Why should CX leaders care about MCP?
About the show
Hosted by Nikola Mrkšić, Co-founder and CEO of PolyAI, the Deep Learning with PolyAI podcast is the window into AI for CX leaders. We cut through hype in customer experience, support, and contact center AI — helping decision-makers understand what really matters.
Summary
Most companies trying to adopt AI hit the same wall: the models are impressive, but they can't actually do anything inside your systems. As Vixxo's Bobby Hunnicut puts it, they have incredible brains and no hands. MCP is how you give them hands, and it's changing how one of the largest facilities providers in the US runs its business.
In this episode of Deep Learning with PolyAI, Damian Sasso, Group Product Manager at PolyAI, sits down with Vixxo Facility Solutions CTO Derek Neighbors and VP of IT Bobby Hunnicut, the client whose work helped inspire PolyAI's Builder MCP. Vixxo keeps thousands of retail, convenience, and restaurant locations running, and they're putting AI agents in front of staff across the whole company, well beyond engineering.
Together, Damian, Derek, and Bobby explore:
- Why an MCP or CLI has become Vixxo's litmus test for adopting any software — and how the friction of leaving your AI tools for yet another dashboard can rule a product out
- How Vixxo is putting agents in the hands of non-technical staff, from a company-wide skills hub to MCP access scoped to each user's own credentials
- Why REST APIs remain the foundation everything else builds on
- Why the companies stalling on AI are the ones letting governance debates crowd out the work of learning
- What CX and operations leaders should be doing over the next 12 to 18 months
Watch the full episode to hear Derek's blunt answer for CX leaders: however fast you think you're moving, it isn't fast enough.
Key takeaways
- MCP access is now a litmus test for new software: Bobby says even “the greatest solution on the planet” becomes hard to roll out at Vixxo if it has no MCP or CLI, because it forces people out of their agent harness and into another tool. His advice to CX leaders: check your key systems for MCP access and ask vendors whether it's on their roadmap — which is how Vixxo's request led to PolyAI building its Builder MCP.
- Agents should inherit the user's permissions, not bypass them: Rather than ring-fencing access with separate MCP servers per role, Vixxo prefers MCPs that authenticate through each user's own OAuth credentials. A person's agent can then do exactly what that person can do, under the same security rules, policies, and data scoping — including for sensitive financial and invoice data.
- Use AI to prove a process, then engineer the tokens out: Vixxo used AI to automate an invoice workflow that had five manual touch points and a backlog of thousands a day across four people. Once the business has shown what good looks like, engineering can rebuild it on REST APIs and lightweight glue to cut token spend — which is why Derek still sees REST as the foundation MCPs and CLIs depend on.
- The real wins are nuanced, cross-system judgment calls: An agent written by an operations person, not an engineer, pulls 90 days of facility, asset, and service-provider history through MCPs when a service request comes in. In one case it linked a “broken” ice machine to two recent toilet clogs and dispatched a plumber with a camera, a water jet, and a two-person crew instead of a beverage technician, avoiding repeat visits.
-
[00:00:00] Bobby Hunnicut: Yeah. I mean, the ability to have an MCP or a CLI for a technology has now become like a litmus test for us, I think. Like, if it could be the greatest solution on the planet, but if it doesn't have an MCP or a CLI, then it's gonna become a lot harder for us to embrace it and kinda roll it out across the company. Because now you've been you've created a walled garden where I have to now leave our agent harnesses to go into your tool to do actions that I want. And that's just going to be a a new friction point. When I wanna try and instill in our engineers and our people here at VCSO, it's like, try and do your entire job without having to leave the harness. If you have a solution that does not work with that, then that's probably an inflection point or something for us to kind of discuss.
[00:00:48] Damian Sasso: Hi, everyone. Welcome to Deep Learning with PolyAI, our continued podcast series where we introduce new technology, speak to business leaders, and encounter all the exciting developments and challenges in the world of AI. I'm Damien Sasso, group product manager at PolyAI, focused on our developer platform, and we've recently had a lot of exciting releases and technological developments that we've done in our agent studio developer platform this year with everything from a REST API stack where we've allowed customers to develop against our PolyAI Agent Studio functionality using APIs, an agent development kit for, you know, more development through command line interface tools, and recently, we've launched what we're calling our Builder MCP. And so on that note, I brought some of our our contacts and leaders, uh, one of our key clients, uh, to talk a little bit about how they inspired us to build out our BuilderMCP and how they're encountering all the challenges that come with AI and new technologies like like MCP. So it's a quick introduction. Joining me is Derek Nabors, CTO, and Bobby Honeycutt, VP of information technology at Vixo Facility Solutions, one of the largest facility solutions providers in The United States and a PolyAI client. Derek, Bobby, welcome to the show.
[00:02:12] Bobby Hunnicut: Hello. Thanks for having us.
[00:02:13] Damian Sasso: Derek, why don't you start just quickly by telling us a little bit about yourself, a little bit about Vixo, and then then we'll start getting into some of the, you know, cool technological developments that you guys are facing and that we're working on at Polya?
[00:02:26] Derek Neighbors: Sure. I've been, uh, in the software industry for twenty five plus years, largely helping private equity or VC companies either get ready to IPO or basically turn turn their business. In the last two and a half years, have really been focused on AI and AI transformation, originally, mostly in the engineering space, but fanning out into the organizational space. I think one of the things that I've seen in the last two years, year and a half in particular, is AI is starting to impact a lot more than just engineering workflows, engineering processes really, you know, basically being pervasive with inside the organization, and so there needs to be kind of a technical bent or engineering bent to help the business transform into that, uh, but it certainly isn't just about engineering and code. It's about a lot more than that. And so from Vixo's perspective, we've been around for for twenty plus years. We're one of the top leaders. If you if you think of a retailer, a convenience store, a QSR, like a a think of, like, a Starbucks, think of a Circle k, uh, Kwik Trip, you name it. We're probably in doing their facilities or part of their facilities work, or we have in the past. Any kind of retailer, you think of a Macy's, you think of, you know, anything you see in a mall, big box store, grocery store, we're probably in there servicing the air conditioner, the refrigerator, their coffee machine, you name it. A pretty kind of blue collar, turn the wrench type of business. You wouldn't think super high-tech, but the reality is it's a lot of moving parts around when something breaks, what information's around that asset, how to find a a service provider that's in proximity to be able to fix that, fix it efficiently, effectively, to be able to get the parts needed for it, and to coordinate all of that work. There's a ton that goes on, and that's you know, we've had technology that has helped with that some in the past, but there really hasn't been a forward thinking look about how to leverage technology to really go to the next step. And, you know, in the last year and a half, I think it's become very apparent that assets, machines, facilities are built for agentic processes, meaning self referential learning loops within the facilities management process really can make a fundamental difference. The thing that's difficult is because we're kind of in a blue collar world, none of the systems surrounding us are very agentic by nature. Meaning, if when you're in the SaaS world, it's super easy to go find everybody and their brother says, go try out my new MCP. Go grab my new REST API. Go, you know, get my CLI. You can really have this conversation. It's really hard to have that conversation with Fortune fifty's. It's really hard to have that conversation with a facilities management group that, you know, is is dealing with, you know, some hardware that's 30 years old. Right? And so, you know, I was kind of brought in to say, how do we transform VIXO into a modern facilities organization and produce Facilities OS, which is the agentic form of managing facilities, assets, and everything related to outcomes for a facility?
[00:05:40] Damian Sasso: No. That's great. And and I think I think you hit hit the nail on the head in how critical your business is to the operations of businesses that, you know, are important to the customers of all different types of industries and consumers across this country. Bobby, like, just to throw it to you, like, when you look at how critical, like, an operations business like Vixo is, what considerations did you have to go through when you start even getting to the point of rolling out, like, an AI solution, something like PolyAI or, you know, any agentic processes across your firm? Like, what considerations and planning had to go into that?
[00:06:17] Bobby Hunnicut: Yeah. So I I think a lot of the industry has been having a really hard time trying to figure out where the ROI with these AI tools is at. ROI seems very straightforward in the engineering space. You know, you're dealing with code. You're building apps. But a lot of the industry was trying to roll this out to nontechnical users, and we're kinda having some struggles there. And that's what we're trying to solve for. How do we put agents in the hands of people that are not in engineering, that are not technical focus at all? You've got these incredible models, these incredible brains, but they have no hands. They have no tools. And that's where MCPs and these other skills kinda come into effect where they allow the end users to work with the data and the systems that they wanna be in on a day to day basis driving these these agentic use cases. So that's kinda what I'm helping Derek out with right now is how do we roll out agents to every single individual in the company? How do we build agent skill sets and teach them how to use these harnesses to do the type of work that they're already doing, but at a much, much faster and more proficient level using AI agentic tools.
[00:07:20] Damian Sasso: That's great. Yeah. And, I mean, it's such a a critical consideration with the people that are involved in using any agent tool. So, yeah, I mean, coming into this year, you know, we've seen so much technological development in just how AI tools get embraced. We spent a considerable time at PolyAI looking in how we can enable developers through things like agent development kits, which I touched on as we kicked off. But MCP has really been you know, it initially launched as part of a protocol a few years ago, and it's it's this cool little, like, you know, tech thing that that like, always it can really be embraced as it real but it's really started to catch on. What does it mean to your organization in the practical sense? Because it's like, you know, something that we can always think of, and you touched on a little bit, as being a technological protocol, but what does it mean to the people that work at VIXO? What does MCP, like, you know, look like in the day to day? Mary, Derek, maybe you wanna touch on that or or or Bobby, but I'll throw it to you to start.
[00:08:19] Derek Neighbors: Yeah. I mean, I think at the end of the day, agents are fairly useless if they don't have headless access to everything that a human would have access to. Right? And so the the the bets that we made is that giving AI and agents to engineers is fantastic, but it only scales so fast and so far. And so the reality is we really needed to say, how do we give agents to the edge? How do we give it to the end user down to the technician out in the field, and everything in between? And what we really landed on is that there's some fantastic harnesses out there already. You know, you could think of codex. You could think of cursory. You you think of Claude. All those are harnesses in their own right. And we and we said, look, we don't really have the resources to go build our own harness like a block does, but we could certainly take one of these existing harnesses. We could do a lightweight company type of brain that sits inside of that, load a number of skill sets, uh, skills that can load into that, and load all of the MCPs that gives everybody access to all of the data that they normally have access to via UI only with their personal agent. And then we can teach them how to write their own skills and how to build their own processes and workflows with the skills as part of that to customize their agent and that partners to themselves. And immediately, the first thing that comes comes in is somebody has a workflow. They have to be able to talk to the systems that they're dealing with every day. Right? So for a a PolyAI is great examples. Hey. I've got a service quest coming in here. I've got this happening. I've got a service provider. I need to reach out and call that service provider. I need to get some information. Right? You know, currently, that's, you know, hey, I have or you know, before that was I have to go input something or go into a UI or I have to ask engineering to go create something that I can interface within calls the API. Right? And so now I'm I'm waiting. If I if I want new functionality for my process, for my workflow, I'm waiting on engineering. I'm waiting on their backlog. I'm waiting on product. Right? And when we gave people skills, they're able to now get in and do all of these things. They said, well, why can't I just have my agent initiate a call on my behalf to Poly? Why do I have to to tell you how to do it? You've gotta go do a bunch of stuff and write about, you know, stuff I don't understand, and it takes six months. How come I can't just play with that? That's, I think, where we really approached and said, look, we really need to look at what does it look like to have MCPs. And I think you guys have been absolutely fantastic. We said, hey, we can take the APIs and roll our own MCP fairly quickly to get people access. And you guys said, hey, we're already on the the stack and we were able to do something very quickly. But that's really the game tinker. Right? Is it it really gives universal access to the users, to the data in the systems that they already have access to, only now you're giving it to their agent as well. Right? You're you're making that data a first class citizen to the agent. When I say agent, I'm gonna say harness. I'm gonna say personalized agent. I don't mean, like, generic agent. I mean, you know, literally, a a personalized agent that is doing work on their behalf now has all of the same access that they have access to. Right? And I think that's one of the things as as ugly as MCPs can be and as, you know, inefficient as they can be, the reality is they're very simple to to connect and to get out to the edges, and the end user doesn't have to understand a lot. If I give somebody, hey, here's the SDK, here's the the API, go write some code to do this, like, it's just not happening. If I say, hey, go create a skill or just talk to your agent and tell you want to do things, and you already have the MCP hooked up, stuff just happens and it just starts to work, and the agent can figure a lot of the things out itself. I think that's one of the things we're really seeing with MCPs that is fantastic is they do a ton of self discovery. Right? They'll try to do something. They say, I can't really do this. They look for a different thing. Hey. I've got a different way to do it. Maybe if I do it in a different order, I can kinda circumvent and do what you wanna do. Right? I mean, I I think they they kind of expose things in real time that a developer using an API would have to do a whole lot of work work through to do and have to understand a lot, and the end user is never gonna do that. Right? And so it kinda abstracts that and lets the the actual AI or the agent decode a lot of what's in there to get the data that's expected.
[00:12:34] Damian Sasso: Yeah. That may makes a lot of sense. You you touched on something that was really interesting, which is the act of having, like, MD files and skill files on behalf of certain personas, certain, you know, people working on certain accounts. You know, Bobby, is that something that you've seen kind of this transition in the world to making onboarding new new people easier, making, you know, tailoring, I think, technology to your entire workforce more streamlined? Is that is that something that this is solving or is it is there other even other elements to it that that's making, you know, sort of the MCPs enable enable your workforce?
[00:13:15] Bobby Hunnicut: Yeah. I mean, the ability to have an MCP or, like, a CLI for a technology has now become, like, a litmus test for us, I think. Like, if it could be the greatest solution on the planet, but if it doesn't have an MCP or a CLI, then it's gonna become a lot harder for us to embrace it and kinda roll it out across the company. Because now you've been you've created a walled garden where I have to now leave our agent harnesses to go into your tool to do actions that I want. And that's just going to be a a new friction point. When I wanna try and instill in our engineers and our people here at Vixos, like, try and do your entire job without having to leave the harness. If you have a solution that does not work with that, then that's probably an inflection point or something for us to kind of discuss. And to your other question regarding how do these markdown files or skills kinda propagate through the business and how they help us bring onboard people, absolutely. So at Vixo, we kinda have a a skills hub that we've kinda built where everyone that has these harnesses are able to publish and build skills and then publish those to that the skills hub. And then anyone at Vixo can go and pull down those skills, you know, fork them, riff on them, or just kinda use them as they're stated on the tin. And that's how I think you get these these kind of the groundswell activity of like, oh, I didn't know so and so in accounting had a skill. I kinda need, you know, 50% of that because I'm doing something else, but over I'm over here in, you know, service provider management. How can they take that skill that has those built in connectivities and tailor it to their own experiences? That's what we're trying to do. We're trying to help them figure out what is possible and have them share broadly so everyone can kinda be made aware of what's going on and what other people are doing with these same tools.
[00:14:49] Damian Sasso: Yeah. It's really that's really interesting. I think one thing that I was really curious to get your take on, because we've started to think about this a little bit from the PolyAI side of things, is is, you know, you can build MCPs for a number of things. Like, we have data now. We have customers that use our platform to analyze their call data and analyze their business trends, and then we have, you know, different roles at at companies like yourself that are actually configuring agents, constantly updating agents, wanna be that human in the loop. And we've looked at MCP servers as a way to kind of almost ring fence those audiences. Like, maybe we have a builder MCP for for certain roles that just wanna build and tailor agents, and then we'd have an MCP server for people that want to analyze their call data, analyze their business trends. You kinda see that as kind of a an indirect use case for an MCP where you can almost lock down certain access by only giving access to certain MCP servers that can reach certain capability, or is that kind of too restrictive in a way for MCPs? What's your thoughts on that?
[00:15:50] Derek Neighbors: For me, I'd also say it's too restrictive. I think what we've kinda defaulted to is really kind of two modes, and our our preference is a second. So the first mode is, I'm gonna say, like, kinda wide open, like, hey. You've got some kind of a key or a token or or similar, and it's giving unfettered access to that resource. Right? There's a lot of danger in that. There's not a whole lot of governance. Right? But it's the simplest, fastest way to get access to something. Right? And then the second way is to basically defer all activity or access to the MCP to that of the user credentials of the person that created the the token or access or similar. Right? So most of those are happening through some some form of OAuth cache credentials. So, you know, hey. I'm gonna hit I'm gonna hit something like Poly. I hit Poly. It asks for my login. I log in. I authenticate. It saves that token. And now my agent that I created and bound up to that NCP has all of the same access I have. So if I have access to build, it's gonna give me, you know, all of the tools to build. If I've only got access to to read data or to get that, I'm only gonna get access to that. And so for us, like, we have a ton of financial data, invoice data somewhere, and it's all scoped basically on the user. So if a user can do it, they can do it within CP. If the user can't do it, they can do it within CP. If there's something scoped where they can only see certain sets of data, that's gonna be scoped to to how they their agent. So, basically, they're inheriting this their agent is inheriting the same security rules, policies, governance that is bestowed upon that actual user.
[00:17:24] Damian Sasso: Yeah. No. That that makes a lot of sense. Bobby, any anything else you wanna you wanna add there? Like, AI governance in the world of MCP is certainly like a such a such a a thing for every organization to think about. You know, any other concerns that, you know, you could advise, you know, our listeners on, you know, that you've looked into?
[00:17:43] Bobby Hunnicut: Yeah. I think we are being fairly progressive at Vixo in terms of, like, just nothing built beats speed at the moment. Let's try and build and just kinda push things and push people to try and use these tools. And and especially in terms of how we're trying to build our own internal MCPs that connect to our homegrown systems, We're essentially building as we go. We kinda push them to be out there. The users try and hammer it with what they're trying to do, saying, hey. I can't do x y z action. Great. Let's talk about that. Is that a quick add to our MCP to kinda continue the development and kinda get out of your way to allow you to continue to build and learn? Um, so we are definitely very much on the, let's just kinda see what happens and build fast. But I don't know if that's a a good fit for everyone, but it's what we're, uh, adopting right now.
[00:18:26] Damian Sasso: I mean, that's music to our ears. I mean, that's the same way we're thinking about things at times at PolyAI because the ability to use this technology to enable organizations is so is so exciting that that kinda makes sense from an approach. You touched a little bit on some of the things you're building internally. Where do you see the role of, like, REST APIs going in the world of, you know, more and more agent use of MCPs? I mean, we talked a little bit about humans using their agents, but, I mean, the beautiful thing about an MCP server is agents can use it that you've deployed, like, autonomous agents as well as humans. So where do you see sort of the role of REST APIs now in an organization from a development perspective with things like MCPs and agent development kits playing a role in, you know, continued updates and changes?
[00:19:15] Derek Neighbors: I think for me, REST APIs were still the foundation. Right? Like, at at the end of the day, the MCP still has to talk to something to interface. If you're gonna do CLI, it has to talk to something to interface. I I think REST has proven to be a pretty stable parabine for interacting with objects. Right? So I think kind of like the the this is a noun, and you can create, read, update, or delete that particular noun, and the way that it's nice and clean like that, I think when people have a nice clean REST API to extend from, you can tell that they have a nice clean MCP. They have a nice clean CLI because things are very segmented and very easy to deal with opposed to more of a graph or a SOAP type of mentality that's highly customized, that's a lot more difficult to deal with. Right? And it it really comes down to discoverability. Right? If you have good REST nomenclature, you can get away even with an agent to just point to it, and it will just try things because it knows the structure of a good REST URL and API. And it can do a lot without even knowing that there's documentation under the hood. So when you expose kind of that same kind of principles and thinking, and you kind of think of things as primitives, and you start to then expose your primitives as resources, and you start to to to do that and and cascade out, I think a good a good bare bones REST API that's well thought out makes it super fast for engineers to build MCPs and build CLIs to then take advantage of that. Right? So, I mean, I I think it's just you know, I I don't think they necessarily go away. I I think they still stay as a building block. I just think you're not gonna see as many people consume them directly.
[00:21:02] Damian Sasso: That's a good point. I I think the auditability of it, what we've leaned into, at least as we've developed out an MCP server that we were, you know, working and and and partnering with you guys on, was the was the thought of auditability around APIs and what APIs the MCP server was using, at least as a starting point. Is that something that's really been important, kinda, Bobby, as you guys have thought internally about internal tools? Because it's kind of a new technology, and REST is not a new technology, so you kinda get to bridge that gap of, like, still maintaining sort of the API auditability behind an MCP. Is that something to think about?
[00:21:39] Bobby Hunnicut: Yeah. I think what's what Derek kinda shared earlier, like, MCPs maybe are aren't the most efficient here. They're having to load a bunch of context in. They're doing a lot of discoverability what's there, but they allow the end users to kinda do things on their own. They don't need to physically know everything that's in that API or what it can do, and they can use natural language to explore and try and build what they want. Don't think REST APIs kinda go away. There's still a great foundational block. If you're trying to do anything at scale or anything that's really reproducible, REST APIs are definitely something that play a part absolutely, especially you wanna start refining these processes and bringing token costs and all that kind of stuff out of it. It's just another way of honing a process. Once you kinda have the business say, hey. This is what I want. This is what good looks like. Great. How do we take what good looks like and make it really, really proficient and efficient to run and cheap?
[00:22:28] Damian Sasso: So as you've kind of, like, really detailed some of the digital transformation that you've gone through at Vixo, enabling your workforce via their agents, you know, giving access control to agents that human humans had, building things internally. What's some stories that you have on some of the efficiency gains you've seen or some of the some anecdotes around it or just data that you've been tracking to show how much more efficient or much more in touch your workforce is, you know, as you've enabled them via agents connected to MCP servers?
[00:23:00] Derek Neighbors: Yeah. I I think just a lot of anecdotes of kind of what's possible. Right? So, I mean, I think one of the things that people get hung up on, probably wrongfully so, is looking at AI simply as efficiency. Right? And and what I mean by that is, you know, we we saw this in spades that the we we used to even tease around, you know, AI means, I I forget what automate the infrastructure. Right? Because, you know, when you look at when you look at so many of the processes that are out there, people's first inclination is I do a, I do b, I do c, I do d, and I run them in order, and I'm having to do a manual touch point in each one of these. And now I have AI, and I'm gonna automate that. Right? And let's use AI to automate. And we look at it and go, that that's, like, the worst use case of AI ever because it's super expensive to pull in context. Like, you're not doing anything special with it. You're you're literally paying a really expensive tool to pick stuff up from a, move it to b, pick it up from b, move it to c.
[00:23:59] Damian Sasso: You're almost just hitting an AI usage leaderboard at that point and not actually solving, like, the problem.
[00:24:05] Derek Neighbors: In what it's moving, it's the same stuff. It's like, okay. The subject line always goes from here to here. It's like there's no there's no logic, there's no nuance. It literally is like, I wanna map this data. Right? And so we started to say like, woah, woah, time out. Like, we need to start to separate what's automation versus what's AI. Right? And and so what we've started to kind of say is AI is really fantastic to do automation that you don't have to wait for engineering on to prove a point. Right? So if you wanna go a, b, c, d, e, and automate that and not have to go get engineering's backlog or have, you know, big product to get you to the top of the list or whatever. You can go do that. Right? And you can start to show, like, hey. Look. I saved a bunch of time by automating. So I'll give you a great example from us, right, is, you know, invoices. Right? So invoices come into an email box. Somebody from accounting was kinda picking those up, looking at those in a folder, dragging them from one folder to another, opening them up individually, copying and pasting them into an Excel spreadsheet, then loading that spreadsheet into another tool that then put them into invoice processing and then verifying that they processed out into the accounting system. Right? So, like, five touch points, a lot of, like, dragging or but no intelligence involved in literally mindless moving stuff from a to b. Right? Hey. Great. Use AI to automate that. Now you're out of that business. You're you're not having to do that anymore. You got efficiency. Right? What used to have 300, you know, invoices a day in the backlog or 3,000 invoices a day in the backlog, and you struggled to keep your head above water between four people, now that's fully automated, cradle to grave. Nobody's spending any time on that other than the final reconciliation piece. That's fantastic. Right? But it's not really a fantastic use of AI. And so what we've started to say is do use AI to do those type automations. Let us know where it's working and going good. And what we can do as engineering now come back and say, okay. Great. What does it look like us to take the token spend out of that, right, and start to then make it efficient? Right? So so we gave you some productivity gains, but we didn't really get a whole lot of efficiency because the reality is your time and the time you're spending that might be pretty close to what the token spend is. Right? So at the end of the day, it's like we just we we gave you more capacity, but we exchanged that for a token spend that that may have been similar to the cost of of you involved. But what it does is it allows us now as engineering to come out and say, like, hey. Could we just do this all through back to REST APIs? Can we just do this all via REST APIs and some lightweight glue and basically pull that out of the system and get the token spin back? Absolutely, we can. Right? And so we're we're starting to see that the real, like, power anecdotes of things are the things that really didn't scale well as humans, right? There's some nuance involved in what's happening to where a typical automation couldn't occur. I'll give you an example is, you know, we we basically didn't get a service request in. That's that's a work order or whatever you wanna call it. And my ice machine is done. Right? Ice not dispensing. I'm Circle k. I have a the drink cooler. It's, you know, a 108 outside, and nobody can get ice out of the ice machine, and my water fountain's down. I need help. And we're gonna dispatch somebody. It's with that, some automations already built in to go determine who the best person dispatch is for, you know, the best provider to dispatch for that, everything about that. But the reality is there's so much more to that. There's the facility that you're in, right? So I'm in the Circle K, I'm at this particular location, and I've got all sorts of data about that. Every service call that I've ever done in that Circle K, I have information about that. Every asset, so the air conditioner, the coffee maker, the ice machine, the beverage machine, the walk in freezer, the POS system, all of those are assets that I have a bunch of information on from either a telemetry perspective or from a service perspective of what's happened in the past about those machines. Right now, an SR comes in. I'm just servicing that SR. I'm looking at that asset, that work request in that moment in time, and everything else is blind to me. Right? So we're able to turn on that the service request comes in and I go to look at all of the history, let's say in the last ninety days around that facility, around all the assets in that facility, and around all of the service providers that has touched something in that facility. And I'm able to create an intelligence packet about how that should impact dispatch. Gives you a great example within that. That the ice maker is broken. It's on a beverage machine. We auto route and it says route out somebody to fix the beverage machine. K? That that's what happens by default. That's where our system goes by default. This agent picks it up and says, woah, woah, time out. You've had two toilets clogged in this facility in the last sixty days. This is the second time you've gone out with a beverage to a beverage machine. I don't think that this is actually a beverage machine problem. We think you've got a clog somewhere in plumbing down line. You need to make sure you don't send out a beverage person. Instead, dispatch out a plumber. Make sure that that plumber has a camera on their truck. They've got a water jet on their truck, and there's two people on the truck. So if they have to water jet it, they have two people to do the water jet, they don't have to come back for a second call. Turns out, they show up, sure enough, 20 feet down the line, there's, uh, a problem, they have to water jet it. In the past, that would have been we sent out a beverage guy. He clears it, says it's all good. Five days later, we get another call, but it's stuck again. We then send out a plumber. Plumber's gonna camera it. They say, yeah. There's something pointing down there, but I don't have a water jet on me or I have a water jet on me, but I don't have another guy. We're gonna have to come back in two days. Right? The the meantime, the actual moneymaker for this Circle k is a beverage machine that's no longer in dispensing ice. Right? So then that's kind of a real world, like, nuanced way that that we can look at that. And underneath the hood, there's all sorts of MCPs involved within that, looking at all of our systems, looking at our invoice system, looking at our asset system, looking at our, you know, prior work order, looking at our facility, looking at the customer, looking at the service provider, and kind of gluing that all together. That whole system was not written by an engineer. That was written by an operations person with skills.
[00:30:02] Damian Sasso: That story is an amazing story in a sense that, like, that use case is amazing because it really touches on, I mean, the value of, like, a solution like a like what we offer with PolyAI, where you're using an agent, a voice agent, chat agent, like a customer service focused agent, um, that you can now connect to a number of systems to think through intelligently in a way that just a human being answering a phone would not necessarily be able to connect all these dots as quickly as agents can as to what's truly the issue at a client site. Not, you know, just a beverage machine, but you have a plumbing issue that's actually gonna cause three additional service calls as opposed to being hit, you know, in a single in a single service call. Something that I wanted to ask both of you as we kind of put a bow on this this conversation was, you know, you're you're in an industry that, to the average person, might be perceived as not, like, you know, as as a blue collar service industry, but you're thinking about things in such a technically advanced way. We're very excited that you're a client of ours and excited to continue to work with you on things like what we've done with our PolyIM CP server. What should CX leaders elsewhere in other industries be thinking about over the next twelve to eighteen months as they think about either, you know, their industry, if they're in a service industry, and another? Because in my eyes, you guys are at the forefront of tech of thinking about the right way to implement AI technology. You know, Bobby first and then, yeah, Derek, just would love to hear your thoughts on that.
[00:31:33] Bobby Hunnicut: Yeah. For kinda calls back to what I stated earlier. Like, MCP and CLI availability is now the litmus test. If there are key platforms that we have at this business that don't have those connectivities, that is probably the step one of me either looking to solution that, trying to build our own MCP, or two, how do I pivot to either a custom solution or a new solution that has those capabilities? I cannot condone or tolerate having those type of really key systems that don't have connectivity with our agents because it's just gonna put blockers or friction points for trying to roll this out in the way that we want to. So look at your systems. Look if they have MCP access. If you don't, how do you engage with your vendors to see if that it's on their road map the same way that we engage with PolyAI? Said, hey. Do you guys have an MCP? At the time, you did not. We offered to kinda write our own, but we wanted to use a first class one from you guys, and you guys built one. Like, that's a great partnership to have. So I would if you don't currently have MCP access for those key systems, reach out to that vendor to see if if that's on the road map. And if not, maybe adjust your thinking from there.
[00:32:32] Damian Sasso: Derek, yeah.
[00:32:33] Derek Neighbors: I think for me, you know, speak direct to the CX leaders out there, right? And it's like, no matter how fast you think you're going, you're not going fast enough. I can't express this enough to my peers. This technology is moving faster than anything we've seen ever by a factor of 10 or 15, and you can kind of look at it in one of two ways. One way to look at it is it's going too fast. I'm too afraid of it. I'm just gonna wait in until it shakes out and and there's a right answer, and I'll adopt that right answer. And and a lot of times in the past, that's been a pretty reasonable way to look at new emerging technology. Unfortunately, in this wave, I think those that are not riding with the wave aren't gonna have a place anymore. Right? I mean, this is the the the kind of the separation that it's putting between companies is so gap oriented, I don't know if that can be closed. Right? And so I think the the biggest thing that happens in organizations that I see is it becomes a governance hell. Right? Everybody is afraid around, like, what what who do we give access to what? How do we do this? And how do we control? How do we and I'm just gonna say, if that's dominating the conversations in the room you're in, you're not gonna make it. Um, that's not to say governance is important. That's not to say that that that they shouldn't be having those conversations. It's it's it's dominating the conversation. Like, if that is if if that is the thing that is where the focus is right now instead of on learning, it's gonna be really rough. And and part of that is, I think, for the first time, there there are executives has to understand how things work at a deep level. There is no more manager or leader and somebody's an individual contributor. We're seeing CEOs, CTOs of the top companies in the world right now be hands on being individual contributors to how these things work. And I'm gonna say as a CX leader, if you're not in getting your hands dirty with this technology, you're not gonna understand where the opportunities are for your organization and for your industry and your market, and the window to take advantage of those is not gonna be really, really strong without getting lost or getting behind.
[00:34:56] Damian Sasso: That's that's great that's great insight. And, I mean, like, from our perspective, you know, we've really enjoyed the partnership with you and your team on building out, you know, building out the MCP for our agent studio platform. We don't see it as just a release or a tool release, but it's kind of a shift in the way that our customers develop, you know, both you you guys integrating and and working with the PolyAI Agent Studio platform. But even since we started building out our initial MCP, we brought more functionality, rethought a lot of things that we know need to be included there, auditability that needs to be there, and we've been you know, we've seen increased interest as well since we put out documentation and and and started to talk more and more about it. And it's just things are moving so quickly in in all industries that, as you touched on, Derek, it's important for even executives to be kind of in the weeds understanding how technology is is transforming their workforce. So, you know, it's been an absolute pleasure to have both of you on the show today. You know, Derek, Bobby from VCSO Facility Solutions, Derek's CTO, Bobby, VP of Information Technology. For everyone that's listening, I encourage you to like, subscribe, you know, stay connected, and this is, you know, another edition of deep learning with PolyAI. Thanks again.