spend some time today with some comments about what I'm getting asked the most questions about the impact of artificial intelligence on our industry and on our business. I've heard market commentators raise concerns about the impact of artificial intelligence technologies on the long-term prospects and terminal values of technology businesses. Specifically that if AI can generate software code and coding becomes commoditized and established technology companies are vulnerable to new entrant competitors or companies taking software coding in-house. In short, the headlines are AI could kill existing technology companies. I don't buy any of that. Those commentators are fundamentally misunderstanding the value technology companies bring to customers.

I believe AI technologies will make businesses like Descartes even more valuable to customers. At the heart, technology businesses do not exist to just make software code. This is not the value they deliver to customers. Instead, they deliver a comprehensive service to customers, a service that includes security, trust, stability, compliance, infrastructure, operational and customer support, workflow and domain expertise, proprietary data, connections, scale, innovation, cross-pollination of valuable ideas and yes, technology functionality that is powered by software.

Generative AI doesn't replace all those things. Generative AI is a tool that allows tech companies to make many of those things better and deliver them faster. Tech companies will leverage AI to make their businesses more secure with AI tools that help diagnose and prevent attacks, they'll make their service availability more reliable with AI tools across their infrastructure. and they'll enhance operational support for customers with AI-powered agents to address routine increase.

Generative AI companies know the market is making a mistake by questioning the long-term prospects of technology companies. They're admitting that publicly, and they're running their own businesses by relying on specialist technology businesses rather than using their own AI tools to build an inferior quality enterprise system. The market peers don't match reality. I've also seen market commentators paint many technology businesses with the same brush that the impact of AI will be the same for everyone. That's also not true.

The impact of AI will vary significantly by industry business model, scale, pricing model and investment commitment. So let me talk to Descartes specifically. What we are, what protects us, the moat around our business and the opportunities that AI brings to our business. First, what we are. Descartes is a network services business. We run the global logistics network. It's the world's largest connected community of supply chain and logistics participants formed over more than 30 years. It's relied on by the community every day to process billions of transactions per year.

We use technology to help our customers solve complicated inter-enterprise supply chain and logistics problems on the GLN that require the cooperation of multiple parties and communities on the network. We're not an enterprise software company. Now let me describe the huge moat we have protecting our business. I'm going to try and help you wrap your arms around how broad it is by putting into some key categories.

First, we're a critical network relying on by the world. As I said, the Global Logistics Network is relied on by the community every day to process billions of transactions per year. It's unparalleled uptime breadth, speed and specialization make it critical to the operations, have our more than 30,000 customers. It's difficult and time consuming for another company to replicate that. It's challenging for our customers to find something as reliable, relevant and comprehensive to switch to. It's the major moat for our business.

Two, we help solve complicated inter-enterprise challenges. Supply chain and logistics challenges are not enterprise issues that can't be solved with just a customer's internal people and data. Supply chain and logistics challenges require interaction with external parties beyond the enterprise whether they be drivers, warehouses, customs authorities, governments, shippers, carriers, logistics intermediaries or banks. If you use AI to create tools or applications to help you, you still need to connect to the supply chain and the logistics world. That means you connect once or you connect and maintain hundreds or thousands of connections to external parties by yourself. The enterprise nature of our business keeps us relevant and makes us a better choice for our customers than trying to do it themselves.

Third, we process transactions. Descartes is primarily a transaction processor as things are processed by the GLN, such as tenders, bookings, loads, invoices bills of lading, custom signs, security filings, et cetera, we charge for our services. Our value is generally tied to the service we provide rather than the number of employees our customers may have now or in the future. Our model is not reliant on seat-based or user licenses.

Four, we help with compliance. Many of our customers use our GLN to help them comply with various laws and regulations. This could include custom filings, security filings, tariff classification, foreign trade zone, warehouse operation, sanction party screening or public freight rate management. customers are often wary of taking compliance burdens on solely themselves, especially given the pace of change of regulations and the financial and other consequences of getting it wrong.

If we earn our customers' trust to reliably help them comply then there's not much financial or other benefits to them changing something that's already secure, timely and accurate. This helps protect our business from new entrants and customers considering taking on compliance burden themselves. It also helps us grow because when we're a trusted and reliable partner for one compliance initiative, our customers are much more likely to trust us with other initiatives in the future.

Five, we were a system of record for many of our customers, our systems are the official trusted source of truth for their critical supply chain and logistics data, using the Global Logistics Network, we help them ensure data integrity accuracy and security of key supply chain and logistics information that they rely on for daily operations. This makes these customers very reluctant to switch to another provider or to do it themselves.

Six, we are supply chain and logistics experts. We're in a very specific market. Our team at live, eat and breathe supply chain and logistics every day when changes happen and they happen quite often these days. You want to know that you're doing business with an expert that's on top of things. Our customers consider this expertise a part of our service offering, and it makes them dedicated Descartes customers.

And finally, we're trusted, financially stable and transparent. We have a very good reputation. We've worked for many years to cultivate trust with our customers through reliable service, fair pricing, secure operations and continued expansion and innovation. We've built a financially stable business that our customers can be confident will be here for the long term. They have access to our public quarterly financial reports to monitor the strength of the business. All these things protect us from customers considering switching to companies with less operational history, reliability or financial stability. Our customers value our success.

Now to the huge opportunities for Descartes with AI. We're actively investing and delivering results to our customers. Let me hit the 3 biggest areas of opportunity for Descartes. Our biggest opportunity with AI comes from the data on the Global Logistics Network. Descartes has the largest trove of real-time supply chain and logistics data in the world. We process billions of transactions a year. We have massive amounts of clean historical and real-time information on the sourcing storage, classification, transportation, tracking, pricing, service history and financial settlement of most transactions in the global logistics and supply chain markets.

AI technologies need data to function. AI technologies are trained and learned from consuming massive amounts of data. AI technologies are only as effective as the data they consume it only as relevant as the time lines -- of the timeliness of the data they get. Most AI technologies are all trained on the same publicly available information on the Internet.

The real value is being able to train AI technologies using nonpublic information, which is exactly what information we have on our Global Logistics Network. Our Global Logistics Network data is rocket fuel for AI. We'll continue to grow and cultivate data on our GLN in a responsible way that allows our customers to benefit from the collective intelligence of the network.

For us, our key focus going forward is respecting, anonymizing and protecting the data we have while preparing for how our customers may want to use it with newer AI technologies.

Second area is that we believe AI agents will change the future of who uses our technology. We think it will change both what we sell to some customers and how we support them. We think an AI agent -- think of an AI agent as a digital coworker trained to do a specific task. AI agents are excellent for reducing human workload by automating repetitive tasks. They are also helpful to handle matters that aren't affordable to have humans do.

Historically, our services have been designed to only be used by human workers often clicking on icons and entering data. However, that isn't the future. We're preparing our services to be used by either human or digital workers. Our customers expect value from digital workers. They don't want inefficiencies in their business from humans doing low value or repetitive tasks that could otherwise be automated. Rather, they want AI agents performing tests and supporting humans who are making decisions.

We believe this is real and current customer demand for us to meet. I believe our business will shift in 3 ways. We'll provide customers the ability to get AI agents and digital workers through Descartes. We're already doing this in areas of our business like MacroPoint. In MacroPoint, you can hire digital work with, to call drivers and get a location check on where the shipment is another digital worker together missing shipment documents for you and yet another worker to address data integrity issues. Each of these AI agents grow our network, improve the quality of the data the GLN has and reduce costs for our customers.

We'll arm human workers with the information they need to make decisions rather than to perform tasks. User interfaces are going to change, screens with complicated series of clicks and reports will change to specific information needed by humanized to help make a decision.

Finally, services will be designed to be consumable by AI agents, whether they are the Decartes agents for our customers' own AI agents, our services need to be consumable in a machine-to-machine format. This may include providing AI agents access to different types of data in novel ways or enabling AI agents to interact with our own digital workers or technology.

We believe AI agents will be part of the future for Descartes and our customers. We're already delivering value to our customers with a agents and investing in delivering suites of digital workers that can help our customers. In addition to the AI agents I described with MacroPoint, these include natural language searches and AI agents for Descartes GLN data mine U.S. import business. AI ages to help deal with challenging match scenarios for denied party screening on parties within [indiscernible] names and addresses.

AI agents helping determine free trade eligibility based on past practices, helping our customers reduce their tariff bill, AI agents making automated tariff classification suggestions for goods and using AI agents to interpret lengthy carrier rate agreements and present optimal selection recommendations, and there's many more.

And finally, the third opportunity for Descartes is to make our business more efficient. We run a multinational, multicurrency multi-pillar business. We operate an enormous distributed technology infrastructure that can be a target for attack for bad actors. We operate and monitor hundreds of products and services at elite availability levels. We provide support to and build more than 30,000 customers.

We grow our business 10% to 15% a year and have historically added 3 to 4 new businesses to the Global Logistics Network by acquisition every year. With that footprint, there are opportunities to improve our business with automation. We've invested into AI technologies to do this. Key examples are AI tools helping our software engineers with initial coding, customer support automation to enable customer self-help for routine inquiries, advanced AI technologies to harden our network security posture and new tools to monitor network performance.

We're investing in AI technologies to help our team. We will get more efficient. However, our customers expect that we can reinvest savings generated by AI technologies into further improving the GLN and/or reducing our need to hire at the levels we have historically. That seems like a sound approach to it.

Overall, AI is a tremendous opportunity for us. we believe it will spur further demand for our trusted real-time clean formatted GLN data and the collective intelligence of the network. It's already allowing us to deliver additional value to our customers with AI agents, and it's helping make our business more efficient.

We believe that the interenterprise scale network infrastructure of our business puts us in a much better position to benefit from AI than legacy or emerging point or enterprise technology solutions.

And finally, to wrap up, Q4 and FY '26 were very strong financial results for us. I'm excited about how the business is performing and the opportunity we have in front of us. I'm now going to hand the call over to Allan on the CFO role for the last time on one of these calls as we conclude the year. The good news is that Allan is going to remain a part of our business, and it's a privilege to be able to keep working with them. Ed Gardner will be the new CFO following this call, and he also gets the benefit of Allan's experience and wisdom as we make this transition.

Ed Gardner is also on this call and available for investor and analyst questions afterwards along with both Allan and me. So with that, I'll turn the call over to Allan to go through the financial results in more detail. Allan?

Thanks, Ed. As indicated, I'm going to walk you through our financial highlights for our fourth quarter and year ended January 31, 2026. We are pleased to report record quarterly revenues of $192.8 million this quarter, an increase of just over 15% from revenues of $167.5 million in Q4 of last year. Our revenue mix in the quarter continued to be very strong, with services revenue increasing again over 15% to $180.1 million from $156.5 million last year in the fourth quarter. with services revenue representing 93% of total revenue this quarter, consistent with Q4 last year.

Removing the impact of both recent acquisitions as well as the positive impact from changes in foreign exchange rates, we would estimate that our growth in services revenue from new and existing customers, that is our organic growth would have been approximately 8% this quarter when compared to the same quarter last year, and this is up from approximately 7% organic growth in services in Q3.

Overall, our organic services revenue growth in the fourth quarter was the strongest we saw all year. Professional services and other revenue, including hardware revenue, came in at $12.6 million or 7% of revenue, up 18% from $10.7 million in Q4 last year. Due to increases in both professional service assignments as well as slightly stronger hardware revenue this quarter when compared to the same quarter last year.

For the year in 2026, we recorded record revenue of $729 million, up 12% from revenue of $651 million in the previous year. For the year, services revenue came in at $67.2 million or 93% of revenue, up from $590.2 million last year as revenue from new and existing customers as well as from acquisitions, both contributed nicely to our growth -- our revenue growth this year.

Gross margin came in at 78% of revenue for the fourth quarter and 77% for the year in our fiscal 2026. A solid increase from gross margins of 76% realized in both the fourth quarter and the entire year last year. The increase in gross margin for both the quarter and the year was primarily due to operating leverage from our organic growth and services revenue as well as a decrease in low margin hardware revenue compared to last year.

For the fourth quarter and the entire year, our operating expenses increased primarily related to the impact of the 3 acquisitions completed during the year, including the 3G TMS acquisition we completed early in FY '26. The increases in operating costs from acquisitions were partially offset by savings realized from the restructuring efforts we undertook early in fiscal 2026 wherein we reduced our labor force by approximately 7% and as we reacted to the uncertainty from tariffs and the changing freight market at that time. Overall, our operating expenses increased by approximately 11% compared to the prior year.

As a result of solid revenue growth, improved gross margin as well as controlled growth in operating expenses, adjusted EBITDA came in at a record $88.7 million in the fourth quarter or 46.0% of revenue up 18.3% from adjusted EBITDA of $75.0 million or 44.8% in the fourth quarter last year. Looking back to the annual results. Again, we continue to see strong adjusted EBITDA growth to a record $329.5 million or 45.2% of revenue, up 15.7% from $284.7 million or 43.7% of revenue last year.

From a GAAP earnings perspective, net income for the fourth quarter came in at $45.6 million, up 22% from net income in the fourth quarter last year. For the year, net income was $163.8 million or $1.87 per diluted common share, up 14% and from $143.3 million or $1.64 per diluted common share last year. With these operating results and strong collections from customers, cash flow generated from operations came in at a record $75.9 million or 86% of adjusted EBITDA in the fourth quarter, an increase of 25% from operating cash flow in the fourth quarter of last year.

For the year, cash flow from operations was $266.2 million or 81% of adjusted EBITDA, up 21% and from $219.3 million or 77% of adjusted EBITDA last year. Overall, as Ed mentioned, we are extremely pleased with our operating results in the fourth quarter and in fiscal 2026 overall, as after a period of some concern last spring when the uncertainty around tariffs was at its peak, our operating leverage from continued strong revenue growth in the second half of the year has allowed us to achieve a 15.7% growth in adjusted EBITDA, while we also improved our adjusted EBITDA ratio to 45.2% of revenue for the year and also achieved 21% growth in our cash flow from operations for the year.

If we turn our attention to the balance sheet, our cash balances totaled $356.5 million at the end of January, as mentioned earlier, for the year, we generated operating cash flow of just over $266 million, while we deployed approximately $152 million in capital towards 3 new acquisitions. After ending the year with just over $356 million of cash and an undrawn line of credit of $350 million, we are clearly well capitalized and positioned to consider all acquisition opportunities in our market, consistent with our business plan.

So with that, I will turn it over to Ed Gardner, our incoming CFO, to provide an update on a few items as we turn our attention to our current fiscal year, our FY '27.

Thanks, Allan. So as we look to the current year, FY '27, we should note the following items. We expect to continue to see strong operating cash flow conversion north of 80% of our adjusted EBITDA and subject, of course, to unusual events and quarterly fluctuations, including potential adjustments related to future earnout payments that exceed our estimates made at the time of an acquisition.

After incurring approximately $5.7 million in capital additions this past year, we expect to incur approximately $6 million to $8 million in capital expenditures this coming year, mainly related to IT equipment purchases. After incurring an amortization expense of $81.2 million this year, we expect the amortization expense will come in at $69.1 million for FY '27, with this being subject to adjustments for foreign exchange changes and any future acquisitions.

After paying contingent consideration or earn-out payments for approximately $1.7 million on past acquisitions last year, we currently anticipate that we can make additional earn-out payments of up to approximately $9 million in FY '27. Our income tax rate in the fourth quarter came in at approximately 25.6% of pretax income, resulting in a tax rate for the year of 24.6%. This is lower than our blended statutory tax rate of approximately 26.5% mainly as a result of the benefit of certain onetime tax items realized in FY '26.

Looking forward to FY '27, we're expecting the tax rate will be in the range of 24% to 28% of our pretax income, which means it will be something on either side of our blended statutory tax rate. And finally, we currently expect stock compensation to be approximately $17.2 million for FY '27, subject to any future equity grants as well as any future forfeitures of stock options or share units.

I'll now turn it back over to Ed Ryan to wrap up with some closing comments and our baseline calibration for Q1.

Thanks, Ed. I wanted to comment on 2 areas that are impacting global trade right now and impacting our thoughts as we plan for the quarter and the year ahead. Tariffs and ongoing and the ongoing Middle East military conflict.

On the tariff front, there have been plenty of headlines about the U.S. Supreme Court's decision in validating EPA tariffs. That was followed by the President implementing a 10% global import tariff that may go to 15%. That can be in place for 150 days unless extended by Congress. Separately, several core decisions are considering the process for a refund of the more than $150 billion of invalidated IEP tariffs.

Here are some tariff-related things we've noted in monitoring the GLN and speaking with our customers. In the several days where there were no valid U.S. import tariffs in place. We saw an influx of imports the United States and companies taking action in free trade zones to move goods from international to domestic status.

The current new tariff regime is temporary and its legality has already been challenged. This leaves our customers in a further period of uncertainty with difficulty making decisions about pricing, cash flow and import levels. The U.S. issued its 2026 trade policy that reinforced its commitment to using tariffs despite the Supreme Court EPA ruling. This includes further investigations in specific sectors with a view to implementing further tariffs beyond the current structure.

The tariff landscape is volatile and compliance is becoming more complex. Rapid shifts in tariffs are likely to continue to come. The process for recovery of [ equal ] tariffs is still unclear. However, our experienced tariff and duty recovery team that has been in place for many years is working with customers already. Recovery processes may require volumes of revised electronic filings to be made to the U.S. custom systems, and we're working with customers to be ready for that potential influx. It's unclear how intermediaries like customs brokers will compensate shippers for tariffs if the intermediary receives a refund. This becomes even more of a challenge for high-volume intermediaries serving thousands of independent shippers.

For our customers, this all means the tariffs are no longer a stack compliance test. You don't think about them once a year and then go run your business. Instead, trade exposure, tariff modeling and regulatory change are dynamic risk management challenges. It's critical to have a global trade management system supporting real-time global tariff data, trade intelligence and trusted partners like Descartes to share intelligence and manage the complexity.

Overall, right now, the invalidation of the EPA tariffs is a source of further instability and uncertainty for our customers. However, it's confirming the value that our tariff management, de-recovery and custom filing solutions bring to our customers in meeting these challenges.

The second ongoing matter impacting global trade are the ongoing military events in the Middle East. From a supply chain and logistics perspective, the impact includes the Strait of Hormuz is effectively closed, trapping many vessels in port and blocking further traffic. Suez Canal remains a risky sea route and ocean carriers have rerouted to [indiscernible] travel around the tip of South Africa. This has caused ocean rates to increase substantially.

Some air spaces have been closed or are deemed too hazardous for safe flight impacting the movement of air cargo and existing capacity. There's been an increase in fuel prices, which impacts both international and domestic shipping activity. We anticipate changes to the existing sanction framework impacting Iran, which will require further shipping scrutiny. Things are more volatile and complex for our customers than ever. We see them adjusting the supply chains to establish new relationships to keep goods flowing, adjusting pricing to reflect unplanned shipping costs and updating delivery expectations with customers to reflect longer voyage times.

We also expect an increase for our optimization solutions that helped decrease vehicles used and miles driven, something we usually see as fuel prices spike. The first 2 months of 2026 have been chaotic, volatile and uncertain for our customers, shipping has proven to be resilient over time, but we're monitoring our network for trends with the latest developments.

For now we approach the year as our customers are cautiously with the expectation that rapid adjustments to more unforeseen circumstances will be necessary. We keep this in mind as we consider how we're calibrated as we start the year.

In our annual report, we've provided a comprehensive description of baseline revenues, baseline calibration and their limitations. As of February 1, 2026, using foreign exchange rates of $0.73 to the Canadian dollar, $1.19 to the euro and $1.37 to the pound. We estimate that our baseline revenues for the first quarter of fiscal 2027 were approximately $164 million. Our baseline operating expenses were approximately $99.5 million. We consider this to be our baseline adjusted EBITDA calibration of approximately million for the first quarter of fiscal 2027 or approximately 39% of our baseline revenues as at February 1, 2026.

We're currently operating above our expected adjusted EBITDA operating margin range of 40% to 45%. Our margin can vary in any period given such things as revenue mix, foreign exchange movements and the impact of acquisitions as we integrate them into our business. For now, we're keeping our target ranges of 40% to 45%. However, we'll monitor how we're performing over coming quarters to consider whether any upward adjustment is appropriate. These remain on certain times for our customers. It's a challenge for them to know what they can rely on in this global trade environment.

Our goal is to continue to show our customers and other stakeholders that one thing they can rely on is Descartes. So thanks to everyone for joining us on the call today. As always, we're available to talk to you about our business in whatever manner is most convenient for you.

And with that, operator, I'll now turn it over to you to handle the Q&A portion of the call.

[Operator Instructions] Our first question comes from the line of Dylan Becker from William Blair.

I really appreciate the question, a nice job here. Maybe and appreciate a lot of the color on kind of the AI conversation in the AI narrative. I think you did a good job talking about the value of the multisided network and your capabilities there. But if were to kind of double-click and maybe dig deeper into the use cases you're seeing and how your customers are kind of asking you and actively deploying AI. I wonder if you could give us a couple of examples on maybe one where the value of the network is enabling you to kind of see context and quantify value that might be a little bit more difficult if it were something more like a point solution that was trying to solve this problem, but then also how you're maybe thinking about the quantification or monetization of that value and what that can look like from a revenue perspective for the business going forward?

Well, there's a ton of -- I'll just give you a broad example. We process shipments all day long. And invariably, we get information over the course of the day that says that something happened to that shipment. So IoT data comes in, other news comes into us, maybe a status messages to tell something is wrong. And sometimes doesn't tell us if something is wrong, it just tells that it's been in the same place for too long. We can use AI to identify that problem.

We can use AI to figure out what to do about that problem. And the important part for us is that we know what the customer was trying to do in the first place. And this may be happening in the middle of the night or the customer like they might not try to figure this out manually until they get in the next day and they probably have lots of problems that might be caused by the same port problem or whatever might be out there. During the night, we can have AI agents go in and fix those problems, right? And say, "Hey, this shipment is going to be late, and it's going to be late by several days if we don't do anything about it. "

And we may be able to go into that shipment, find out if something is wrong, know what was supposed to happen and rebook them on a series of new ships or plans or trucks that puts them in a situation where it's only late by an hour or 2 or a couple of hours. For what might cost them $1 or $2 on our network, we might save them hundreds of dollars and days worth of time trying to figure this out.

And here's that example I just gave you could encompass lots of different AI solutions, but all of them aimed at trying to find out where problems exist. And help the problem a customer solve it before they even know the problem. We're just coming back to them the next day and they say what happens to the shipment and "oh, it's 5 hours, it's going to be 5 hours late, and then they look a little further and they go, well, was going to be 5 days late. " And in the middle of night, Descartes fix this automatically for $2, whatever. And we see all kinds of opportunities for that all over our network.

Perfect. No, that's very helpful. And then maybe I also appreciate the color on kind of the evolution and kind of dynamics relative to tariffs in the Middle East. And if we were going to step back traditionally, global trade complexity tends to serve as a net positive to your point, for the business. But is there any way that you would kind of contextualize the puts and takes of any kind of prolonged scenario here?

And what that looks like if some of those shipping channels continue to be blocked for extended period of time, the implications on volumes, the importance on more subscription -- just any way to kind of think about the puts and takes between the 2 segments of the business there.

I mean, most of the time, the cargo still has to go. And it's just a matter of how it's going to get there. And you saw several examples over the past 10 years where when it takes longer, we get more bookings because people book both ways around the world. We -- our customers' prices go up for their customers, and it creates a lot of supply chain disruptions. That has traditionally benefited Descartes because we help them sort through those complexities. We help them go see what all the options are. We help them make new bookings so that they may get cargo in from 2 different places in the future, then maybe have several factories around the world and they decide to do something else to get the cargo in and they have to figure out what the tariffs and duties are when they do that, maybe it's more money.

But you also get the target there a week earlier. And all kinds of things like this where customers use our network and databases more frequently because these problems occur. And I think that's what we're going to see here, too. I don't know how long this is going to go on. I don't know how long that Strait is going to be closed. There's talk about mines being late in it right now. There's also talk of escorting ships through it.

So we're just going to have to see what happens. But in the meantime, our customers have a lot more to think about. And a lot of the times, they have to think about it, they go into our systems to figure out what to do, and that's usually good news for us.

Next question is from Chris Quintero from Morgan Stanley.

Congrats on the solid set of results here guys. I wanted to ask about how you are thinking about capital allocation given where the stock is now and obviously, how you all feel about the defensibility of the business and the opportunity on the AI front. And -- what does that mean for potentially organic growth versus reported growth and the delta there?

Okay. There's a couple of questions in there. One, on the acquisition front. We're starting to get to a point where prices had come down, and we were getting more deals done. And now you see what's going on in the public markets, and you know that has to translate into the private markets. And that causes another reset and set of negotiations that occur.

When the value of public companies go down, that's what private equity firms would look to typically to say, hey, that's that's what these things will be worth eventually. That's why you should buy this company and that company. That puts them in a -- it puts us in a situation where we may be able to buy assets for lower dollar amounts than we have in the future or have in the past -- excuse me. That will be good news for us.

As I mentioned in the beginning of the call, we're sitting on a lot of cash. We're sitting on a lot of excess capacity to borrow, and we probably have even more than that if we wanted to. We're $350 million now. it's like 1x EBITDA, so we can probably get more if we want going to expand that to get more deals done. So we think we're in a very good position, ignoring what the stock price is and the value of the stock and we can't help the people think we get lumped into the technology companies.

I made a whole argument at the beginning of this call that we might not be appropriate to lump us in the semi guys. And maybe the problems being overblown to begin with. But we keep making a heck of a lot of money, and we keep making more money than we did the quarter before for 20 years in a row now. And we use that money to buy companies up.

And when markets are in turmoil, and we keep making a lot of money, and we use that money to buy companies, we think we're going to be in a very good position to be able to do that, and we're just waiting looking, trying to make good decisions. And we would like our stock to be up, but that's not really what's material every day. It's we're running this business, and we keep getting -- making the business bigger and we keep making the business make more money, and we use that money to go buy companies and we don't think big games changing. We think are -- that's what we're going to continue to do.

When I look back at some of the worst times in the financial markets and think about what happened to us, those were some of the best times for us in the financial crisis and the pandemic we really benefited. And I think you may see that even here, and we're certainly near enough to be in that position. We're healthier than other companies. That puts us in a good position to buy it.

Also, some of the things I mentioned in the beginning of call, the fact that we're our network is a great place for this AI technology. There's a lot of AI companies out there. Now almost everyone I look at in our space, they're all small. They all look like features to me that will be great on top of our network. And I think that's going to put us in a good position as those companies, some of them succeed and they want to go further.

We're a good place for them to combine because we have 30,000 customers, and they're using our network to do some of the things that will be a great fit for some of the features that come out from small companies. And we want to be in a position to either merge these companies into ours or if they're real small and the technology looks cool. But because of the way AI works right now, it might not be hard for us to replicate that functionality, and we may have a decision to make about whether we want to buy the company. or just build the functionality ourselves.

And it used to be that building functionality took a long time and as it gets to be easier and easier to build it in the half is faster and better. you might see us make more decisions where we say, hey, we're just going to build better selves. So we'll see what happens, but I like the position we're in, for sure.

Got it. And then just as a quick follow-up on professional services. How should we think about the ground cloud business and the safety retraining that needs to happen? Is that going to be a tailwind for fiscal year '27? How should we think about how much of a benefit that could be?

Well, as FedEx and more and more companies like them start to outsource drivers, we think that Grand Club business is going to be more and more valuable, some of the stuff that they're doing right now. I think likely to help us any company announce that you have to do more stuff and we're the dominant service provider in that business, it's an opportunity for us, so we're excited about that.

Our next question comes from the line of Paul Treiber from RBC Capital Markets.

Congratulations on the solid results. The -- just a question on next quarter baseline. Does baseline include the acquisition of Order Mine. And then also related to baseline, are you assuming strengthening organic growth or consistent organic growth compared to this quarter?

So I believe -- and Ed, correct me if I'm getting this wrong, but I think it is up February 1, so order mine is not in there, small DOL. So I wouldn't imagine it would be material. Maybe, Ed, you can take the second part of that question?

Yes. I think generally, as we come across into any given quarter, we expect at least plan for a similar organic growth rate in that quarter. We normally see a variation of 1 point either way. Obviously, it can be bigger either way. But not the thinking coming in.

Lot of uncertainty answer, Paul. So it's hard for us to -- we're happy it's going back up to where it was, and we hope it stays here and maybe even grows a little bit. I don't see anything out there that's going to get us to the 15% that we were at in the middle of pandemic. And I don't see anything that's going to drop us back down considerably.

Okay. Nice to see the improvement this quarter. And a second question, just on the M&A team and with Ed moving into the CFO role, to what degree can you speak to like the M&A team, the the composition there and if you're backfilling Ed's role?

I can probably Yes, yes. Yes, I can say. Look, we've got some internal movement as a result, we've been getting ready for this for a while, as you can imagine. And part of that has been more people internally. -- in M&A as well. We've got a general manager structure where we've got GMs that are involved in helping shape the business for each of our pillars, and those GMs have been getting more and more involved in the negotiation with founders and being the front person as they really understand the business, and that's been really helpful us.

And it's actually allowed us to increase our capacity with without growing the team as much as we'd expect over the last, let's say, 3, 4, 5 years. And so I think moving forward, we plan to do more of that. And we do have some openings. We do have an opening in the corporate development team, but we've got someone stepping in to lead it right now internally.

It's also -- and by the way, Paul, I mean, 1 of the reasons I was ticking around is not only to help with the transition for Ed, but to help in M&A deals, which she was always quite involved in as well. So Allan moving back towards that just to help out and make sure we're getting all the deals that we want to get done as companies for us because he's been doing it for a long time for us.

Our next question is from John Shao from TD Cohen.

I take my question come back to a strong quarter. So could you maybe give us an update on the mentality of a customer at this point? I know you guys are pretty close to them. So do you see them actively requiring AI features or just early-stage conversations.

Did you name a specific customer in there? Or did you say general.

Just in general, do you see -- let's say, when you're getting conversation with the customer, do they also require the AI is 1 of the important features or it's just something nice to have?

No. I think a lot of our customers and they may be well behind our thinking in it, but they're still starting to say, "Oh, these things can help me? Do you guys have agents that we can use to solve some of these problems -- can you just take it over and saw some of the problems for me. And you know our sales rep a telling the AI agents that we currently have and the ones that were in the process of building so that they can figure out how to incorporate it into their processes.

I think it's early days for our customers in this -- for most of them. Some are a little more advanced than others, but we're well ahead of that and trying to build and anticipate the agents that we would be providing to them to help them get jobs done in their back office. And maybe you have agents that help communicate with some of the agents that we're going to have internally that can provide them information so you really have agents talking to agents, AI agents talking to AI agents. And then just using their employees to make decisions 1 step above that, but a lot of the work has been done to make that a faster decision to make.

That's great color. My second question is, could you maybe help us break down your service organic growth this quarter? How much is coming from upselling and how much is coming from market share gains? Because I do remember you were talking about some market share gains last quarter.

We're getting it for both. I don't know if I don't have specific numbers on it, but it's coming in both directions and it has been for a while. You hear with a lot of the AI functionality we're going out, that's starting to visibly produce revenue, which is great, new organic growth.

We also have, in several instances, we have situations where we've done a whole lot better than our competitors because we're bigger company that maybe had better thoughts on how to solve bigger problems in the market. We also have lots of different products. So it's easier for the customers to switch to us.

In a lot of cases, I think some of our competitors have indicated bullishly, I think that they might end up being a competitor to our customers one day and jump out of the technology business and into being a broker or a order or some other type of middleman we've been very clear over the years. That's not what we're doing.

We're out here to provide technology. And if there's money to be made doing your job, I'm going to sell you technology and let you make the money. I'll take $10 a transaction to provide a technology solution that helps you make $200 a transaction as to a customer, and I'll be happy about it. And we had competitors that had made overtures towards -- well, maybe I'll just take the $200 and that now you're not a technology company anymore, how you're a freight broker or free Ford or whatever. We have never made that leave, and we will never make that leap.

We provide tools and software and a network to solve problems. And there's a lot of money to be made by our customers in doing that. our experience has been that's great because they use our stuff more and more and more, and they're happier and happy with us for giving them the opportunity to do it.

Next question is from Stephanie Price from CIBC.

Just sticking to the AI topic. I hope you could talk a little bit more about the AI opportunity around data on the GLN, -- do you expect you can eventually monetize the data? Are you seeing it more in terms of selling additional products? Like do you have some customer use cases at this point that you can kind of point to?

The -- using the data, remember, it's our customer data. I'm not selling their data to anyone. But to the extent I can anonymize it and use it to help them make better decisions. And I may be able to anonymize everyone's data and use it to help specific customers make better decisions because I know things that are going on generally in the supply chain. I think you can see us do that all over the place segment. We have -- the example I gave a minute ago right at the start of the call, right, sort of the community section is a great example of that.

We see a problem in a port -- who knows how we hear about that. We may hear about it from 1 carrier. And then we're helping 30 freight forwarders fix the problem because we go got there was a problem in Rotterdam right now. We need to get all this cargo out of routine. They might have to wait to come in the next morning at which point they're well behind in the process of doing that. And maybe the solution is moving everything to anchor whatever. And we could do that with human invention, and we can do it very quickly.

And the reason we're able to do it is because we found out about it quickly because several customers may have it happening to them when we find out from watching their data. and then do something about it because we know what they were each attempting to do in the first place. We knew where they wanted this shipment to be 20 days now. And that might require several new bookings, right? I got to tell hey, we're coming into a different port.

I got to get different trucking companies got they get different railroad. They're going to get different dray haulers at the end of these moves. All coordinated together and working on what is affecting an effective new shipment. And our customers will be quite happy to hear we did that overnight to solve a problem for them and still get the cargo there on time or roughly on time, and we did it for just a couple of hours.

And there were no humans involved. And we see opportunities for that significantly increasing over the years and expanding the size of our network as a result and really helping our customers soft problems that required a lot of manual intervention just 2 years ago.

Okay. That's great color. And then on the margin side, obviously, very strong margins in the quarter, trending above your 45% target. Are there any metrics you can point to around AI in terms of potential cost savings or productivity improvements you've seen from AI so far? Or should we think of these more just in terms of the 7% headcount reduction and the flow-through from that?

I mean there's a couple of components. The 7% reduction was a long enough time ago that it was already in our numbers in previous quarters. We always have on our network and our data content businesses as we get new revenue, our costs are relatively fixed. So there's a constant push up in those businesses. and some of the most profitable businesses we operate and they get more profitable every quarter. And then you add AI to that, where we're able to do more stuff, more efficiently handle more customer support calls, develop more lines of code, answer calls more quickly, things that one, make customers happier to deliver functionality to them faster. -- and cost us less to do it. And it's a win all the way around.

And I think that's -- I talk to my friends. I'm independent of Decadent talking to my friends about what happens with today. I think over time, I everyone's job may change, but I think they're still going to be work for everybody. You might have to get a different job or do something different in your job every day, and that might be frustrating to some people. But just like when the Internet came out, I remember Allan Greenspan talking about the massive changes in productivity that it created. And I think we're about to see that all over again. I would look and go -- it's hard for me to imagine that the world's economies wouldn't expand significantly because of this.

I see what's just going on in my company. And I think we're at the tip of the iceberg in this right now. It's going to be massive for us and a lot of other companies in terms of either cost savings or increased productivity or increased dollars that we're able to bring or increased customer satisfaction. And it's probably going to be all of those things together. And if every company is able to do that, you're going to see the whole world's productivity pick up massively, and that's got to be good. It's got to be good for the world economy. And it might be a little frustrating for people that have to change their job, but they will.

The Internet change a ton of stuff, too. Mobile phones change a ton of stuff, too. And this is the next big one that's coming along. to me, it's probably in line with the Internet coming out, a massive, massive change that's going to make every company more productive. And for companies like ours that are in the middle of it, it's going to provide us a lot of opportunity to expand and help our customers do much more sophisticated things that they couldn't have imagined 10 years ago for us to be able to do for them. And now it's going to be possible. And I think that's going to be great news for everyone.

Our next question is from Cole Couzens from Wolfe Research.

I know you're not reliant on seat-based pricing models, but I believe there's some small exposure in your software business. Is there any way to quantify like what percent of revenue is currently seat-based? And is there a chance that you could change this? Is there any chance you could change this going forward like some of your competitors?

It's about 15% of our business is seat-based. And without question, we will change it. It's changed over my lifetime, I've seen the pricing mechanism change like 10x and always aimed at what are we doing for you and how much is that worth? And I don't if I'm charging the per seat to do that. And all of a sudden, if there's a Gentech agent doing it and we can't measure seats anymore, we're going to find another way, transaction-based pricing, how many bookings build lading or whatever did you do in a month. Everything has minimums in our business anyway. So it's just going to be a new mechanism. And you may be referring to some of our customers, our competitors that have done some stuff to move -- to change it and we're perceived to be doing it unfairly. I mean, I think one of the things our customers have come to expect from Descartes is that we're always pretty darn fair about how we price stuff. And when we put something out for them that changes the way that we do it, it's a fair way to do it. But again, it's a small part of our business and not something I'm particularly concerned about.

Sorry, I was just going to add to that in case it was hard to hear is 15.5%. -- just under 15 in case it sounded like $50 million.

No, I got that. And maybe just on the organic growth in the quarter. It sounds like it came from both market growth and share gains. Maybe if you can just expand more on what's driving these share gains? And how sustainable this is going forward.

I talked about it a little bit before, but we're a big company with a lot of solutions and a lot of customers, and we're a safe choice. I spent some time talking about that in the prepared comments. And as things get complicated, I think people look to go to the safe guy, they know it's going to handle the problem. We have some businesses where our competitors sell and they're facing a little bit.

We had some competitors that have jacked up prices on customers and made some customers angry, all of those things came to benefit us. And sometimes, I would just stand to Stephanie a minute ago, sometimes it's tough to sit there and be the guy that's more than fair all the time and well, I could take advantage of this situation and make more money in the short run, and we never do that.

We're we always are planning for the long-term relationship with these customers. I'll just pick on one of them, but I would always say to people, there's only 1 FedEx, don't get in a fight with them or UPS or Congo or whatever else, right? And we've gone to great strides and at our own cost to us because we could have been pigs about it at various points. and chose to take the customer-friendly route because if I have 40 contracts with them, I would like to sign the 41st and the 42nd and the 43rd too. And if you start doing stuff that makes them think you're not a great cat to do business with, they're not going to sign thos next contracts with you.

And we've taken the approach that's key, play the long beam for all these things and it's been paying off over time as we get bigger and bigger. Everyone always told me it would get harder as we get bigger. And I think because of the approach we've taken to it, it's always gotten easier. They've come to treat us like partners as we have more relationships with them. But when we're fair with them, they're very comfortable signing up new contracts with this. And some of that's playing out now and to our benefit as we get bigger and bigger.

Our next question is from Robert Young from Canaccord Genuity.

First question for me would be on the trade data and intelligence and real-time tracking, they've been talk 1 or 2 drivers of growth for a number of quarters now. just thought it would be interesting to get some insight on the degree of penetration into the GLN user base? Like are we still very early in the deployment, there's been a lot of world shakeups to drive that? And how far are you into the user base?

I think there's still a long way to go. A lot of competitors in that space were bought up by people that don't really serve the supply chain, they serve banks and legal law firms and things like that. A lot of our competitors kind of slowly walked away from the business, and that's been great for us. We become the absolute global leader in it. One other companies have come up for sale in that space, we bought them. and become a more dominant player in that industry.

And therefore, the place that everyone always turns to. And the more governments come out and change these tariffs all the time and the more they changed the sanction parties or add to the sanction partners. The more people have to pay attention to that and buy more access from us. And there's a long way to go, and it's going to keep coming. And you might see us get into related businesses with it.

You also may see us using AI to combine some of our real-time data off of our network anonymized to supplement that data and make it more valuable. So we like that business in the long run. I've also heard people say, "Hey, well, AI let somebody else get into that business and I get there's not a chance. " It's so much going for us there. We have so much to get that data even though it's publicly available to get it from all 140 countries and then all of the different agencies within that country that are able to identify sanction parties or add to the tariffs or duties regime and we then put all that data and normalize it, put it all in one database.

We then distribute to our customers in whatever format they want SAP New whatever they want to use it in. And then we don't charge that much for it, right? So it doesn't make any sense for anyone to try and replicate this because I'm charging you $20,000 a year. It's just like it's practically free. And maybe the most important part is you can't go to the government. And when they say, "Hey, why did you shift to this guy you weren't allowed to ship to and say, well, I built my own AI tool and the government is going to look at it and go, well, it didn't work. It's a lot safer to say, well, I got it from the current and the government goes, well, Descartes usually right about these things.

I wonder who's actually right here. We're a safe choice. And for a very low cost, we think that puts us in a very defensible position. and to trend for some of the trying to replicate that in the long run, I think it's a full banner.

Okay. My second question, this agentic opportunity for self-healing logistics that you keep coming back to as an example. It sounds like you're framing it as a future state, but and you've got the data and you've got the signaling from the network. And so I'm curious, is there a technology gap -- or is that just execution and engineering to roll something like that? Like how far realistically and is that...

We're doing some of it right now. It's going very fast. -- the most interesting part of that, and we haven't talked about it much yet. I've alluded to it a couple of times. It's going very fast right now. Our ability to come up with new ideas and roll them out is now weeks and months versus months and years.

We're coming up with new ideas. And the ideas are coming so fast, and I'm shocked at how fast we're building these things using off-the-shelf AI tools that we're adding to our network and using against our data, as I mentioned in the prepared comments, and it's going very, very fast. And I'd say half the cases I don't even have to sign the customer to a new product. They're already signed up to have them going to manage shipments.

They pay a certain price to do that. And if I have -- if I have the opportunity to go in and change their shipments to their benefit it works out great for me. And we're so great for them to, for a couple of bucks. I'm solving a very big problem for them. And I think there's -- we keep thinking of more things we can do like every week, there's more things coming out or some of the -- and our organization is talking to our customer goes, "Hey, you know we can do this for the customer.

And when we used to have those concepts or this thing happened 10 years ago, it was like, "Yes, we do that for the customers could take us 10 years to code a year to code that. Well, now it's like 3 weeks and there's no coding involved. And we're solving the problem for the customer this is a huge opportunity for us and a big benefit for our customers. It's a head scratch to me right now what people are saying about the lumpiness in with companies that are enterprise software companies.

And I don't even think I believe that they're in the same kind of trouble that everyone else does. And I don't think we're like time either. I mean, I think we have this network with all the proprietary data and our customers are helping us -- we're helping our customers manage things. And AI can help us do it better. And I think we're in the catbird seat going, -- all we've got to do is execute. And if I complement our company at anything, it's we're very action-oriented and we're pretty good when we get an idea, we go after it hard and make it happen. And now it's a lot easier to make it happen. So we're excited about the opportunity that we have.

The next question is from Mark Schappel from Loop Capital.

Just. 1 here. During your prepared remarks, you called out areas of strength in your business, global trade was 1 visibility, customs and regulatory. What parts of your business maybe weren't quite as strong as you would have liked?

I mean, most of the businesses to Cuba stellar numbers, most of it as every part of our business was performing better than we hoped. I don't know if there's anything I'd call out -- I don't know if you have any thoughts on anything that was not great. I mean I'd love it if the trucking volumes were better and funny enough or getting better right now. And even in that business, we took pretty well we're able to take a bunch of business from our competitors. So that business was up. I don't know if there's any that you would say we underperformed at?

No, I think come network volumes in general are still not where we'd love to see them, whether that's -- Air has been growing reasonably well. I think you'll see from the available -- the information bailout there. Ocean vary depending on the country and the U.S. freight market has been in a freight recession for a while. So we'd love to see those volumes pick up. But generally, yes, we're really happy with the performance.

There are no questions at this time. I would now like to turn the conference back to Mr. Ed Ryan for the closing remarks.

Great. Thanks, everyone. We appreciate your time on the call today, and we look forward to reporting back to you on Q1 and Jim. Have a great evening. Thank you.

This concludes today's conference call. Thank you for participating. You may now disconnect.

Good afternoon, ladies and gentlemen, and welcome to Descartes Systems Group Quarterly Results Call. [Operator Instructions]

I would now like to turn the conference call over to Scott Pagan. Please go ahead.

Thanks, and good evening, everyone. Joining me in person on the call today are Ed Ryan, CEO; Allan Brett, CFO; and Ed Gardner, EVP, Corporate Development. I trust that everyone has received a copy of our financial results press release that was issued earlier today. Portions of today's call, other than historical performance, include statements of forward-looking information within the meaning of applicable securities laws. These statements are made under the safe harbor provisions of those laws.

These forward-looking statements include statements related to our assessment of the future. and current impact of geopolitical trade, tariff and economic uncertainty on our business and financial condition; Descartes' operating performance, financial results and condition, cash flow and use of cash, business outlook, baseline revenues, baseline operating expenses and baseline calibration, anticipated and potential revenue losses and gains, anticipated recognition of revenues and incurrence of expenses potential acquisitions and acquisition strategy, cost reduction and integration initiatives, timing of management changes, the approval and potential share purchase under a normal course issuer bid and other matters that may constitute forward-looking statements.

These forward-looking statements involve known and unknown risks, uncertainties, assumptions and other factors that may cause the actual results, performance or achievements of Descartes to differ materially from the anticipated results, performance or achievements implied by such forward-looking statements. These factors are outlined in the press release and in the section entitled certain factors that may affect future results in documents filed and furnished with the SEC, the OSC and other securities commissions across Canada, including our management's discussion and analysis filed today. We provide forward-looking statements solely for the purpose of providing information about management's current expectations and plans relating to the future. You're cautioned that such information may not be appropriate for other purposes. We don't undertake or accept any obligation or undertaking to release publicly any updates or revisions to any forward-looking statements to reflect any change in our expectations or any change in events, conditions, assumptions or circumstances on which any such statement is based, except as required by law.

And with that, let me turn the call over to Ed Ryan.

Thanks, Scott, and welcome, everyone, to the call. Today, we're reporting record strong quarterly revenues and adjusted EBITDA. We're now ahead of our year-to-date plans and focused on a strong end of the year. We're excited to go over these results with you and describe how we're well positioned to help our customers in an environment where they're making many tariff and artificial intelligent investment decisions. But first, let me give you a road map on this call.

I'll start by hitting some highlights of last quarter, some aspects of how our business performed and how we're positioned to help customers. I'll then hand it over to Allan, who will go over the Q3 financial results in more detail. After that, I'll come back and provide an update on how we see the current business environment and how our business was calibrated for Q3. And we'll then open it up to the operator to coordinate the Q&A portion of the call.

So let's start with the third quarter that ended October 31. Key metrics we monitor include revenue, profits, cash flow from operations, operating margins and returns on our investments. For this past quarter, we again had strong record performance in each of those areas. Total revenues were at a record high of $187.7 million, up 11% from a year ago. Record high services revenues were up 16% from a year ago with our continued focus on generating recurring revenues. Record net income was up 20% from a year ago. Record income from operations was up 24% from a year ago. Record adjusted EBITDA was up 19% from a year ago. Our adjusted EBITDA margin was up 3 points from a year ago to 46%. We generated a record high of $73 million in cash from our operations, up 22% from a year ago. So strong record results across all of these key metrics.

At the end of the quarter, we had $279 million in cash, and we were debt-free with an undrawn $350 million line of credit. That included us using $37 million of our cash in Q3 to acquire Finale inventory, an acquisition that we discussed on our September financial results call. We remain well capitalized, cash generating, growing and ready to continue to invest in our business. Our principal growth drivers in Q3 were largely the same as I've described in detail in past quarters. They are as follows: first, global trade data and intelligence. It remains a chaotic tariff and trade environment for our customers. In the last 90 days, our customers have seen these significant changes. -- want a truth on tariffs between China and the U.S., extending the tariff status quo while negotiations continue; two, tariff expansions on metals, copper, timber and furniture; three, tariff relief for food stuff; four, new reciprocal trade agreements between the U.S. and countries like Argentina, Switzerland and Malaysia; and five, the implementation and temporary pause and enforcement of BIS 50, a regulation that expanded the number of denied parties that the U.S. entities needed to screen against.

We continue to be a provider of choice for our customers for car data, sanction party assistance and research on trade flows. We help our customers keep their business flowing and help them plan for tomorrow. When things are changing rapidly, they rely on us for timely and accurate updates. In Q3, the changing trade environment provided strong demand for our solutions. Second is foreign trade zones. The uncertain trade and tariff environment has many of our customers needing more of our help to find the most efficient way to import goods. One mechanism that's being investigated by more of our customers than ever before is foreign trade zones or FTZs. These are designated spaces for U.S. companies to import goods on a tariff and duty deferred basis, only triggering payment when the goods are removed from the FTZ for shipment into free circulation. There's a detailed regulatory regime to manage these FTCs, including keeping track of everything flowing in and out of the FTZ and regular government reporting. However, with heightened and uncertain tariffs, it has become an effective way for our customers to manage their imports and cash flow. We've seen higher demand for our FTZ solutions than in previous years, and that was a good driver again this quarter. The third is e-commerce customs clearance. Earlier in the year, the U.S. eliminated the dominates exemption, which allows foreign companies to ship goods duty-free to U.S. customers where the value of the goods was less than $800. With that exemption gone, foreign e-commerce sellers needed to adapt to a new regulatory structure with new filings and submissions of tariffs.

To do this, these sellers and their brokers need solutions that can handle large volumes and velocities of shipments that interact with U.S. customs and get goods quickly to prevent delivery delays. We have market-leading solutions to help these high velocity importers, and it was a strong driver of growth in the quarter. The fourth is real-time shipment visibility. Shippers and brokers want real-time visibility into the location of shipments in transit. Shipment tracking is an expected part of the consumer experience. So this is critical information for customers. In the business-to-business environment, shipment tracking allows for better planning on preparing delivery resources, whether they be loading dock doors or human resources unloading trucks. Getting accurate location information isn't always simple, particularly in the truck market as many smaller independent truckers may not have the technology to provide automated location information.

However, our MacroPoint solutions are the best at getting tracking information, leveraging carefully designed mobile applications and artificial intelligence agents. This market-leading tracking rate led to continued strong network performance by MacroPoint in the quarter. So similar revenue drivers to previous quarters have contributed to our record revenue performance this quarter. When combined with the cost rationalization effort we undertook earlier this year, we also had record operating performance.

So next, I want to talk about artificial intelligence because it's becoming a bigger and bigger part of our business. I mentioned artificial intelligence helped our MacroPoint business, but I wanted to take a bit more or talk a bit more about how AI impacts cart overall. First, let me give some context for when you're thinking about Descartes. Descartes is the network business with a huge network infrastructure. We run the global logistics network. We're built by connecting huge numbers of shippers, carriers, governments and logistics intermediaries together. We are not an enterprise software business. Logistics and supply chain problems are not enterprise problems. They are intra-enterprise problems and challenges. To solve them, you need data from multiple external sources, and that's what we do.

We transmit and house massive amounts of data to help our customers source trusted clean, formatted and real-time data because that's what's most valuable to them. So the questions I've been getting from shareholders, analysts and others is what's the impact of artificial intelligence on Descartes' business? The answer is that the impact is overwhelmingly positive. I'll talk about this in detail, but in summary, AI increases demand for our data and decision-making tools. Our customers want massive amounts of clean, formatted real-time data to help them make decisions on our own network or to power their own AI investments. Data is the fuel for AI solutions. That data needs to be from a trusted source, everyone knows poor data can lead to poor decision-making and execution.

AI allows us to offer new solutions and services leveraging our network infrastructure and data and AI allows us to run our network and business more efficiently.

Now let me go into a bit more detail. The first GLM data powers AI. AI tools massively speed up the pace of automation for our customers with AI agents or agentic AI and we expect that most of our customers will eventually be running some form of AI tools to automate processes within their business. These AI tools are powered by data, businesses that will be the most successful with AI are the ones that can train their tools with enormous amounts of current and clean data. In the supply chain and logistics world, that means that our customers' AI strategies and successes relying on getting more clean data from their trading partners. Our customers need information about things like the location, schedule and amounts of resources not in their control, including inventory, vehicles, vessels and people. This is why AI makes Descartes Global logistics network even more important for the customers. The Global Logistics Network helps our customers get massive amounts of real-time data for an enormous number of global trading partners delivered in a clean manner that can empower AI tools.

The scale, reach and global nature of Descartes network has never been more important to our customers. Descartes is a network business, we get paid as we help customers get and process more data. We believe that AI is a huge potential tailwind in demand for our global logistics network. The second is that the GLN data includes the collective intelligence of the network. We expect that our customers will use AI to answer questions about how to best run their own businesses. and the power of AI may mean that they'll be able to answer questions that they haven't even thought of asking yet.

But some of those questions will be best answered using the collective intelligence of data available on the Global Logistics Network. Then give it as the difference between predicting the traffic patterns on a particular road using only vehicles in your own fleet compared to being able to get a better answer for traffic patterns using the vehicles of every participant on the Global Logistics Network, where the difference between responding to a shipment delay by limiting yourself to 1 airline, you've worked with versus every possible alternative with an air carrier available over the Global Logistics Network.

Collective intelligence, available over a massively scaled network matters when you're solving interenterprise solutions and that collective intelligence is another data source that powers AI for our customers. The third area is the GLN fueled AI with real-time information. Further, the most successful businesses will power their AI with current information so that the answers they get aren't stale. For that, our customers really need real-time and constantly updated information from a trusted source dedicated to data, and that's what the Global Logistics network provides. We're processing shipment moves and getting location information in real time. We're quickly updating compliance rules, sanctioned parties, tariff rates, trade agreements and regulations, shipping rates and schedules. We live, eat and breathe supply chain and logistics at scale. And we believe that's even more powerful business in the AI world.

So we believe that just the fact that our customers want to use AI increases demand for the Global Logistics Network, but AI also allows us to make meaningful changes in the services and value we deliver to customers and also in how we make our own operations more efficient and effective. Next area is AI enables new GLN services for our customers. We recently ran an internal employee AI Descartes hackathon with exactly that go in mind. What our employees' ideas for using AI to deliver more value to customers or making our business more efficient. We had overwhelming employee interest and participation with more than 50 new suggestions for projects, and this is in addition to the projects we've already completed or have underway.

Generally, we leverage AI for customers in 2 ways: One, by delivering new automated services that were too expensive or challenging when they were manual, and two, by allowing our customers to leverage the large amounts of data on the GLN to get better or faster answers that can help them manage their business. An example of new automated services include using a agentic AI with our MacroPoint business. MacroPoint helps our broker and shipper customers get location information on in-transit shipments. Oftentimes, we can get this information from direct data feeds to vehicle telematics or trucking company transportation management systems. However, there's still a substantial number of small and/or independent truckers that don't have those technological capabilities.

Having a staff of hundreds of people to call these trucks and ask them where they are, just isn't economically feasible for our customers. However, with agentic AI, we can work with them to download and use our mobile app or automate inquiries to truckers and get more tracking information for our customers much more efficiently. In just a few short months, we've had more than 300,000 outreaches using our AI agents, resulting in more than 180,000 drivers joining the MacroPoint network. The result is happy customers, more billable truck loads for our customers. So it's a great example of an enhanced service that just wasn't feasible before AI automation came to the table.

Some other things that were already gone underway for our customers, natural language searches of our GLN data mine U.S. import information and faster results to get competitive intelligence. Automated logic and denied party screening to deal with challenging match scenarios on parties with ambiguous names and addresses. This allows customers to process large shipment volumes more quickly. Free trade eligibility assessments using AI recommendations based on past practices, helping our customers reduce their tariff bill, automated tariff classification suggestions for goods, using AI agents to interpret lengthy carrier rate agreements and present optimal selection recommendations; and finally, leveraging actual historical delivery service times for particular businesses to allow for better planning decisions.

AI also allows us to run our own network more efficiently. AI allows us to make our own internal operations more efficient by automating tasks, minimizing human error and enabling oversight and analysis that wasn't previously possible. For us, AI can help us with these areas such as enhanced network security as we deploy tools to monitor, target and even counterattack malicious activity, more intense network performance monitoring to minimize service disruptions, code development by providing engineers with a running start with suggested code and development or maintenance of services. This is something we're already seeing great benefit in. And finally, automated and self serve customer service, leveraging the enormous amounts of product documentation that we produce.

So AI has a great opportunity for Descartes and for our Global Logistics Network. We believe it will spur further demand for our trusted real-time clean formatted GLN data and the collective intelligence of the network. It's already allowing us to deliver additional value to our customers with enhanced services. and it's helping make our business more efficient. We believe that the inner enterprise scaled network infrastructure of our business puts us in a much better position to benefit from AI than legacy or emerging point or enterprise technology solutions.

To sum up before I hand it over to Alan, Q3 was a very strong quarter for us. Trade and tariff uncertainty fuel demand for many of our services, we saw AI have a meaningful impact on our service delivery to customers and we completed an acquisition of our -- in our e-commerce pillar that's already contributing an excellent job all around by Artcare team. I'd look to touch on one other item outlined in our press release today, and that is that we're planning on a CFO transition after the end of this fiscal year. Alan has decided that after more than 30 years as a public company CFO, including 12 at Descartes, he wants to take steps towards retirement. So Allan will be handing things over to Ed Gartner in March 2026 and consistent with our established CFO succession plan. Alan is going to stick around in the business as an adviser to help us with the CFO transition and also more generally to keep helping our business grow. It continues to be a great privilege to work with Alan. He cares for the business a ton, which I think is reflected in his desire to stay involved with the business going forward.

We're also thrilled to have Ed Gartner ready to assume the CFO role, someone that I've worked with for more than 20 years, and Alan has worked with over his entire 12-year stint at Descartes and as a ton of financial experience with our business and the many acquisitions that we brought on board and will likely already be a familiar face to many shareholders and analysts. With Allan and Ed's long working relationship together, we expect a seamless transition in March. So those are our plans for the future, but we still have Allan on the San until March.

So now I'll turn the call over to him to go through our Q3 financial results in more detail. Allan?

Thanks very much, Ed. I appreciate those words. So as indicated, I'm going to take you through our financial highlights for our third quarter, which ended on October 31. We are pleased to report record quarterly revenue of $187.7 million this quarter, an increase of 11% from revenue of $168.8 million in Q3 last year. While revenue from acquisitions completed in the past 12 months, including the acquisitions of 3G TMS and Finali inventory completed earlier this year contributed nicely to this growth. Our growth in services revenue from new and existing customers from our existing solutions was also a very significant driver of growth this quarter when compared to the same period last year.

Looking at our revenue details further. Our revenue mix in the quarter continued to be very strong, with services revenue increasing 16% to $173.7 million compared to $149.7 million in the same period last year representing approximately 93% of total revenues in the third quarter this year. Based on these results, we estimate that organic services growth on an FX-neutral basis came in right around 7% in Q3 after averaging closer to 4% in each of Q1 and Q2 this year. While we saw some reasonable strength in our transaction volumes in Q3, the majority of the growth in services revenue this quarter continue to come from strong results in the global trade intelligence pillar as well as strength in our e-commerce customs filing business and our transportation management solutions, including MacroPoint free visibility solution again this quarter.

As expected, partially offsetting the strong growth in services revenue, license revenue came in at $1.7 million or 1% of revenue in the quarter, down from license revenue of $3.5 million recorded last year in Q3. While professional services and other revenue came in at $12.1 million or 6% of revenue, down from $15.6 million in the third quarter last year. That's mainly a result of the inclusion of approximately $3.7 million of low-margin hardware sales from our ground cloud business in our Q3 results in last year's comparable period.

As indicated, these lower license and hardware sales were expected, and we continue to focus on driving growth in services revenue across our business. For the first 9 months of this year, revenue came in at $536 million, an increase of 11% from revenue of $484 million in the same period last year. Again, with revenue from acquisitions completed this year as well as organic growth in our existing solutions, both driving this revenue growth. Again, services revenue drove this growth year-to-date growing approximately 15% over the same 9-month period year-to-date last year.

Gross margin came in at 77% of revenue in the third quarter up from gross margin of 74% in the third quarter last year, again driven by the low-margin hardware sales we recorded in last year's results. Excluding these hardware sales, gross margin would have improved slightly over the same quarter last year as a result of the continued leverage we experienced with revenue growth from new and existing customers. Operating expenses increased by approximately 11% in the third quarter over the same period last year, and this was heavily related to the cost coming from the acquisitions completed in the past 12 months, offset partially by the cost benefit of the restructuring plan that we put in place during Q2 of this year.

So as a result of continued cost control and the operating leverage we get from both acquisitive and organic revenue growth, we recorded adjusted EBITDA growth of 19% to a record $85.5 million or 45.6% of revenue, up from $72.1 million or 42.7% of revenue in the third quarter last year. For the first 3 quarters of the year, adjusted EBITDA has increased by 15% to $241 million from $210 million in the same period last year, with adjusted EBITDA ratios increasing to 44.9% from 43.4%. If we look at our GAAP financials, net income came in at $43.9 million or $0.50 per diluted common share in the third quarter, up nicely from net income of $36.6 million or $0.42 per diluted common share in the third quarter last year.

We should also note that the income tax expense for the third quarter came in at $14.5 million or 24.8% of pretax income which is slightly lower than our blended statutory tax rate of 26.5%, mainly as a result of recognizing some previously unrecorded R&D tax benefits from previous periods. Net income for the 9-month year-to-date period was $118 million or $1.35 per diluted common share compared to $106 million or $1.21 per diluted common share in the last year in the 9 months, again, as a result of higher operating profits from our growing business.

With these operating results and strong AR collection offset partially by higher cash tax payments in the quarter, cash flow generated from operations came in at $73.4 million or 86% of adjusted EBITDA in the third quarter, up from $60.1 million or 83% of adjusted EBITDA in the third quarter last year. For the 9 months year-to-date, our operating cash flow has increased 20% to approximately $190 million or 79% of adjusted EBITDA, up from $159 million of adjusted EBITDA in the same 9-month period last year.

In these 9-month periods, cash flow from operating activities was impacted by the following: first, in the year, impacted costs and compare cash flow impacted the payment of $55 million contingent asset ratio for previous deals, we show these on the acquisitions. [Technical Difficulty] in the first half of the year, we need to incur approximately 1 additional in the fourth quarter of this year.

We see approximately 50% of our cash as in the fourth quarter to complete amortization expense will be approximately $21 million for the fourth quarter, with this figure being subject to adjustment for foreign exchange rates and future acquisitions. Our income tax rate for the first 9 months of the year came in at approximately 24.1% of pretax income which is just below our blended statutory tax rate of 26.5%.

For the fourth quarter, we currently expect our tax rate will come in fairly close to our abundant statutory tax rate. And as a result, we should experience a tax rate in the range of 24% to 28% of pretax income in Q4. However, as always, we should state that our tax rate may fluctuate quarter-by-quarter from onetime tax items that may arise as we operate internationally across multiple countries. And finally, after incurring stock-based compensation expense of $14.8 million in the first 9 months of the year, we currently expect stock compensation to be approximately $6 million in the fourth quarter subject to any forfeitures of stock options or share units.

So that's it for the financial update. As Ed mentioned, we have a well-planned CFO transition in the works, and I'm excited to be able to work with Ed Gartner on the [Audio Gap].

Thanks, Allan. These continue to be challenging business conditions for our customers. From a tariff and trade perspective, I outlined earlier, some of the things that have happened over the past 90 days. Looking forward, the U.S. Supreme Court is considering the lengthy -- sorry, the legality of many tariffs with no identified time line for resolution. Customers are also adjusting to new commodity-specific tariffs -- and given the speed with which they were implemented, remain uncertain about additional tariff changes they may see in Q4.

And the remains ongoing geopolitical tensions impacting trade, whether it's tensions in the Middle East, impacting trade lanes, the ongoing war in Ukraine impacting it and its resulting trade sanctions or the potential [Audio Gap] how consumers will behave in this economic environment and the early returns seem positive. This binary action will have a big impact on general economic activity and shipping related to inventory replenishment in 2026.

For Descartes, we've grown during challenging business conditions in the past. Our plan is to continue to do so now. Some of the things that we believe continue to put us in a good position to do that include we're particularly strong in global trade intelligence. We believe we can provide a ton of help to our customers in an environment where people are looking for information or help managing tariffs, continually updating sanction party list first for competitive intelligence dealing with increased export licensing complexity and implementing new duty deferred foreign trade zones.

We're diversified globally. We've got domestic transportation solutions that can be used around the world and where there's shifting international trade relations, we have an established global logistics network that can be leveraged by our customers. Our network model and processing of large amounts of clean formatted real-time data put us in a great position to capitalize on AI opportunities. We have a total growth model. We have an extensive track record of acquisition activities to complement organic growth. Changing market conditions often provide us with even more opportunities to add solutions for our customers and grow by acquisition.

Finally, we're a well-capitalized cash-generating business. At Q3 quarter end, we had $279 million in cash and $350 million in -- excuse me, undrawn line of credit. In our quarterly report, we provided a comprehensive description of baseline revenues, baseline calibration and their limitations. As of November 1, 2025, using foreign exchange rates of $0.71 to Canadian dollar, $1.15 to the euro and 132 to the -- great Britain pound and including the estimated contribution from the acquisition of Finale inventory, we estimate that our baseline revenues for the fourth quarter of fiscal 2026 were approximately $161 million and our baseline operating expenses were approximately $98.5 million.

We consider this to be our baseline adjusted EBITDA calibration of approximately $62.5 million for the fourth quarter of fiscal 2026 or approximately 39% of our baseline revenues as at November 1, 2025. We're currently operating above our expected adjusted EBITDA operating margin range of 40% to 45%. Our margin can vary in any period given such things as revenue mix, foreign exchange movements and the impact of acquisitions as we integrate them into our business. For now, we're keeping our target range to 45%. However, we'll monitor how we're performing over the coming quarters to consider whether any upward adjustment is appropriate.

We've noticed that there's been uncertainty in public market conditions that have contributed to lower than historical valuation multiples for many logistics and supply chain technology companies including Descartes. Considering how Descartes is currently performing, we remain optimistic about our ability to achieve our long-term financial plans. However, it's uncertain how public markets will trade for the foreseeable future given everything going on in the world. With that uncertainty, we believe it's prudent and in Descartes' interest to apply to start a normal course issuer bid to have the option to purchase Descartes shares in the open market over the next 12 months if and when we think it makes sense.

Having the normal course issuer bid mechanism available to us will allow us to react quickly and appropriately to differing public market conditions. These remain uncertain times for our customers. It's a challenge for them to know what they can rely on in this global trade environment. Our goal is to continue to show our customers and other stakeholders that the one thing they can rely on is De carte. Thank you to everyone for joining us on the call today. As always, we're available to talk to you about our business in whatever manner is most convenient for you.

And with that, operator, I'll now turn it over to you for the Q&A portion of the call.

[Operator Instructions] Your first question is from Chris Quintero from Morgan Stanley.

Allan, congrats on a fantastic run here and best of luck in your next part here of your life journey. I wanted to double-click on the organic growth rate, specifically around the transaction volumes. Allan, I think you said reasonable strength. So what did you exactly see there? Was there an improvement in the volumes? Or was it kind of largely a stabilization? How would you describe the volume component here?

Well, a lot of volume picked up -- Yes, let volume picked up was from our competitors. If you look at the trade steps, ocean and truck were fairly flat, but we were able to grow in those areas because we had solutions that were more attractive to customers than some of the one-hit wonder competitors that we've had in the past. And that enables us to pick up in areas like the Type 86 filing that we pick up quite a bit of business in the BIS-50 area where new government regulation came in and we were able to take our position in the market and go in and get a lot of new customers with bigger contracts that committed to us for a long period of time if we haven't passed customs filing initiatives.

Things like that added up to -- even in the face of transportation statistics that we probably would like them to be better. But we were able to grow substantially. I guess our position in the market and a bunch of things that I mentioned on the call are already helping. I don't think I said it in the prepared comments, but MacroPoint was at 87%, which is the highest truck rate in the industry by 20 points. And -- but still, the customers want to track all their shipments. And we're not using AI to get that number up, it's now 90%. And just in a couple of months, that shift occurred. And that's not only more money for us. It's happier customers, and they're paying us more money, but they want to track all their shipments and that put us in a situation where our customers are happy. We're making more money and we're beating our competitors handily because they haven't moved to market with these kind of solutions as fast as we have.

Got it. Okay. So stable-ish kind of industry volume trends, but you all just really took some market share here in the quarter. I would love to follow up on the AI commentary you gave at totally makes sense from the macro point perspective, improving that tracking percentage rates. How do you think about the monetization angle of it? Are you higher prices? Is there a separate SKU to get some of this agentic capability? How are you thinking about that more broadly?

Probably a bunch of different ways, but some of the more pertinent ones, and we said we had that challenge with the employees that identified new things. It's doing more for our customers with the data that we already have. So I'll give you an example, take a shipment delay and we know when it's supposed to be there and we see something happen with a plane or a truck or a ship that says, "Hey, there's going to be a problem with this shipment." We could identify that that's going to be a problem; we can figure out what to do about it and executing for them. I can imagine a world in a couple of years where I'm charging a customer to do all of that, but that work used to take them hours and hours internally, and they wouldn't even come up with a very good solution for it.

I could see a world in a couple of years where we may be telling the customer, hey, that shipment you have it's going to be 8 hours late, and they go, "Oh, why that's why is it going to be late and we go because it was going to be late 5 days, and we figured out the problem and we booked you going somewhere else. And as a result, you're only going to be delayed a few hours. And to our customers, that's great news. It could cost them hundreds of dollars to deal with that and have an angry customer. And in the world I just described, we identified the problem faster than they ever would have done it themselves, came up with the best solution we could possibly come up with under the circumstances and rebooked them what they'll pay for and got them in a situation where they got bad news and it didn't work out that badly because we used AI tools and the data on our network to come up with a better solution for their customer.

Your next question is from Dylan Becker from William Blair. .

Allan, thanks for the question here. And Allan, congrats on the retirement of the best and a pleasure working together. Maybe sticking on the theme of AI with you, Ed, to start. I appreciate all the color on kind of the opportunity for value and monetization to come, but maybe if we think about the implications to kind of a moat and platform defensibility of the network here, maybe there's perception or at least the bottom threat in competition entering the space. It feels like the scaled network that you guys have is a massive differentiator. But wondering maybe how you think about the network as a leg up not only on compounding value but also maybe the complexity of trying to replicate this or something like this from scratch.

I mean I've been in the network business, it's my entire life. And I'd just give you 2 examples. You can't really compete with us as a network until you have all the connections. No one's going to switch from my network to yours if you only have half of the connections that I have. They needed people that come in and solve the entire problem. And that makes it very hard for someone new to come in and compete from scratch. Same with the data content business, you have to have all the data. You can't just get some of it and then start competing with us. It's not attractive to customers. And what that means is you have to spend a whole lot of time and effort upfront to to recreate those businesses, if you even could and you can get any customers to do it. It's like by the time you start being able to monetize it, you could be 5, 10 years in. And I can tell you, just on the network side, the data all changes and the connections all change over that period of time. But we're -- we had the advantage of starting from the beginning when all of this started, and building all of this stuff. And there hasn't been a new network entrant in 20 years and data content the same thing, right, as people got to collecting the data content. But how do you get all of it because that's what you need to start.

And the reason our data content businesses are so profitable is we don't charge any individual customer too much money. We have collected all the data over time, and now we just have to update it. And that has a certain cost to it. But once you get over that cost, it is a very profitable business because all the new customers are pure profit. If you wanted to try and start that from scratch, you're losing money for years and years and years to get to the point where you have your head above water. And it just made it unattractive for people to try and get back into it. So I look and go, hey, with all the stuff that we do for these people and the amounts that we charge them, it's not that attractive to get into it. You're going to lose a lot of money for a long period of time until you get into it and it's probably just not worth it to people. and that's why we haven't seen anyone try to do it.

Great. That makes perfect sense. And then maybe switching over to Allan or Ed, if you have thoughts on this as well, too. But on the services, the organic services step up how should we think about kind of the sustainability of subscription demand given we continue to highlight multiple moving parts and factors driving sustained complexity here. And then if you do think and you segment it out on kind of the volume recovery side, more of a market share story at this point, how we should think about kind of the volume normalization continuing to play out over time as maybe we get a sense of normalcy at some point here in the future.

Well, I mean I'll take it, if Allan has anything else to add, he can jump in. I think our customers, they they don't know exactly what's going to happen, and there's a lot of uncertainty out there. I called out a lot of it on the call. I think when that uncertainty goes away, you're going to have -- you're going to see increases in volumes and assuming the economy is in good shape when that happens. And frankly, we don't know the answer to that question. What we do know is that we've got to run our business to keep making 10% to 15% and really trying to beat 15% growth in EBITDA no matter what happens.

It's why you saw us make the moves we did earlier in the year to cut costs. that we wanted to cut costs that we thought, hey, we make 1 promise to our shareholders, and that's what we're going to make 15% or attempt to be even better than that every year more than we did the last. And we are laser-focused on that. And there's some things we can't control in the business. The things we can, we want to try and control on the revenue side. And certainly, on the cost side, though, we have a lot of control. And it's not that we like making the moves that we did. No one likes firing people cutting costs somewhat substantially.

But we thought that's what we have to do to run our business properly and to keep people wanting to invest in our business so that we have the money to go out and buy more companies when other companies get themselves in a whole lot more trouble than we do because they're not willing to make those tough decisions. And we are. And I think that's what separates us from a lot of the other smaller players in this industry that it's easy to be a high flyer. So like what happens when 1 of the engine blows, you got to kind of keep running the business until you can get more power.

The next question is from Paul Treiber from RBC Capital Markets.

congrats Allan on the retirement. Just first question, the U.S. Department of Transportation announced a number of changes to U.S. trucking regulations. How do you see those impacting your domestic trucking business positively or negatively?

I don't know that they're going to have a big impact on us. Most governments come in and put rules in place and we help customers comply with those rules. I'm not sure if that's going to happen with these particular rules. But when you have to track your trucks more accurately when you have to make sure your drivers are legal, and you have to make sure your drivers are not driving overtime or things like that, you need software solutions to track if you have a big fleet and guys like us come in and help people do with that. And oftentimes help act more efficiently in the process. So buy our software comply with some government regulations, but will also help you run your fleet more efficiently so we can save you money at the same time so that you have the money to kind of pay for this new rule the government put in.

So I see a comment there's going to be -- they'll always become. They're always going to have more rules for truckers and we just want to be there and prepared to help them with the ones that we think we can solve for them and have software that we give them that saves them money in 5 other places, too, so that they can continue to afford to pay for some of these things and operate more efficiently, even though the government just told them they had to do something.

And then just a second question, just on capital allocation. You did mention valuations are down. You're putting in place NCIB. It sounds like you see opportunistic opportunities. How do you look at the balance between repurchasing shares and capital deployment on acquisitions, like is there a priority for 1 versus the other? Does it depend on relative valuations of each?

Well, we see a lot of stuff for sale right now. And we think the winner in this space is going to continue to bring businesses in and make them part of their own business. We think with our network, we're in a very good position to do that. There's lots of businesses that would be better if they operate on top of our network. And I see AI drive it a whole lot more business in that way as well. Almost every AI tool I've seen in the logistics and supply chain space looks like a feature to me. I'm sure there was some guy years ago working at word perfect and thinking, well, I've got the best word processor in the market. I've got the legal market all tied up and all of a sudden microclot comes in and goes, and I have Excel, and I have PowerPoint, and I have your e-mail and all the stuff and you go, they can't compete anymore. And I think we're in that kind of situation with the network that we have.

A lot of these businesses are in desperate search of customers, and they will one day be a feature, just like a word or were perfect is a feature as part of the Microsoft suite of tools. I could see these things getting layered onto our network and being a lot more valuable as a result. So I think you're always going to see us gravitate in that direction. At the same time, we recognized that probably because of AI and maybe a couple of other things that are going on in the market, not much to do with us and other than maybe a misunderstanding a little bit of our business, if there's someone out there saying, "Hey, Descartes is an enterprise software company," I'm going like not really, we're a network, and we're different than those other guys. And if you're thinking you're going to take all the enterprise software guys down a little bit because AI might harm them. You shouldn't be footing us in that same category because we have a lot of things that are probably going to take advantage of AI. And we still have to deliver, we still have to make those things happen as you always do. But I like our chances. I like the cards that we have in our hands right now a lot better than I do many other people. And I think that's going to continue to result in more and more acquisitions for us. And as long as we see that, we're going to be trying to buy businesses up.

That having been said, when our multiple drops to a level that that we think is way lower than it should be. And we have some cash on hand, we might see us picking up some stock. Right now, it's out there as a placeholder to make it quicker to do if we wanted to do it. And otherwise, we're going to keep going about our business. And if we believe the market values us properly at some later point, we might not be as focused on it. But right now, we go, hey, it's gotten beat up a lot and maybe you can our mind on fairly.

Your next question is from Kevin Krishnaratne from Scotiabank.

I've just got 1 in Allan also congrats and thanks. It was a better player you're working with you hope to continue to do so going forward in new roles. -- e-commerce, you talked about that being a beneficiary to your organic growth. I know you touched on sort of the transactional piece with the filings and seeing a benefit there. Can you maybe talk about what you're seeing -- you've been beefing up that business to now inventory Seller Cloud. You mentioned the holiday season, things are looking -- get to start off. So any kind of color there, maybe the size of this business, the growth and sort of what you're seeing there with the growing piece of this -- of your e-commerce business?

I think it's like 12% now. Allan, correct me if I'm wrong, but it continues to grow, and we continue to pick up good assets there that we think provide solutions to the customers that will benefit them in our network in the long run. Finale is a great add-on to Seller Cloud. Finale, if they had a customer that got you big at some point, they used to kind of -- that customer would graduate from there and leave and go to somebody else. Now all of a sudden, we have the ability to have them graduate and go to our next solution of Seller Cloud. So that's attractive for us and maybe shows you how a lot of acquisitions go on the Global Logistics Network. A lot of times, 20 years ago, we were buying stuff and thinking, I hope it grows, but I'm not going to count on that. I'm going to count on being able to cut costs and manage the business more efficiently than the people we bought it from.

Now with 26,000 customers and growing we start to look at these things and go, we can't help but grow these businesses. There's just too many people on our network that would like them. And the example I always use when I'm out talking to shareholders is I buy some company with 500 freight forwarders and they love it. And I look and go, "Wow, we have 5,000 freight forwarders. So if I buy this company, the first thing I'm going to do is walk it around to the other 4,500 and say, "Hey, what do you think of this?" Now they're not all going to buy it initially, but they're all going to take a look if we ask them too. I mean, we've got big relationships with all these people. And when we walk around a new solution to everyone that's -- they have to look at it. And a lot of times, the smaller companies that we're buying, they didn't feel like they have to look at it previously. They looked and went I don't have to meet them at whatever all of a sudden Descartes buys the company and they kind of have to take a look at it. And sometimes, they take a look at it and buy it. And that's good news for us.

That e-commerce space has been going great. We keep picking up more assets there and those assets, we've been able to grow them all. So that's exciting for us. And I think it's going to continue to be a good space for us that you'll see us continue to expand in over the years.

Your next question is from Stephanie Price from CIBC.

It's Sam Schmidt on for Stephanie Price. I had a question around the year-to-date adjusted EBITDA growth that's tracking towards the higher end of that 10% to 15% target growth range. How should we think about growth there going forward?

I think you're going to continue to hear us say, 10% to 15%. We've beaten 15 many times over the last 20 years unapologetically I think we were up almost 30% in 1 quarter, if I remember correctly, 7 or 8 years ago. As our network gets more and more profitable as our revenue picks up at a higher growth rate, when Scott and I started running the business directly 15 years ago, we were growing like 1%, 2%, 3%. And all of a sudden, now we're growing at 4%, 5%, 6%, 7%, 8%, 9%, 10%, depending on what's going on and I go, it's a heck of a lot easier to get to 15% EBITDA growth with 7% organic services growth, because I can leverage that and get that up, get the EBITDA up to 10% or 11% or 12%.

And then I add on a couple of acquisitions and all of a sudden, I'm well over 15%. I don't think you're going to hear us say a different number. We think that's a number that we'll always be in a good position to hit. And we think that if we can keep growing that EBITDA every year, our stock price has to kind of follow along. I was explaining that to one of my kids the other day that we use an investment bank or now it's a private equity guy and I was going, look, I don't know what's going to happen the stock price over time. Companies like ours are valued at different multiples, and we now have a ton of control of that. month-to-month, but we do make more money every year, and that has to end up showing up in the stock price. And we're pretty confident we can continue to do that. And if we do, it's tough for the stock to not keep going up.

Your next question is from Jean Share from TD Cowen.

Alan, congratulations on retirement. Good luck with the next chapter. I just want to ask your customer mentality at this point. I understand they're still waiting for some more clarity. But do you think a certain point, they're going to develop some kind of fatigue. And as a result, they're more willing to spend regardless of the environment?

Yes, we'll see. I hope that's the case. I think as they get more certainty, they will be willing to spend. And we're seeing in the 60% of our business that's subscription sales. We really haven't seen any slowdown. It popped up significantly in the pandemic, and it's never really stopped. The transaction volumes are ebb and flow. They zoomed up in the middle of the pandemic and zoom back down again. And Gap is kind of a steady pace and then they've been up and down for the last 2 years. But I'd call it like lackluster transaction performance. But our subscription sales have continued. I think most of the world realize that logistics and supply chain was a lot more important than they thought it was in the middle of that pandemic because the customers were telling them that. And the first place you put your money is into technology because that's where you get the biggest bang for your buck and that's where the customer notices the most.

And so I think that's been great for us. It continues to today. And we hope when transaction lines pick up, that we're going to benefit from that. I'm pretty sure we will. And in the meantime, we're running our business as best as we can to try and keep it in 15% EBITDA growth every year and keeping a great solution for our customers so that so that they always want to use this, and they want to sign more contracts with us. And we spend a lot of time doing that, and I think it's going to pay off.

Got it. I also wanted to go back to the restructuring you did earlier in the year. Can I assume this quarter's OpEx and EBITDA include a full run rate of your cost savings?

Yes, that's correct, John. Absolutely. The full impact, we had partial impact in Q2 and now the full impact is in Q3.

Your next question is from Raanan from Gostin.

Alan, congrats on an excellent tenor as on our CFO. Thanks for squeezing me in. I'll keep it to the singular question. In terms of the strong organic delivery in the quarter, you mentioned you're taking share on market volumes. But how should we think about the contribution from other growth drivers like cross-selling, pricing and new logos? Was there an acceleration of any of those drivers quarter-on-quarter?

Yes. I mean, I mentioned earlier, we're being very successful taking stuff away from our competitors. Cross-selling inches up every year. 15 years ago, it was minimal 20% or something. Now you look at it in 60 to 70 -- 65% to 70% and we continue to get better than that. Probably about 5 questions ago, I explained why as we get a bigger and broader solution set, it's tough for the customers to not consider it and take it seriously. And then the thing I mentioned at the end of the last question is important, right? We spend a lot of time making sure that our customers get what they were promised. I mean I would joke people, but it's true, we will lose money to make sure that you've got what you want. And you know how serious we are about making money, but it's really important to us that our customers get what they were promised. There's only 1 FedEx in the world. And I could say it about any of our big customers.

But I don't want them hating us. I want them to think Descartes would do anything I needed to do to make sure that I was successful in doing it. And you could look and say, "Hey, that's because you charge recurring revenue fees right? You want to get your money. And there's some truth to that. But maybe more broadly, we want them to think we're a good company to do business with. They were fair and that we try our hardest and then we try to make sure that the customer gets what they want. You've heard us say customers for life a lot of times on these calls. That's what we're talking about because I want them -- when they have their 32nd contract with us, I want them to be quite happy to sign the 33rd, 34th and 35th contract with us. It's really important to us. And from 20 years ago where maybe the company wasn't so focused on that kind of stuff and now it is. And I think we know that's the right way to behave. If I'm buying something from someone, if they stick with me, and make sure that they're trying their hardest to make sure they get what they want, I'll deal with some problems some of these things are complicated. I'll deal with problems as long as I know that they're going to keep trying to make sure that I'm successful. And we've gone a great length to do that. And I think that's a big part of the reason you see our cross-selling continue to tick up every year because the customers know we care about them.

Yes, I would just add on that price remains similar to other quarters. Price is a very small part of that growth in Q3 similar to past quarters as well. So no big change there. We're using price increases responsibly to offset inflationary cost for us, but it's not the main driver of our growth.

Of course. Congrats on the strong results.

Your next question is from Mark Chapel from Loop Capital.

This is Tim Grieve on for Mark. I guess my 1 will be on the TMS replacement cycle. Are you seeing evidence of that accelerating? And where is Descartes win in versus the legacy TMS competitors.

I don't know that I see it accelerating, but it's a decent market for us right now, and we continue to pick up more transportation management solutions. We have 6 or 7 of them right now, depending on what kind of customer you are Ford or broker free, big retailer manufacturer these types of things. And we have a lot of good solutions to solve those problems. We continue to look at other TMSs when they come up or AI features that we think would be a good part of TMS and I think we're going to continue to remain in a leadership position there, especially with some of the companies that -- the midsize companies that they used to do it, get bought up in the as their focus and they lose their people, and we just keep sticking in there and buying more companies that can solve more types of problems for customers. And over time, I think that has helped us to win the day.

We have a lot of different solutions and sell a lot of different problems, and people look at us and go, those guys are going to be around. They're not going to get bought up by a private equity firm and everything is going to go to [indiscernible] there a public company that's neutral in the industry, [Audio Gap].

Think we just lost Ed's voice there, but he's just emphasizing that that we're well diversified and with the size and scale to manage properly. Sorry, we're just on the whole audio problems for Ed, but hopefully, that answers it for you. .

[Operator Instructions] Your next question is from Scott Group from Wolfe Research.

This is Carl on for Scott.

[indiscernible] Got thrown off the call, but I'm back now.

This is call on for Scott. We recently saw a competitor announce a change in their pricing philosophy to get away from per user fees. Maybe what percent of your revenue is based on per user pricing versus volume-based or fixed pricing? And how do you think about this evolving in a world where some of the brokers and borders are talking about structurally reducing headcount?

Yes, I've heard this argument a bunch of times. There's a bunch of different ways we price. It's not just per user, have all types of transaction processing charges even in some of our subscription services, per truck per mobile handheld device. And yes, sometimes per user, I don't think that's going to be a big challenge for us. If they start to have less people using the system because they become more efficient, we're going to come up with a different way to extract value. I know the guy you're talking about, and I think they probably shot too high and there's a lot of problems with customers right now because of that. And I think if you see us start to do that, it's going to be a more reasonable approach too.

Okay. Helpful. And we're seeing some of the orders seeing pretty big increases in customs revenue as a result of de minimis going away. Are you guys also seeing that benefit? And how does a big increase in customs filings and customs complexity impact you guys going forward?

I mean you hear us say all the time on things called the complexity helps us, and I think that's correct. Look at the situation we're talking about here at the Type 86 we've almost doubled our revenue in that space in just a couple of months. And honestly, 1.5 years ago, we were very concerned they were going to cancel de minimus and all of that business could go away. And what ended up happening was our sales team came up with the approach of we'll just keep charging you for all the shipments that you make per shipment and the same way we were doing it before. And instead of making a type 86 filing, which is going away, we'll make a type 1 filing. And so we were able to switch our customers over to that solution. And we were thinking we were doing pretty well. And then our competitors started really struggling to handle type 1 filing with the massive amount of volume that some of the bigger players were producing millions and millions of transactions a day and our network has the ability to deal with that because we've been doing in customs filings for FedEx and DHL and UPS and a lot of other big players for years and had already dealt with millions of transactions a day.

So we had -- as a network operator versus a software company, which I think a lot of the other guys were just software companies, we had a network that was robust and able to process the transactions quickly. And we saw almost all and then switch over to us, and it really ends up being a gigantic benefit for us in the last several months. So happy about that.

There are no further questions at this time. Please proceed with the closing remarks.

Thanks, everyone. We look forward to reporting back to you on Q4 in March. And otherwise, if you're looking for one-on-one discussions with us, please reach out to us, and we'll find a way to talk to you. Have a great day, guys. .

Ladies and gentlemen, the conference has now ended. Thank you all for joining. You may now disconnect your lines.