How EPG Is Using AI for Warehouse Document Processing

1 - > SPEAKER_00: AI has been overhyped when it's positioned 2 - > as a replacement of systems. 3 - > That's not what we're doing. 4 - > We're not ripping out your WMS or your execution stack and 5 - > replacing it as AI. 6 - > So once you start thinking about that, then you're going to be 7 - > like, okay, well, this is going to replace everything.

8 - > No, it's not. 9 - > What it's doing is it's helping you rather make intelligent 10 - > decisions and leveraging the visibility that you might have 11 - > actually achieved through deploying these systems and then 12 - > making you giving you that competitive edge to be able to 13 - > be ahead of your competition and also not only understand the 14 - > visibility of the supply chain, but also execute and be future. 15 - > SPEAKER_02: Welcome into another edition of the CargoRec series 16 - > where we are talking about AI use cases in logistics.

17 - > And today we're talking with Jet Chitanin. 18 - > He is the president at APG America's, and we are going to 19 - > be talking about their tools around the new era of AI with 20 - > their Aura program and where intelligent document processing 21 - > is part of more of a broader level of products that they are 22 - > solving with AI. 23 - > And so, Jet, welcome into the show. 24 - > SPEAKER_00: Thanks for having me, Bright.

25 - > Looking forward to this conversation. 26 - > SPEAKER_02: Now give us sort of a high-level view of we 27 - > mentioned that the broad spectrum of products that EPG is 28 - > targeting. 29 - > So give us that high-level view of who EPG is, your ICPs, your 30 - > target customers. 31 - > Who are you talking to and why?

32 - > SPEAKER_00: So EPG is a at our core, we are a supply chain 33 - > execution platform. 34 - > So everything from warehouse management software, 35 - > transportation management software, contract and billing, 36 - > which is very important in the 3PL world, yard management as 37 - > well. 38 - > And so this year, earlier this year, we launched our AI 39 - > environment, which sits on top of our execution layer, on top 40 - > of our platform, or any platform for that matter.

41 - > And what it does is it's focused on solving challenges inside the 42 - > floor walls of distribution centers and warehouses and 43 - > leveraging AI to be able to make really smart decisions using 44 - > AgenTic AI specifically. 45 - > And that's gotten us a lot of success, especially having also 46 - > won uh the best product award at Logimat, which is a large 47 - > European um show that can be compared with Modex or ProMat. 48 - > SPEAKER_02: And so as you are developing these new products in 49 - > sort of this new tech renaissance that we kind of find 50 - > ourselves in working in in logistics and supply chain, how 51 - > are you choosing to develop the different products and how did 52 - > they sort of come to fruition?

53 - > Was this something your customers were asking for, or 54 - > were you seeing it in kind of the data that you wanted to 55 - > optimize for them? 56 - > How are you approaching your customers with these different 57 - > product sets? 58 - > SPEAKER_00: So it's all about problem solving, right? 59 - > That's a great question.

60 - > It's all about problem solve solving. 61 - > Uh, you know, we observe there are certain areas in the 62 - > warehouse and even beyond, you know, because some of our 63 - > applications go beyond uh what happens in four walls. 64 - > But uh it's all about you know making sure that we understand 65 - > what the challenges are and can we leverage AI using this? 66 - > Rather, can we leverage AI to solve these problems?

67 - > And that's how some of these came into fruition. 68 - > I'm happy to go into more details regarding use cases, but 69 - > we saw, just to kind of give you an overview, we saw uh 70 - > challenges while receiving product. 71 - > And that is one area where consistently we got feedback 72 - > about how cumbersome is the process to unload everything, to 73 - > get the delivery notes, to get all that information for you to 74 - > then be able to really start doing your work.

75 - > And then so on and so on, we uh gradually started to uncover 76 - > more and more challenges that we could solve using AI. 77 - > So we transform actually our company uh internally as well as 78 - > uh you know developing this application and leveraging AI 79 - > because you know, if you don't adapt, then you're left behind. 80 - > So that's the approach that we're taking. 81 - > SPEAKER_02: So let's let's talk about some of those different 82 - > use cases because we got a couple of your your case studies 83 - > that were sent over, and but we're the the IDP product.

84 - > So tell us a little bit about that product, and because I have 85 - > some some data that shows that 13 minutes are saved per 86 - > delivery across the goods reception process and at a 10 87 - > dock facility running 70 trucks a day that adds up to 15 hours 88 - > is saved daily. 89 - > Walk me through where those 13 minutes actually come from. 90 - > SPEAKER_00: Sure, absolutely. 91 - > So to sort of center this uh this conversation, IDP, which is 92 - > our intelligent document processing, sits inside a 93 - > broader uh array of use cases, which is called as uh the EPG 94 - > Aura Observer.

95 - > So observer, it's like an eye. 96 - > So you you you can an I can read a document, and I can look at a 97 - > video, and I can look at a podcast, right? 98 - > And also hear it, of course. 99 - > So so that's the idea behind it.

100 - > We've also, you know, um partnered with Nvidia on on some 101 - > of the camera technology that we're using in in other use 102 - > cases. 103 - > I should say the intelligent video analysis, which is part of 104 - > our uh observer. 105 - > Here, the challenge was a lot of organizations were using OCR to 106 - > detect documents, to read those documents. 107 - > However, you know, when things are inside the warehouse, 108 - > they're not always perfect.

109 - > Uh as you know, you get all these delivery notes, they're 110 - > crumbled up, there's stuff written on it, so on and so 111 - > forth. 112 - > So it becomes extremely hard for people to parse out that 113 - > information, understand what that is, and put that into um, 114 - > you know, uh enter that information somehow to capture 115 - > it and enter it into your WMS. 116 - > So what we did is um, you know, uh using AI uh technology, we 117 - > were now we're able to understand and recognize 118 - > patterns.

119 - > So it's it's very simple. 120 - > What you do is with a camera, you take a picture, the AI uses 121 - > and it contextualizes the picture that you've taken, 122 - > understands what if there's information missing, if there's 123 - > information that's blurry, so on and so forth. 124 - > Uh, and and really recognizes those patterns and builds up 125 - > that information so that you get everything as it should be, and 126 - > then you then uh take that information and upload it 127 - > directly to your WMS.

128 - > So all that process uh happens pretty instantaneously. 129 - > Where you see people uh save uh save on time is you you 130 - > mentioned the goods receipt process. 131 - > So that can be broken down into five, let's call it major 132 - > categories check-in and unloading. 133 - > So this is when your trailers come in, you're checking in, 134 - > you're unloading the trailer, so on and so forth.

135 - > Then you perform your initial inspection and identification of 136 - > what product it is. 137 - > You've got your goods receipt recording, that's when you 138 - > record all the information that you've received. 139 - > Then, of course, you have quality control, and then you 140 - > put away. 141 - > So, in all of these steps, the major three steps or sub steps, 142 - > I should say, where we can save time on are initial inspection 143 - > and identification, just with that camera capturing all that 144 - > information instantaneously.

145 - > Similarly, with goods receipt recording as well, and then uh 146 - > handling of uh you know different uh loading units and 147 - > so on and so forth, and then quality control. 148 - > So we we did extensive time studies also uh at a customer 149 - > site as well, and then we that's how we came up with that 150 - > 13-minute number. 151 - > So then you can extrapolate that, and as you mentioned, 152 - > that's absolutely right, it can potentially save up to um you 153 - > know almost two shifts worth of work.

154 - > SPEAKER_02: Now, in a traditional shipment process, 155 - > there could be all different kinds of modes that are used to 156 - > complete the journey of getting that source, you know, to porch 157 - > process completed. 158 - > And as most of us know in this industry, there are you know all 159 - > of these different information silos, there's acronyms, there's 160 - > you know, language barriers. 161 - > How do you sort of account for all of those different 162 - > information silos and make sure that once that document is 163 - > processed, that everybody can kind of understand it from the 164 - > same lens?

165 - > SPEAKER_00: Excellent question. 166 - > So I'm gonna go one step back and talk about how our AI 167 - > platform or AI environment is developed. 168 - > So at the core is something that we call as cognitive core. 169 - > That is sort of the brain, uh and rather the heart of the AI 170 - > system.

171 - > There we have our own technology as we're using multitudes of 172 - > LLMs to be able to um analyze all the information and use and 173 - > leverage AI. 174 - > And then we have something called a semantic brain. 175 - > And what that does is it contextualizes information. 176 - > So semantic brain is where you can upload all of your 177 - > documents, your workflows, and so on and so forth.

178 - > So let's say you were customer XYZ, and um you have some very 179 - > specific processes in your warehouse, whether it's related 180 - > to shipping, whether it's related to just whatever you're 181 - > doing inside your facility, and you can actually upload all 182 - > those into the AI environment. 183 - > The AI environment uses our LLMs as well as that information to 184 - > contextualize what it's seeing and looking in real time on that 185 - > specific document.

186 - > And that way it's able to understand and recognize this 187 - > acronym in this context means this activity. 188 - > SPEAKER_02: And so as your well, with that, I it almost sounds 189 - > like maybe like the that's a key part of the onboarding process 190 - > when you bring a new client on that that's going to be 191 - > utilizing your services. 192 - > Because if you're doing, you know, uh if you have a WMS and a 193 - > TMS, and then you have the these different document imaging 194 - > processes, then I would imagine that that could create a 195 - > situation where maybe you're surfacing things that things 196 - > that are a problem or inefficiencies that were a 197 - > problem that the customer didn't know about.

198 - > So, how are how do you approach maybe um the pre-onboarding or 199 - > the pre-boarding and then the onboarding uh during those 200 - > customer conversations? 201 - > What do those conversations look like? 202 - > SPEAKER_00: So it's always uh because applications can be so 203 - > broad, and this is just one application, you know, the 204 - > onboarding process can be, depending on what the scope is 205 - > going to be for the entire project, it can go on, right? 206 - > So it it's it can be an iterative process.

207 - > Uh what we've tried to do is make you leveraging AI, and this 208 - > is what I want you know, sort of the audience to also get away is 209 - > uh get from this, rather, is you don't have to have your 210 - > instructions in a specific format. 211 - > You don't have to have, you can just say, just like give you an 212 - > example, right? 213 - > I mean, if you go on um and and any sort of then an AI platform, 214 - > and then you say, I need a ticket, flight ticket to 215 - > whatever it is.

216 - > I live in Raleigh. 217 - > So Raleigh, uh, and then uh just find me a flight ticket for May 218 - > 1st, and these are your parameters, do it. 219 - > So you you don't tell them what to do inside, it's gonna then 220 - > figure it out uh based on the models, right? 221 - > We're using a similar approach here where you have the 222 - > beginning state, end state, that's how you solve problems.

223 - > However, to your point, that can and will uncover some 224 - > inefficiencies in this process. 225 - > Where again, if you if you relate it to a um to a 226 - > traditional AI that you're using every day, it's gonna say, okay, 227 - > fine, I finished this action. 228 - > But now do you want I've seen I noticed that there's something 229 - > additional. 230 - > Do you also want me to look at that and and and give you a 231 - > recommendation?

232 - > So that's sort of the way that it's gonna work. 233 - > SPEAKER_02: And so it's more of the exception management for uh 234 - > a lot of these different roles where they don't know what they 235 - > don't know, especially during the onboarding process, but 236 - > there could be some opportunities where you know 237 - > that 13 minutes that we cited earlier could lead into more 238 - > efficiency saved across an entire, you know, sort of 239 - > shipment flow. 240 - > Am I understanding that correct correctly?

241 - > SPEAKER_00: Yes, that's right. 242 - > And and again, just sort of reiterate that's one use case. 243 - > We have others as well, but that's the the one where we can 244 - > absolutely pinpoint and say this is what we've observed in real 245 - > time. 246 - > We've done time studies and saved um on cumulative time 247 - > saved throughout a shift.

248 - > SPEAKER_02: And so uh one of those other use cases that that 249 - > were brought up is it is IVA on the operational impact. 250 - > And so the Aura observer, which is one of your products, and 251 - > then the video partnership uh got a lot of attention, as you 252 - > mentioned, at Logimat. 253 - > Without some of those hard numbers, how does IVA, first of 254 - > all, what does I guess sort of IVAs stand for? 255 - > And then what is the big problem that it's solving?

256 - > SPEAKER_00: Okay, so IVA stands for intelligent video analytics. 257 - > So it's as simple as you know having our uh AI system be 258 - > deployed and and you have any cameras you can have. 259 - > Like we don't necessarily recommend certain type of 260 - > camera, but it's basically tied into the camera system. 261 - > Any camera system that you have.

262 - > This acts like a supply chain manager for the most part, or 263 - > help that a supply chain manager can can really use. 264 - > Imagine a warehouse and uh using cameras, it's constantly 265 - > detecting or and understanding and contextualizing what's 266 - > happening. 267 - > So you're not telling it that this is a person, this is a 268 - > yellow vest, and so on and so forth. 269 - > It already knows this because of the LLMs uh that I just talked 270 - > about and and and other proprietary uh technology.

271 - > So what it does is let's say that you have um an accident in 272 - > a specific aisle, or you have a product that is spilled, or uh, 273 - > or you have obstacles, or if you have a pallet sticking out where 274 - > it shouldn't be, so on and so forth, it's already going to 275 - > look at that and it can give you an alert. 276 - > It can give you an alert to the supply chain manager and say, 277 - > this is what's happening here. 278 - > How do you either want to handle it, or if there's a specific 279 - > action that you need to trigger if I observe this, then go ahead 280 - > and trigger that action uh by itself.

281 - > So it's it can be used for uh accident detection, uh safety 282 - > protocols, whether those are being followed or not, uh 283 - > observing pallets, like if a pallet is standing there um for 284 - > uh way too long uh and it needs to be uh put into uh onto a 285 - > trailer, it will give you an alert and you can set all kinds 286 - > of alerts using that. 287 - > Uh overcrowding areas, it can generate heat maps. 288 - > You know, there's you know, pretty much, I don't want to 289 - > make it sound like a hyperbole, but it's sky still in it.

290 - > SPEAKER_02: And so as the I would imagine that 291 - > manufacturers, shippers are the the target market that that EPG 292 - > has has been working with and and going after for you know 293 - > these different types of use cases. 294 - > Um I I am curious about the uh sort of formal onboarding 295 - > process. 296 - > Do these do these additional products work best with your 297 - > existing customers, or are new customers coming to you and 298 - > saying, we have this problem, we don't know how to solve it, and 299 - > we think you might be able to solve it?

300 - > Tell me a little bit about those different demographics. 301 - > SPEAKER_00: Yes, absolutely. 302 - > So um it is it can be both. 303 - > And and the reason why we have seen so much success early on, 304 - > and we continue to see a lot of interest and a lot of practical 305 - > um solving practical applications is because we've 306 - > kept sort of the end goal in mind is to solve these problems, 307 - > and we've tried to make it so that it's independent of our own 308 - > software, which is WMS or TMS, so on and so forth.

309 - > Of course, we'd prefer it to be on our own platform, makes 310 - > things easier, especially at Modex. 311 - > We had a lot of uh interest there uh from companies, you 312 - > know, wanting to learn more and really come coming to us with uh 313 - > with problems and challenges, uh, and some of which we didn't 314 - > think about, uh, and but we could certainly use those and 315 - > apply those, apply our AI environment to those, to solving 316 - > those use cases. 317 - > So I would say it's a it's a bit of both, and we've intentionally 318 - > kept it agnostic so that you can pretty much use it with any 319 - > existing software, and you're not beholden to using our 320 - > platform, uh, but certainly you'll you'll get more benefits 321 - > from it.

322 - > SPEAKER_02: Oh, that that's interesting. 323 - > So it it's integrating into what maybe a user is already have 324 - > already invested in, and so it's an additional intelligence layer 325 - > on on top of that. 326 - > SPEAKER_00: Yep, absolutely. 327 - > SPEAKER_02: So you've done the the pre-qualification, you you 328 - > you figured out, oh, this is gonna be, and I'm talking from a 329 - > customer point of view, this is gonna be a good fit for us.

330 - > What should I do on my end of things to make sure that I'm 331 - > prepared from a data lens, from a tech lens to make sure that 332 - > I'm gonna be able to hit the ground running if I choose to 333 - > engage with you? 334 - > SPEAKER_00: Yeah, so we have a very detailed and specific 335 - > process if we go through and walk through the customer. 336 - > What I want folks to understand is uh I remember somebody 337 - > mentioning that adding in a new ERP uh is like getting a root 338 - > canal.

339 - > It's it's painful, and but you but you know that you have to 340 - > get it done. 341 - > Right? 342 - > That's not the case here. 343 - > Uh, just like with, you know, it may not be as simple as 344 - > subscribing to JATGPT and you start using it, but it is closer 345 - > to that than it is to uh deploying a new ERP or WMS.

346 - > So uh we have a detailed list of documents and checklists through 347 - > what through what's required, what's needed, and it's it's 348 - > very use case specific. 349 - > Uh that will walk you through, and it's a very uh it's a 350 - > detailed and thorough process of uh us looking at the environment 351 - > and then uh assessing where we can add value if we can, and 352 - > then moving forward with uh with that. 353 - > So it's it's a very uh detailed specification that we walk 354 - > through with customers and uh understanding.

355 - > Because if you don't understand, if you can't see it through 356 - > their lens, then we can't solve their problem. 357 - > SPEAKER_02: It's as you know, more and more teams are uh 358 - > adopting these tools, there is you know a segment of the 359 - > population that is incredibly fearful about it using these 360 - > tools. 361 - > And oh, is you know, if I start to use this tool, is it going to 362 - > replace my workload? 363 - > Based on your experience and the teams that you've worked with, 364 - > how are you handling some of the pushback that that comes with 365 - > that fear?

366 - > SPEAKER_00: So that is, I would say that's the um, you know, 367 - > boiling the ocean uh category, right? 368 - > Like that's not what we're doing. 369 - > We're not boiling the ocean, we're not trying to figure 370 - > everything out. 371 - > And and that also comes from some of the hype from AI, right?

372 - > It's like people saying that AI is gonna solve all problems. 373 - > So the bottom line is AI has been overhyped when it's 374 - > positioned as a replacement of systems. 375 - > That's not what we're doing. 376 - > You still what would need it's not we're not ripping out your 377 - > WMS or your execution stack and replacing it as AI.

378 - > So once you start thinking about that, then you're gonna be like, 379 - > okay, well, this is gonna replace everything. 380 - > No, it's not. 381 - > What it's doing, it's it's making you, it's making helping 382 - > you rather make intelligent decisions and leveraging the 383 - > visibility that you might have actually achieved through 384 - > deploying these systems, which in itself can be a big feat, and 385 - > then uh making you giving you that competitive edge to be able 386 - > to be ahead of your competition and also not only understand the 387 - > visibility of your supply chain, but also execute and be 388 - > future-proof.

389 - > SPEAKER_02: And so as you're you're, I guess, building these 390 - > out or building these systems out with different teams, uh, 391 - > I'm curious as the, you know, maybe some of the executives 392 - > have bought in, but it's down to you know, that sort of in the 393 - > trenches employee or that department that has to manage 394 - > the actual change management and the adoption and making sure 395 - > that that people are using these tools. 396 - > And your experience, is it really sort of one person like 397 - > the AI ops lead, or you know, someone internally that's you 398 - > know put in charge of like being the champion of you know the 399 - > different adoption tools of AI?

400 - > Is there more of a success rate that you've seen with different 401 - > roles or you know, departments, or evolutions of how you know 402 - > the modern manufacturers are moving into the in the modern 403 - > age using AI? 404 - > SPEAKER_00: So I wouldn't say that it there's necessarily a 405 - > group of people that that we've seen more interest in. 406 - > It really depends on the company's DNA and whether you 407 - > know they're a little more forward-looking as opposed to 408 - > whether they're conservative specifically.

409 - > Uh, and and the reason why I say that is because our use cases 410 - > are so varied. 411 - > So now I talked about the four walls, uh, solving problems in 412 - > the four walls. 413 - > That's primarily what we focus on. 414 - > But we also have something called as an orchestrator, uh, 415 - > which can understand if there's a delivery coming in that's 416 - > late, then it can manage all the workflows inside the four walls 417 - > based on the late arrival of that delivery to reprioritize 418 - > all the work so that you can get the rest of it out as soon as 419 - > possible and as efficiently as possible.

420 - > So I would say operation supply chain and IT all have to sort of 421 - > align uh to be able to make the decision. 422 - > But I don't necessarily see a specific category or specific 423 - > subfunction within a company that that has been more excited 424 - > or or more um willing to move forward with it as opposed to 425 - > how the company is structured and and whether they're more of 426 - > a forward-looking company or or a conservative company. 427 - > SPEAKER_02: Yeah, because there's definitely a little uh, 428 - > you know, with some conservative companies, there's a you know, a 429 - > hesitancy almost to adopt these tools and how they, you know, 430 - > they don't want to, what I've done for you know 10 years has 431 - > worked for me.

432 - > I don't want to change, you know, that that kind of mindset, 433 - > which maybe has to be massaged a little bit. 434 - > And once they start seeing, you know, sort of the eye-opening 435 - > moments that these tools can provide, then it leads to to 436 - > greater adoption. 437 - > And I and I'm curious if you've seen that maybe with with your 438 - > own customer base, how they, you know, maybe they'll get started 439 - > with document processing and then now they want to add on 440 - > another layer.

441 - > Are you seeing more of a an all-in-one approach where 442 - > someone wants to jump all in and rework everything, or maybe like 443 - > a phased approach? 444 - > SPEAKER_00: Uh phased approach is is what I've seen primarily. 445 - > And it makes sense. 446 - > Crawl, walk, run.

447 - > That approach makes the most sense. 448 - > And that's what we've seen um more and more. 449 - > But yes, we have we've had some conversations with customers 450 - > where we worked with them for a while and and you know, they 451 - > know uh our capabilities and and they have trust in what we can 452 - > bring to the table. 453 - > Those are uh are proceeding with having, even though even though 454 - > it's phase, they want to go go sort of let's call it a big bang 455 - > approach, more of a big bang approach.

456 - > And and uh we've seen some success there as well. 457 - > What I will say is yes, there's going to be uh a lot of uh 458 - > trepidation. 459 - > There's going to be a lot of customers thinking that, you 460 - > know. 461 - > What should I like?

462 - > Should I really do this? 463 - > But the bottom line is you gotta start somewhere. 464 - > Start small because think about it, Blythe, just like twenty, 465 - > thirty years ago, right? 466 - > We didn't have cell thirty years ago, we didn't have cell phones 467 - > or we just started getting them.

468 - > Now we're able to text. 469 - > Now we're able to have Wi-Fi. 470 - > Now we're video, now it's AI. 471 - > So it's constant change, right?

472 - > So if you don't change at the appropriate rate, then you're 473 - > gonna be left behind and your competitors are gonna go ahead. 474 - > It doesn't mean that you have to, you know, go in and and flip 475 - > everything upside down, but you gotta start somewhere. 476 - > SPEAKER_02: Absolutely. 477 - > And maybe uh out outside of the use cases we we've already 478 - > mentioned, are there any other maybe moments that you can pitch 479 - > to a customer that can get them to start you know crawling 480 - > before they walk or before they run?

481 - > SPEAKER_00: Uh yeah, no, absolutely. 482 - > I mean the the the key is to um understand how clean is your 483 - > data and and and really understand that um because you 484 - > know if you have naturally if you have garbage data, garbage 485 - > is gonna be coming out, right? 486 - > So that is where I would say the customers or prospects or 487 - > whoever is exploring AI, whether it's our solution or somebody 488 - > else's, which I don't think specifically I I haven't 489 - > encountered anyone who's solving problems in this realm the way 490 - > that we are, but um regardless, you know, they should make sure 491 - > that their data is uh is clean, the data is accurate, and and 492 - > ultimately that is gonna then help them to start with a use 493 - > case, start with saying where is where which outcome is going to 494 - > yield me the best possible result inside the facility?

495 - > Uh what's gonna because ultimately it all boils down to 496 - > ROI. 497 - > And and if that's the case, then you start there and if you see 498 - > it working, then you expand, and so on and so forth. 499 - > But you gotta you gotta start somewhere. 500 - > SPEAKER_02: How do you know if your data is dirty or not?

501 - > SPEAKER_00: Um that's that's a good question. 502 - > I mean, uh you will if you have, you know, it's basically if you 503 - > have a WMS system or or a system that's been that's a legacy 504 - > system that you've been using, uh a lot of the times, depending 505 - > on the size of the organization, if it's too small of an 506 - > organization, then they know in general they don't have a good 507 - > system of managing all of their data. 508 - > Uh but from a mid for a mid-sized organization, you 509 - > know, it also through their um through their operations, it 510 - > becomes somewhat evident that they don't have they have 511 - > disparate systems, disconnected systems.

512 - > If they can't talk to one another, if you don't have 513 - > end-to-end visibility, that is also a sign of you not having 514 - > the right type of either data visibility uh or uh or data 515 - > cleanliness, if you want to call it that, to be able to execute 516 - > something like this. 517 - > SPEAKER_02: And so, you know, f a final couple questions here. 518 - > Uh anything that you feel is important to mention that we 519 - > haven't already talked about? 520 - > SPEAKER_00: Yeah, no, I mean, uh as I said, you know, visibility 521 - > used to be the big thing uh for supply chains, right end-to-end 522 - > visibility.

523 - > We need to understand where, why, how, so on and so forth. 524 - > And that's more and more uh is becoming more and more table 525 - > stakes to be able to get to the next phase as as opposed to the 526 - > end goal, which it should be, uh which it was perceived to be a 527 - > number of years ago. 528 - > So uh what I will say is uh again, going back to the message 529 - > of you know, you you you gotta start somewhere in terms of 530 - > innovation, even if it's small, even if it's utilizing a 531 - > specific use case, so on and so forth.

532 - > See if it works, but you have to be able to, you know, take that 533 - > leap uh and start small and and don't try to again, as I said, 534 - > boil the ocean and measure that result. 535 - > And if it leads to a positive ROI, then you sort of have the 536 - > indication of where you need to go. 537 - > SPEAKER_02: All right, perfect. 538 - > Well, well, well, Jet, I think that's a a great place to end 539 - > the conversation.

540 - > Where can I folks or where can I send folks to connect with you, 541 - > connect with EPG? 542 - > SPEAKER_00: Sure, yeah. 543 - > So uh, you know, of course, uh visit our website, www.epg.

com, 544 - > uh, echo papagolfepg.com. 545 - > And you can find me on LinkedIn. 546 - > It's JetJ-E-T-T, C-H-I-T-A-N-A-N-D.

547 - > And um I I checked the other the other day, and there's only one 548 - > result that you can find. 549 - > So it's uh that you know that's uh perks of having an unusual 550 - > last name, I guess, but that's where you can find me on 551 - > LinkedIn. 552 - > So please feel free to connect and you know, happy to engage in 553 - > conversations and answer questions, uh, whether it's 554 - > related to EPG or just around AI or uh or anything for that 555 - > matter that that pertains to the industry.

556 - > SPEAKER_02: Perfect. 557 - > Well, well, thank you so much. 558 - > And I'll I will find that that singular link for for LinkedIn 559 - > and make sure I put it in the show notes just to make it that 560 - > much easier for folks. 561 - > Uh, but but this was really interesting conversation, so 562 - > thank you, Jet.

563 - > SPEAKER_00: Thanks for having me, Fly. 564 - > Thank you. 565 - > Absolutely. 566 - > SPEAKER_01: Thanks for tuning in to another episode of Everything 567 - > Is Logistics where we talk all things supply chain for the 568 - > thinkers in freight.

569 - > If you like this episode, there's plenty more where that 570 - > came from. 571 - > Be sure to follow or subscribe on your favorite podcast app so 572 - > you never miss a conversation. 573 - > The show is also available in video format over on YouTube 574 - > just by searching Everything Is Logistics. 575 - > And if you're working in freight logistics or supply chain 576 - > marketing, check out my company Digital Dispatch.

577 - > We help you build smarter websites and marketing systems 578 - > that actually drive results, not just vanity metrics. 579 - > Additionally, if you're trying to find the right freight tech 580 - > tools or partners without getting buried in buzzwords, 581 - > head on over to Caggorex.io where we're building the largest 582 - > database of logistics services and solutions. 583 - > All the links you need are in the show notes.

584 - > I'll catch you in the next episode and go dive.