Why Home Depot Refuses to Build One Big AI Agent

0:00Angie Brown: So we estimate across weather geospatial customer preferences, we've got about 1.5 million deliveries at risk on an annual basis. When we piloted this in Chicago and we're, you know, continuing the rollout now, one of the headlines that really stuck out for me is we were having about a 5.3 % failure rate on deliveries in Chicago before we implemented the very first version. And once we had implemented the very first version, we had driven that down below three to like two, eight, two, nine and through there. So it's a pretty significant basis point drop. We're continuing to learn more along the way and continuing to get better.

0:39Angie Brown: When it comes to customer sat, on-time delivery is a huge component of that. And we want to continue to drive that number down as low as possible. Today, we're talking with Angie Brown, CIO of Home Depot. Home Depot runs over 2 ,300 physical stores and also one of the largest e-commerce businesses in North America. I think it's around about$25 billion a year on online sales. They sell lumber, hammers, they can help you with your whole kitchen renovation. And that may seem a long way from the AI sort of use cases that we usually cover. But it turns out that they are using AI in a variety of really unique ways.

1:19And the interesting story for us here is that they're using agents for things that happen in the physical world, figuring out how to deliver orders efficiently, answering phones in stores, helping contractors quote for projects. Angie leads the team that is actually building all of this. Angie, welcome to Beyond the Pilot.

1:40Angie Brown: It's great to be with you today, Sam and Matt. Thank you for having me. Angie, I mentioned the 2 ,300 stores. Can you give us a sense of the sort of technology business that runs behind this? Where does AI actually sit in here? So if I take a step back and just think about the company at large, you know, just like what you mentioned, we've got over 2300 stores and the sixth largest e-commerce business in the States. And so there's a huge like technical presence, but then how you run those stores. one of my favorite things to do is to take a new employee and go walk a store and point out all the different components of technology that make that store hum.

2:20Angie Brown: At the same time, like obviously with the digital presence that we're referring to, a huge online presence, a lot of times, you know, people tend to forget the supply chain behind that, that powers it. So if you think about what really makes all this come to life, it's how we move products both out to our customers and to our associates, I mean, and to our stores. And then you can just keep pulling the thread. I mean, if you think about marketing, if you think about pricing, if you think about merchandising, you know, technology truly, when you look at our strategy for a company, it underpins everything that we're investing in and how we are bringing that experience to life for associates and our customers.

3:08This is VentureBeats Beyond the Pilot podcast. It's about enterprise AI in action. I'm Matt Marshall. Today's episode is presented by OutShift by Cisco, Cisco's emerging tech incubation engine and driver of agentic AI, quantum next-gen infra and beyond.

3:27So Angie, we're talking about AI and agents. Someone who's maybe putting in a new ceiling fan or renovating a bathroom, we've all done it. Walk us through, maybe I'm doing some phone research. I'm taking a photo. I'm loading it to your assistant called Magic Apron. How do you look at it as the person building AI? Walk us through each step.

3:51Angie Brown: So one great place to start is just search online. If you come to the website and you start just looking at ceiling fans, maybe that's your first. There's a tremendous amount of logic that goes back into the search results that you're seeing. You can also engage with what we call Magic Apron on the site. So perhaps you've narrowed it down to a couple of different ceiling fans that you're interested in, but like you want to know the difference between those. You can engage with, you know, a conversational agent that and ask questions. You'll get prompted. Is this going indoors? Is this going outdoors?

4:27Angie Brown: You know, what is the type of fan speed that you want? Or do you want a light? Do you not want a light? and help you continue to narrow down on that. There's little things along the way, like whenever you're looking for those ceiling fans, you're going to see an estimated delivery date on each one of the product information pages. All of that. If you could think about all the logic that goes into that to compute behind the scenes, how quickly we can get something to you or showing you how many are in stock in your local store, if that item is actually in the local store. So maybe you've gone through an experience where, you know, you found a couple in the search results you're interested with, you've popped out to Magic Apron, you've better identified indoor, outdoor, etc.

5:11Angie Brown: And then the other things that you can start to engage with in Magic Apron are what are the tools that I need to get this done? Things as simple as a stepladder to, you know, the right screwdrivers and things of that nature. Do you have light bulbs? Do you need to buy light bulbs? Our intention when you're interacting with that is to do a multitude of things. It's not just about getting you the one item you came to look for, but it's getting you the things you need to get the project done and the confidence and the know-how to actually go and execute that project. You've got AI all through that experience.

5:49Angie Brown: Obviously, we've trained a lot of models with product information, but also the project know-how to help you through that experience? Hearing that answer, I think a lot of us will say, okay, there's this an assistant that leads me through all those things that you've just talked about. But I think if I'm understanding the story correctly, the assistant, this magic apron that I'm going to be involved in, it's just one part. There's actually more in the AI, in the fulfillment and delivery apps, right? Or even in the professional contractor business. So encapsulate what you're most proud of of your AI journey so far.

6:27Angie Brown: Keep going from there. You've built your cart now, and so you're ready to check out. There's a couple of different places now that AI starts to interact with that, your estimated delivery date. But what's happening behind the scenes to get you that estimated delivery date is a tremendous amount of fulfillment logic. And that fulfillment logic is looking at where you are, where the items are located and the fastest path to get you that item. If it's in our store, the fastest path could actually be using, you know, the stores of fulfillment engine. We may be able to get that to you in two hours or less.

7:02Angie Brown: If it's not an item that we carry in our stores, maybe it's coming out of our own of our distribution centers. AI is all the way through that. If this was a bigger item that we needed to give a delivery truck, like to your house, AI kicks in there too. We're going to be assessing what that route is, looking out for bad weather, etc., making sure, you know, to increase our on-time and complete. And then once you get to the other side of purchase, if you have questions, returns, you need to interact with a call center agent, anything of that nature, AI powers a lot of those too. If during that journey, let's say you wanted to pop out and actually call a store and confirm, you know, that they had it in there.

7:44Angie Brown: Maybe you're a little suspect of, you know, whatever inventory shows online. You can interact with AI when you call that store as well. They can give you the information on the Isle and Bay. They can even send you the link so you can shop directly there. So it's coming to life in so many different parts of the experience. And I think the biggest thing for us in grounding is the friction points of a customer when they are shopping with us, we are constantly leaning into what are those friction points and how can we make them better? And increasingly, increasingly, the answer is by incorporating AI into that journey.

8:26So Angie, let's talk about the order intelligence. This one I found really interesting, right? So this is one of your sort of first agentic kind of things that you guys have rolled out, if I understand correctly. you know, helps you to basically find people's houses or find where the actual delivery place is. Can you tell us like a little bit about that? And how are you finding that working compared to what you had there before?

8:53Angie Brown: Really, it looks out for three different types of risks, like a weather risk. If there's been flooding, icing, anything of that nature, could that be impacting the route? The other thing that it looks out for is what we call geospatial risks. So do you have a narrow road? Do you have a narrow driveway? Do you have a neighborhood access challenge? Something of that nature. And we're comparing the truck type that we're getting ready to send the product on to those geospatials. And then we're looking to see if there's an anomaly there that would keep that truck from actually making it through the recommended route.

9:32Angie Brown: And then the third part of that is customer preferences. So a lot of times a customer has like a drop location that they're very specific about. Or perhaps we've done this delivery route before and we know there's a gate code. Those types of things. So you can think about it in those three chunks, like weather, geospatial, customer preferences. And all of those things go in together to give us one of three signals. Do we need to contact the customer? Do we need to contact the driver? or do we need to change the truck type? And so I will clarify, when you get to that stage and you're getting one of those three signals, it is still human in the loop to take action on those signals.

10:20Angie Brown: Obviously, as we think about how we're continuing to mature this, we're pulling that logic further and further up and then to where you could start to also automate those actions instead of having a customer call to say there's inclement weather, the roads could be delayed, do you want to reschedule? We could be popping that through your proven or your chosen communication method, asking you directly via text and letting you engage with the calendar there to choose a new delivery date if you wanted to reschedule. This series is brought to you by OutShift, Cisco's incubation engine. By creating an open, interoperable infrastructure, OutShift is enabling agents and humans to share intent, context, and reasoning.

11:08The cognitive evolution for agents is here. Explore the Internet of Cognition at outshift.com. Where I'd like to go next is how you actually built this, this agentic delivery on this side of the order intelligence. Like, what is the model? What's the orchestration? How does that agent work and hand the work back to the human?

11:33Angie Brown: You know, one of the biggest things that we had to think about whenever we were starting on this journey was like, what is our taxonomy going to be? What is our stack going to look like and things of that nature? So just in general, we had to put a lot of time and energy into what our spine was going to look like. What is our platform going to look like and things of that nature? And really, we've layered this out. You can think about it at the top as the experiences that you interact with. You're going to interact with things in a variety of different points of entry. Underneath that, we've actually put a really thin layer tied to that client.

12:09Angie Brown: And we call it like a client planner that helps determine inference, pick up the right next high level agent, etc. to pass it off to. And underneath that, then you get into the meat of our high level agents. and these are typically driven by domain. So for example, like we will have a domain agent around selling. We will have a domain agent around post-purchase. We will have a domain agent around delivery. Underneath that, we even have a finer grain level of sub-agents. One of the really good examples of that is like if you're selling, you may have a sub-agent specific to paint. You may have one specific to power tools.

12:51Angie Brown: You may have one specific to configurables, et cetera. And then underneath that, you know, a lot of this takes advantage of tools and common APIs and, you know, our data stores, et cetera. And so when you think about this, you know, specific with a supply chain use case, a lot of it was getting the data in underneath to where the agents and the subagents could interact with it. yes, leveraging tools like Google Maps. One of our biggest kind of grounding principles on this is that we expect reuse at the experience level. And so, you know, we really had to work hard to figure out we're not going to have one agent that rules them all, how to create a sub-agent architecture that let us take advantage of the client-specific context of what it was trying to achieve, get it to the right place as quickly as possible, but still allow reuse across different experiences.

13:51Yeah, that's fascinating that you've decided to go with that planner, which feels fairly light. So it's planning, and you quickly divert to these sub-agents through specialists. So one thing that's missing from that is, is some sort of meta agent that's saying, aha, this person is just buying a single hammer. How do we make sure that we're helping them with the entire project and lead them into that? If you have just a planner and then just immediately designating it to a specialist, how do you have that meta agent that has that bigger logic?

14:31Angie Brown: I think one of the things, and we're testing our way into this, But one of the things that we are finding is you can inference a lot of context from how the customer is coming in to engage with us. If they are coming in online versus if they are coming in in store. So, again, adjacent from the delivery example, but let's talk about Magic Apron as an example here. If I am using Magic Apron online versus if I am using Magic Apron in the aisle. And, you know, both of those things are accessible. However, your interaction model is actually very different in a store. We feel like we can jump to a more meaningful, contextualized conversation based on how you're coming to us.

15:16Angie Brown: That application layer of where you're starting can be a good indicator of that as well. So, Angie, let's stick with a magic apron. Okay. So, my guess is that sort of the first early versions of that existed long before agents, right? Right. That that you're sort of your online store and stuff like that. How do you then sort of decide, OK, we're going to put agents into Magic Apron. What sort of time frame does that take to actually sort of do that? And then also, how do you sort of evaluate that? It's anything from, you know, the agent development kit, which, you know, we're pretty hefty Google shop.

15:56Angie Brown: So we've got a lot of Google ADK running around there. Also within there is like, you know, the agent registry discovery and onboarding, the tools registry, MCP enablement, the control plane, agent to agent enablement. When you go underneath there, we have LLM evaluation and observability, you know, around like obviously observing everything that's going on. And you keep on going down the stack into prompts and services. And we have a prompt management hub underneath that with memory management. We get into models, you know, that have been fine-tuned with different pipelines. And, of course, underneath all of that is an Alledge Foundation with both unstructured vector databases, hybrid search, and a data mesh underneath there as well.

16:47Angie Brown: all wrapped with a whole ton of security guardrails and safety evaluations and agent identity and all of that fun stuff around it. So I'm curious, like you mentioned ADK. How do you make the decision to go with ADK as opposed to, you know, Langchain or, you know, OpenAI's offering or something? You mentioned that you're mostly a Google shop. Is that purely like the decision on ADK is just for that? Or what sort of time frame do you give and how do you evaluate these things before you decide, yes, this is the one we're going to production? The time frame varies, honestly, by the decision you're trying to make.

17:25Angie Brown: And like we have a number of partners. I think our Google journey started back when we moved our website to Google Cloud over a decade ago. And a lot of our data sits within Google BigQuery. and, you know, the vast majority of our data sits within Google BigQuery. So there's some synergies that you get from that. We're always testing, you know, different things as well. Like, for example, we've got Azure OpenAI. We like the tension between using, you know, Google on one side and then OpenAI to judge the outcomes of, you know, what we're getting from Google. We do something similar when it comes to writing code too.

18:08Angie Brown: You know, we obviously have a lot with Claude, but then we keep open AI models as well to help us on code reviews and things of that nature. So it's not that we are a Google-only shop, and I should definitely say that when you get into things more like computer vision or traditional machine learning, things of that nature, you're going to find a lot more open-weight, like open -source solutions out there. We're heftier with Google on the generative side. I think one of the things is, you know, the context training that has to be done anytime, you know, there's a switch. So there's a stickiness, you know, level there that comes in.

18:46Angie Brown: We've also kind of grown up our own, like, homegrown platform as well that we call Magic, you know, Magic Forge. And depending on the type of compute that we're talking about, some of our most complex things are also using, you know, Magic Forge. and then with others on ADK. There's a constant evaluation there. It's really hard not to go and chase every, you know, potential new model, you know, that comes out. But I think we try to take a pragmatic view into, is the juice worth the squeeze? One of the biggest things that we're trying to do is drive for cost efficiency. And so testing different models from that perspective on the cost side too.

19:32I think you're describing what seems to be kind of an industry best practice, which is you have that control plane. You're building your own layer there, and then you're being able to then use whatever solution you need for that particular application. We were going through Magic Apron. You rolled it out, and there was an interesting reaction.

19:55Angie Brown: Story went, we were super excited about Magic Apron, put it on the website. Customers liked it. you know we were early days we were evolving there there were still some things that we even learned on the consumer side but the pros like you said just were not engaging and so we have been investing in changing that we have relaunched it on the b2b site a lot of times you want to talk about that project coming to life that is typically what a pro is trying to interact with how to complete a job. And so we have really leaned into a few different things like list builder and list builder AI, trying to help them, you know, tell me a little bit about your job you're doing.

20:42Angie Brown: It could be, you know, putting at a fence, give me the size, you know, that you're working on and we can generate a materials list for you based on that. So you're not having to do the math on the number of post counts or, you know, things of that nature. How much concrete you need? Do you need overage? And so those types of question prompts are, you know, just very much more helpful for the pros. Even outside of Magic Apron, we found that some of the ways that we benefit the most is for things like blueprint takeoffs. So I don't know if you've ever built a home from scratch or worked with an architect or had someone that did, but, you know, it starts with a blueprint and you have to be able to take that and understand, you know, a lot of the core materials that you need to get started in construction way before you ever get to faucets and lighting and all the pretty stuff.

21:39Angie Brown: So from that perspective, your time to take that blueprint and get a quote back in those pros' hands is critical to how much, you know, how interested they are in working with you. So we've got an entire workflow on blueprint takeoff that turns around a quote in, you know, 24 to 48 hours instead of the week plus that it used to be. And so from that pro perspective, you know, those are some of the things that we found, Like speed really matters. How do we get them to a material list as quickly as possible? We built in like the ability to take all sorts of input, like, you know, show me your napkin.

22:25Angie Brown: You know, we can translate that into help you translate that into a materials list. We're helping them do something they need to do and do so even faster, helping them think through the prompts to create that list. It's not that a consumer may not want those things as well. That's always analysis we're looking at as to how those, you know, kind of, I don't want to say come together. This is a great example how they're built on the same core infrastructure, but we are contextualizing the experience slightly different on B2B. But, you know, are there other signals to where we could start to expose more of that on the consumer side as well?

23:04That's a great example of how it's really not the technology to some extent. It's speaking through what their use case is, what they actually need. And so they need speed. They need that blueprint. They need that list. They need the quote within a certain amount of time. When you rolled it back out, is there anything that you can tell us around the technology side? Has your framework, you talked about the framework, being similar or different depending on the use case. Has that framework evolved? What I mean by that is the agent to agent, there's the client layer and then the specific move to delegate to the specific agents.

23:46Has that all remained the same throughout, or is that evolving, your logic there?

23:53Angie Brown: Can I say both? I mean, I think the same, you know, kind of high-level intention has stayed pretty consistent, but obviously the evolution that we're doing underneath there is continuing to evolve. A couple of examples I would give you of that, like, you know, so much of this work and bringing it to life is really less about the LLMs and more about the engineering around them. When we first started on this journey, we historically had to provide like a lot more summarization in order to get that context. And now newer, better models, you know, are better at that context. The models are more intelligent, you know, for sure.

24:35Angie Brown: And we see that, you know, coming to life. But I think some of the biggest things for us was, you know, the depth of the questions that we get. These are not one word or one line responses. And so you have to truly build up that, like, share context across and, you know, go from it's not just about product knowledge, it's about project knowledge to and you can see it going even further into like, you know, you could get into building codes and regions and things that nature and you just need to keep adding on additional context around this conversation to make it as you know meaningful as possible do you do you look at that as sort of the end goal is to build this sort of oracle that knows everything about construction about you know all those sorts of things and and the and sort of the thing i'm curious about too is you've sort of talked about that really what has worked the best perhaps is just making what you currently have more efficient as opposed to, you know, totally new products.

25:42How do you think about those sorts of things as well?

25:46Angie Brown: You know, and maybe this sounds a little goofy, but one of the things that I would say is, I mean, Home Depot first and foremost has always been about customer service. We want to be the place where you can come and get them know how you need and the confidence you need to get your job done. These tools give us an amazing way to, one, assist associates in having that confidence in order to, you know, help us, customers through a project, but then also help, you know, associate customers directly through our digital platforms. And so do we have this, like, be the Oracle, you know, goal? I think, you know, I would restate our goal to be like, customers come to us when they have problems and they need to get projects done.

26:30Angie Brown: And we absolutely want to give them the projects. I mean, the products, the know-how and, you know, the list to get those done as easily as possible. So they've got confidence to take on even more projects at their household. If we can make the small one easy, you can move on to your next one and your next one and your next one. And we're there to help you along the way. Okay. So one of the other things that was really interesting that came up was the whole sort of use of IVR or sort of an AI version of IVR, right, in the stores. Can you tell us a little bit about that? And then how are you finding, I'm also really curious to sort of find that, like you said, you know, you've always been about customer service.

27:12You've got this huge team of people that actually work in physical stores. How do they feel about these new tools that you're bringing in?

27:20Angie Brown: So when you start with the IVR, you know, when we rolled out NGA with Google, We've got it in about a thousand of our 2300 stores right now. So when you call one of those stores, you're going to interact with a conversational IVR instead of your traditional tree based IVR. That IVR can help you with a few different things. One, you know, it is multilingual. Not all of our associates are multilingual. So, you know, that's a good thing. It can check your order status. It can help you, of course, with hours and things of that nature. so that you can go deep onto item information. So this morning, funny enough, even before this call, I was playing around with it.

28:03Angie Brown: I need to buy every driver in my family one of the, like, jump kits for their battery. If their battery goes down, they're not that expensive. They're wonderful to have on hand, and you can easily get your car started again. As you can tell, I don't even know what to call it, right? I call it a jumps kit. There's probably a better term for it than that. So I call one of the stores that has it and I was like, I'm interested in buying, you know, something I can jump my car off with. Can you tell me what you have in store? And she asked me a question I didn't know the answer to. And I said, I don't know the difference.

28:38Angie Brown: You know, what are my options? She comes back. She tells me the two that she has in store. And then she asked me if she want, like, if I want her to text me the product. I said, absolutely. She confirms it's the phone number I'm calling from. and then so she texts me a link to the actual product on the website to where I could pick it up and buy it from there if I wanted to or obviously put it in a buy online pickup and store order and I could read more about it. So that concept of helping you understand what's physically in the store and a little bit like even helping you get the product knowledge to get going, we estimate things like that will drive probably close to three times increase in the number of questions that we can answer on the IVR versus having to pass you to a person.

29:27Angie Brown: Now, the person's help is always there, and that's one of our guiding principles. We want you to be able to get out of this IVR experience as quickly as you want to get out of it if you want to talk to a human. Think about the other side of that. So let's say I am trying to page to that person in the aisle to help you and answer that question. You get into the complexity of in what department, the product knowledge of that associate, are they available? Are they assisting another customer? Are you having to wait on the line where they finish that assistant? So none of those things are intended to replace the employee knowledge.

30:07Angie Brown: What we see happening more than anything is those employees can stay belly to belly with the customer that's in the aisle and make sure they're giving them great experience. And then of course, like they can pop out to the phone if you want to. All of us in corporate, we spend at least a day, a quarter working in each one of the stores. And I was talking to one of the, one of our deepest technical resources, you know, on this. And he was telling me about in one of his store days a guy walked up with a picture and the picture was of a plumbing um something and there were valves and switches and etc etc all over that you know pipe and the guy shows it and says you know can you help me find this and Hari is looking at this and there are like eight different products on this you know and he's not comfortable in the plumbing aisle, a lot of associates aren't.

31:04Angie Brown: And so he loads the picture up into, you know, magic apron in the store in store mode. And they start to talk through what, you know, component is broken. And, you know, in no time at all, Hari's able to, you know, get that down to, it's a ball joint that has to be replaced. They find the aisle in the bay, they walk over there, they get it, they can talk through any other products that they need. So that confidence, especially when you're talking about aisles like plumbing or electrical and things like that, for an associate to take, you know, a customer through, we are getting amazing comments, you know, from the confidence that gives our associates because we're not looking to, you know, do anything other than augment the knowledge of the associates and give them that exact same confidence.

31:54You have customers all over the state. So you have a much sort of broader sample than San Francisco, for example, right? Roughly, what is the percentage of people that are prepared to talk to like a more intelligent AI, IVR nowadays compared to, you know, like in the past, I think everyone was just like, give me the person, give me the person, give me the person. As it's starting to actually work, and it's fascinating that you're saying that this is helping to answer three times, you know, as many questions and things like that. How many people actually stay on and prepare to talk to the AI?

32:30Angie Brown: I don't know. I don't have those numbers up in front of me. I will tell you that for sure. I love listening to the calls, though, that start out like you can almost hear the eye roll, right? Like as soon as you hear the IVR like kick in, I think a lot of human nature is like, oh, my gosh, I've got to talk to, you know, can I just talk to a human? And then the number of times like we, you know, we listen to those calls and they divulge into then like the, okay, hold on, I'll give this a try. Okay, hold on. That was helpful. Okay, hold on. No, you did answer my question. Thank you. And like the times that you will hear a customer come back and say thank you.

33:12Angie Brown: So, you know, we all always are watching that. I don't think we're perfect yet. and you know by any means and that has actually been some of the learnings like i said we're in a thousand stores we're you know we're working on uh correcting a few things before we get it out to two thousand and we want you to be able to get to an associate when you want to get an associate and we don't want that to be frustrating well we have found that you know the conversational nature of generative ai it really likes to help and sometimes the humans asking for a different kind of help and AI keeps trying. And so it's been an interesting mix where like we're trying to now, like we're going to go back and layer in like deterministic controls on escalation.

33:58Angie Brown: So it's great. You start out conversational, et cetera. But, you know, a few things, business rules, when you ask for help, policy boundaries, et cetera, those are much more deterministic. And so we're bringing those things together. If you're in Silicon Valley, you're hearing, hey, this is a revolution happening. and I'm seeing it with my colleagues, friends, and acquaintances, where you're starting in an LLM, you're starting in Claude, you're starting in an open AI, you don't go to Magic Apron, right? You may eventually, if you're forcing me to, but at what point does it flip? Are you seeing that happen?

34:34Are you ready for it? And I've got a question related, which is then how do you, maybe we can get to this in a second, but how do you approach that, right? This idea of the Oracle, the idea of that context and keeping that context for somebody alive and how do you do that?

34:50Angie Brown: I was recently at like a customer solutions conference and it was primarily retailers that were talking in there. And it was really interesting. The gentleman, you know, from the company couldn't fathom walking in a physical store, period, the end. There is a little bit of a difference in opinion. And, you know, whether or not that is where the masses will, you know, move to, I think is a little bit too early to tell. Right now we see very nascent traffic coming from, you know, LLMs when it comes to actually purchasing. So a lot of times we see a lot of product knowledge or question and answer that happens there.

35:36Angie Brown: And then when it's time to purchase, You know, sometimes you're seeing that pivot move over directly to the retailers. But we're building to be ready for anything. We're building to be ready for, you know, wanting to complete that transaction directly within the LLM. Of course, we think about how, you know, that could come to life. We think, you know, knowing the customer in those instances is going to be, you know, really important. Being able to provide kind of a contextualized, personalized experience around that. So if you think about how loyalty may start to play into these, like even if you're on, you know, an open AI, chat GPT, et cetera, of that nature, and you're starting your experience there when it comes time to buy, you know, the more you can even bring that customer knowledge and the knowledge of that relationship with a retailer up funnel.

36:31Angie Brown: but we're not waiting for it to take off. I think is the headline. We're definitely approaching the interaction model to be ready for that. Is it growing? Yes. And when you look at the growth that's happening, can you say things like it's doubling, it's tripling? Yes, but it was a really small number to begin with. You can't help but think back to the conversations when even with digital commerce, we thought physical stores were gonna go away and they didn't. They became great compliments In a lot of ways, we think Agenda Commerce will feel similar. It'll be a great complement to other models that continue.

37:06There's this notion that Lowe's kind of won the race with the assistant, getting it out there early. But that Home Depot kind of has won on the plumbing, right? All that context around it. It may actually be set up potentially leapfrog, right? If we're talking about that context around the inventory, IVR, all those applications along with Magic Apron, if you see Anthropic and OpenAI dealing with that context of the user, they're collecting all this memory and context around them. Every now and again, they have to jump in and provide that disclosure. Hey, we have this memory feature. Do you want to turn it on or off?

37:48How do you do that? It feels like you are set up to have this great context and to switch it on. And I'm just wondering what your approach is there to win this race.

37:58Angie Brown: It's a broader question than any, you know, one retailer. I think the north on knowing what our customers need and how we can remove friction is still a great, great guidance to that. When we think about like memory and context and things of that nature. So those are some of the next frontiers that we have to continue to productionalize. One of the examples that we use is I've asked you, you know, I told you I need a PetSafe product. Why the next interaction? I'm not having to remind you I need a PetSafe project. And you could just think how that grows into like a total home and things of that nature of what you've bought before.

38:34Angie Brown: Knowing your brand preference, knowing that you like Milwaukee tools and how then, you know, we're serving up better recommendations. All of that just comes around to how do we make this easier for the customer? And definitely having that knowledge on a broader like realm makes it easier for the customer to do this. What are some of the other things that you see? Like what do you see as the future? Okay. You're talking about memory on customers and helping out customers in that way. What other things do you see agents enabling going forward with what you've been doing? I get super also geeked out about what happens behind the scenes.

39:11Angie Brown: I mean, we talked a little bit about the delivery agent. I love the opportunity as it relates to assortment, space planning. Today we have 2 ,200 stores, you know, and as you're really thinking about each one has 30 to 40 ,000 SKUs that sit in there. When you start to think about the productivity of those SKUs, the assortment of those SKUs, what's selling and what markets and what's not. I mean, this is a longstanding retail, you know, dilemma that we've always had. But man, the ability like to apply AI into that and not just then AI, but moving into agentic AI, because it's one thing to come up with the perfect assortment.

39:55Angie Brown: It's another thing to take that perfect assortment and translate it into a beautiful planogram. It's another thing then to put that planogram and assign it to a store and understand all the product moves that have to happen on that. And then baseline against that or store labor that you want to utilize in order to reset that planogram and then do it on a seasonal basis or on, you know, as products are changing, whether that be, you know, as products are coming into trend to do so more frequently. A lot of those processes today are underpinned by heavy subject matter expertise, heavy human data analysts, entry into like CAD systems and planning systems and things of that nature.

40:39Angie Brown: I mean, you start to streamline all of that and turn it into here your signals. Do you accept? Here's what this is going to mean. We'll update your planogram and get it going for you. and it's just going to, you know, enrich that flywheel around better and better store experiences, contextualize for the customer base. At the end of the day, I want you to come into a store, find exactly what you want, know exactly where it is and have the exact right amount of inventory in for it. And when I can use all of this data in a richer way, it just helps the ability for us to do that. And it sounds like you've got a lot of things that you're working on going forward.

41:17Thank you for joining us on Beyond the Pilot today.

41:19Angie Brown: Thank you very much again for your time as well.

41:50to sign up for our newsletters.