Behind every successful enterprise WhatsApp bot is a lot of unglamorous, practical design work. In this episode of The Dialogue Architects, host Lauren Goerz talks with Nick Thomson, General Manager of Got Bot, about what it really takes to design and scale WhatsApp bots that handle real‑world volume, complexity, and operational risk—far beyond the GenAI hype cycle.
In this episode of The Dialogue Architects, Lauren Goerz sits down with Nick Thomson, General Manager at Got Bot in Cape Town, to unpack the realities of building and scaling high‑volume bots for commerce, support, and automation—especially in markets where WhatsApp is the primary customer channel.
Nick shares his journey from account management into NLP, APIs, JavaScript, and ultimately Python/Rasa, where hands‑on experimentation taught him how dialogue systems actually behave in production. Today, he leads teams that must balance generative‑AI client expectations with the real engineering work: reliable integrations, multi‑step workflows, rigid flows, regex‑based routing, fraud checks, and failover plans when client APIs or websites buckle under load.
Lauren and Nick dive into the architecture tradeoffs behind enterprise automation—fast vs. cheap vs. complex—how to design workflows that survive message‑volume spikes, and why diagramming in tools like Excalidraw or Miro remains the only reliable single source of truth across internal and client teams.
They also explore multi‑bot orchestration, agent‑to‑agent handoffs, the challenges of WhatsApp/Meta governance and bans, and Nick’s prediction that by 2026, companies will lose patience with autonomous agent failures and demand measurable ROI, stronger security, and far more system discipline.
A grounded, practical episode for anyone designing or governing real‑world conversational systems at scale.
About the Guest
Nick Thomson is the General Manager of Got Bot, a leading conversational AI and messaging automation company in Cape Town. With a background spanning account management, NLP, API integrations, and hands‑on Rasa development, Nick specializes in designing and scaling enterprise WhatsApp bots in one of the world’s highest‑volume messaging markets. At Got Bot, he oversees teams responsible for automation in retail, logistics, and commerce, balancing GenAI innovation with reliable workflow‑driven design. He is known for his practical approach to architecture, diagram‑driven collaboration, and governing multi‑bot ecosystems across brands and departments.
Episode Timestamps
(00:00) Welcome and guest intro
(01:08) Nick’s origin story
(05:32) Role today and GenAI reality check
(06:59) WhatsApp commerce and scaling
(10:31) Project priorities and workflow design
(13:49) Diagramming with Excalidraw and Miro
(18:14) MCP and agent orchestration
(25:21) Customer war stories and ops challenges
(29:42) Metrics, feedback, and containment
(31:24) 2026 predictions and wrap‑up
Links & Resources
• Nick Thomson – LinkedIn
• Lauren Goerz - LinkedIn
• Got Bot
• Learn more about designing trustworthy AI at Rasa: rasa.com
About The Dialogue Architects
The Dialogue Architects is a podcast from Rasa, hosted by Lauren Goerz, exploring the craft and strategy behind designing conversational AI in the enterprise. Each episode brings together technologists, designers, and product leaders to unpack how dialogue is built, scaled, and governed in real‑world systems.
[00:00:00] Lauren Goerz: Welcome to the Dialogue Architects, where we explore how enterprises can thoughtfully design, scale, and govern conversations between humans and machines. Today we're joined by Nick Thompson, who's joining us from Cape Town South Africa. The current general manager of Got Bott, a company that's actively consulting big brands today with our agent AI projects and on LinkedIn, a self-described bot overlord.
[00:00:19] Lauren Goerz: Nick, welcome to the podcast.
[00:00:36] Lauren Goerz: Hey, Nick, welcome. So excited to chat with you. I feel like I've seen you in the broader, conversational interspace, uh, space for a long time now, and I'm, I'm really keen to kind of hear about your story. One of the things that I love about your experience is you have a lot of. Hands on, key board experience with customers and high level kind of project management experience.
[00:00:55] Lauren Goerz: So you've really experienced all of the different roles that kind of exist in these types of projects. And I'd love [00:01:00] to hear, really, just to kick off today, tell me your origin story. Where do you come from? How did you end up in this space? What did, what did it look like? Your journey to here?
[00:01:08] Nick Thompson: Thanks so much, Lauren, for the intro.
[00:01:09] Nick Thompson: It's really nice to be chatting to you. Um, RA has really been a special part of my journey, but in a very quick nutshell, I was running away from sales for a very long time, and then six and a half years ago I started a job, uh, at got bot as an account manager and handling a lot of the on the ground requests.
[00:01:26] Nick Thompson: It started very quickly with, um, really jumping into natural language processing and playing around with intents and training phrases and responses. Then one very fateful day, uh, colleague, a senior colleague of mine asked if I could update an API call for one of the servers that we were talking to, to fetch information, to display to the user.
[00:01:47] Nick Thompson: And in that moment, I wasn't even sure what an API was, to be honest. Um, but I thought, look, I'm running away from sales, so let's, let's go as deep as we can into the technical side of stuff. And basically from [00:02:00] that, that was, that was really the beginning, I think of my. Understanding that there's a limitation with building bots if you don't understand how to write code, which can interact with APIs.
[00:02:14] Nick Thompson: And basically, for me, they're learning what I needed to with JavaScript with Postman to then, um, basically building those APIs and then. Seeing really where that went because I mean, a lot of bots just needed APIs. So if you can figure out the way to get the information safely and then show it to the user, it's really quite a copy and pastable exercise.
[00:02:34] Nick Thompson: So that was the start of me jumping into, into the configuration side of APIs with bots. But my. Deep love, I think actually came from NLP and, um, actually interacting with the Duckling en entity extractor of RAs a long time ago because, um, as soon as I learned how to write the JavaScript of how to, uh, talk to the APIs and veg the information, the next thing I wanted to do was [00:03:00] figure out how I could build and work on something locally, because the issue is.
[00:03:03] Nick Thompson: All of our stuff was in the cloud and you can't exactly build a bot locally and do the thing. So the best way for me to learn about bots was actually first figuring out how to install ZA locally on my computer, and then playing around all the different types of config because we were in a place where we were trying to move from an old type of tech into the new, new type of tech.
[00:03:23] Nick Thompson: And there's so many cool things that Raza did that's we were thinking about. Okay, cool. Let's try and embrace some of these things. So. Learning Python was actually purely to run Raza, and then I was so excited as soon as I got my action server phishing, real live weather information. And I think that's the cool thing with bots is it's actually very satisfying.
[00:03:42] Nick Thompson: Once you, you, you start at the very simple idea of what it can do and then kind of incrementally making it better and more impressive and seeing where the failures are and fixing them and. Yeah, I mean, fast forward a few years later, I just spent a lot more [00:04:00] time training teammates to do certain things so that I didn't need to do all of the on the ground work.
[00:04:05] Nick Thompson: And now I spend a lot more of my time making sure that when we are talking to clients or when clients are asking for certain, uh, things to be done, that I, that we are very clear about what is being asked for, because the, it's very easy to misunderstand. Um, what is being requested and then to potentially even build something that isn't being asked for.
[00:04:25] Nick Thompson: So trying to make sure that we actually are aligning on what the intention is because there's 50 different ways that you can accomplish the same thing, and trying to just do it in a way that is gonna provide return.
[00:04:38] Lauren Goerz: Yeah, I think that's something I've noticed more today than certainly two years ago is, is how many different ways there are to kind of scramble an egg.
[00:04:48] Lauren Goerz: I mean, you could, before there was really only so many options and, and you really pulled some, some good bits and pieces out of the Raza archive there from, from, uh, duckling to, you know, intent management. Those, you know [00:05:00] now I think, um. Folks that are coming into the space from the ent ai arena definitely would, would look at those words and think, wow, y'all are a bunch of dinosaurs.
[00:05:08] Lauren Goerz: But they're still active in projects today, here and there. Yeah. Um, nonetheless, I think, um, it's fun to hear your story 'cause I think that's, that parallels very much my experience as well. Very cool. My kind of, uh, dive into the technical universe really began with, began with Raza as well. I came very much from kind of the drag and drop UI based world of building conversational interfaces.
[00:05:27] Lauren Goerz: And then with Raza. You gotta move it locally. So I think that was, that was also a part of my journey. Either way. I'd love to, maybe just to ground our conversation today, I'd love to learn a little bit more about your current job role today at Got by, what are you, what are you working on? What's your day-to-day activity?
[00:05:42] Lauren Goerz: And then we can dive in because I'd love to hear a little bit more of stories from the field, things that you're doing with customers today.
[00:05:48] Nick Thompson: Yeah, it's trying to build, it's, it's quite a complex. Quite a complex, um. Roll just because there's [00:06:00] re requests, for example, where, um, there's technology that's flashy, like large language models, which everyone wants to have an element of generative AI in their workflows.
[00:06:11] Nick Thompson: And there's great places for the generative ai, but there's also really great tech in place long before generative AI that can do the exact same job with benefits or more rigid workflows. And so what I do find myself. Doing quite a bit of is tempering down the beliefs of what Gen AI is actually capable of.
[00:06:32] Nick Thompson: Because the reality is we've got some excellent workflow mechanisms that don't require any type of gen ai. A lot of the time it can just be number selections or Reg X based or whatever. We don't need to always talk to the generative AI to make the decisions. So I find myself quite a bit, um. Building some really exciting fraud detection things, but then also having to communicate the limitations of what the tech can actually do.
[00:06:58] Lauren Goerz: Yeah,
[00:06:59] Nick Thompson: and one of the [00:07:00] interesting things is just, um. With, in South Africa, there's a, there's a huge focus on WhatsApp for mobile commerce. And what, what we really find ourselves doing is trying to connect clients who have very high workflow needs. So one of our clients, for example, had so many, um. Tracking order requests as phone calls that were very expensive for them, that as soon as we converted that to a link or a chat bots workflow, that then they could put their tracking order in and then find the information.
[00:07:31] Nick Thompson: You could very clearly see the increase in, uh, bot workflows led to a very serious decrease in phone calls. So it's not very glamorous a lot of the time, but it's trying to find pain points where. For example, one of the companies that we work with has very complex routing for certain users. So, um, there's one bot that you can go to, but there's.
[00:07:56] Nick Thompson: Essentially 50 different groups that could be coming to the bot. And each [00:08:00] user has a different group and different groups have abilities. Certain groups can speak to agents, certain groups have different benefits. And really building this, uh, menu that can be used by as many people as possible, but also being very accustomed to that specific user.
[00:08:15] Nick Thompson: And one of the interesting things is we just find a lot of clients wanting is to still work with number menus instead of button menus. Mm. Or some, some, some industries works really nicely with, um, uh, button menus that you can kind of navigate your way through. But what we're finding is that number menus.
[00:08:31] Nick Thompson: Seem to be safe for some things. And, um, building those self-service menus has actually been very helpful for a lot of our clients. Because last year, for example, um, we were expecting, I mean, I still get the numbers right in my mind, what there were, but we were essentially expecting, I think it was something like 10 million messages over the course of a month.
[00:08:56] Nick Thompson: And we received something like 20 million messages in the [00:09:00] first three days. So we had a very, very, um, and the network that we have is excellent, but essentially we needed to scale our systems very quickly to handle the volume because if we didn't scale the systems and there'd be massive delays and the issues that, and it became like a media thing where essentially if we weren't gonna handle it digitally, there's gonna be a problem on the ground for the client.
[00:09:22] Nick Thompson: So there's a lot of the time, um, very tense deadlines on resolving problems. Um. Some of the really exciting thing, actually, maybe just another side of it that, um, is just touching into, um, the workflows and marketing mechanisms from adverts to workflow to, um, interaction through, uh, WhatsApp as a channel.
[00:09:48] Nick Thompson: That's something that's been quite, uh, cool, where we can essentially, um, send, send out broadcasts to users and help clients manage, uh. Lists where they can interact with their users. [00:10:00] Um, and a product catalog following is, uh, following WhatsApp.
[00:10:04] Lauren Goerz: That's exactly kind of the similar build pattern that I'm seeing starting to emerge, is that you have this kind of like generative fallback and then.
[00:10:11] Lauren Goerz: Once you figure out those core use cases, pulling them out and, and making them slightly more, let's say formalized, whether that be in, in, in the, if I'm using the word formalized, because I think there's lots of ways, you know, it doesn't necessarily have to be entirely hard coded, but there's, there's lots of different ways to do that.
[00:10:27] Lauren Goerz: So I think we're, we're seeing a similar pattern with, with some of our customers over here as well. I would be curious, especially as we're talking now, we're talking about like. Dialogue, architecture. I think one of your jobs when you're, when you're serving your customers, ultimately is to help them set up that, that architecture, you know, deciding when to use what, where.
[00:10:43] Lauren Goerz: And that's actually, I think, becoming one of the most interesting challenges in the sphere today because there's no, there's no rules necessarily, but you have to do it this way or that way. How do you, how do you approach these challenges with your customers? You know, where do you even begin? How do you start to set up these projects?
[00:10:57] Nick Thompson: Well, it really [00:11:00] simply will come back to what is most important a lot of the time, and that can be answered by what is most important. It being very quick, it being very cheap, or it being very complicated. And then usually you can find, okay, we want it to be very complicated and we want it to be built by tomorrow.
[00:11:17] Nick Thompson: In that case, the third option, which is price is slightly negotiable. So, um, it's really trying to figure out like, is it, is it a complexity thing? Because then we need to really work around testing and then iterative launching because, um, launching something which has four modules of complexity and testing them all at the exact same time is asking for, it's a QA nightmare.
[00:11:38] Nick Thompson: Just trying to align with the testers, aligning with the team who's making the changes, making sure that everyone's testing the, the latest version. Um. Yeah, I think the, I think trying to agree with me, trying to understand is the timeline the most important? Is the complexity the most important? And then really mapping it out because I think that that's, [00:12:00] that's something which I thought to a certain extent AI would solve by mapping it all out.
[00:12:05] Nick Thompson: But the thing is, what I'm finding is a lot of it is actually still very hard coded because it's not like with an API, for example. You can only really speak to the final API once you've gotten all the information from the previous steps. You can't just go to the last one first because there's a very specific process for, you need to check a few things before you go to that step, before you go to the next step.
[00:12:27] Lauren Goerz: Yeah,
[00:12:27] Nick Thompson: and I, I just. I've seen a little bit with the generative AI implementations that we have is that's multi-step workflow. Understanding is just not there, and the reality is that's where the biggest value is, is getting four pieces of information, handing it over to an agent, sending that closed ticket information into their fresh desk or into their Zendesk or whatever it is, so that the loop is closed.
[00:12:51] Lauren Goerz: Absolutely. And I think that's actually what you just mentioned is something, a similar theme I've noticed with lots of, uh, different practitioners, I'll say, that have been in the [00:13:00] conversational interface space before. Let's say the ent AI revolution is all of us are kind of waiting to go back to these first principles of, hey, we, we were building conversationally ai so it could do stuff for users, not just give them a paragraph of text.
[00:13:13] Nick Thompson: Yes,
[00:13:13] Lauren Goerz: exactly. I think, I think that's, that's, um, the thing that I feel like we, we all need to collectively keep fighting for is like, at the end of the day. We want these things to actually do things for users. We don't want, you know, just, just telling them how they could do it themselves doesn't always solve the problem.
[00:13:27] Lauren Goerz: Um, so they've really taken self-service to the, to the next level there in terms of, you know, figure it out all yourself. Nonetheless, I would be, I'd love to dive now layer deeper. So once you've kind of figured out. Your, your project, um, you know, I think, I think you said fast, cheaper, complex. Pick two.
[00:13:43] Lauren Goerz: Once you get to that level, what are some of the things that you're noticing in the way that you set up projects today? Has anything changed or is it pretty much the
[00:13:49] Nick Thompson: same? Uh, one of the things that has been the most amazing implementation is using a tool called Xca Draw, which is a completely free tooling.
[00:13:58] Nick Thompson: Um. I [00:14:00] mean, I wonder if I can maybe open one of these things up here, but essentially just using Xca Draw as a way to draw out the full diagrams so that the entire team is on the same. Yeah. So this, do you
[00:14:13] Lauren Goerz: mean like uh, full diagrams or kind of, or are you talking about mapping out the architecture of your project?
[00:14:18] Nick Thompson: So this over here. Okay. Maybe, I dunno if you're gonna be able to see the whole thing, but this is just mapping like a validation flow.
[00:14:28] Lauren Goerz: Mm,
[00:14:29] Nick Thompson: so it's like full
[00:14:29] Lauren Goerz: diagram.
[00:14:30] Nick Thompson: There's multiple steps where, um, it has to check previous and then building different menus based on certain variables that have been set.
[00:14:39] Nick Thompson: The, the thing is that we need to have a digital mechanism, and usually Miro actually works quite nicely as well. I've noticed a lot of people use Miro because it's really good for collaborate, collaboration, and then, um. Can you, can you still, can you still see me? I'm seeing it stuck. Okay. There we can see everyone moving again.
[00:14:59] Nick Thompson: So [00:15:00] the, the most important tool really, I would say is the drawing diagram. So that's what we are scoping and what we finally build are, um. Uh, prototypes at a very early stage and something like Miro is really helpful because you can, um, prototype what the whole flow should look like, make copy updates there, and that can be the single source of truth that the devs then can also use for the latest version.
[00:15:24] Nick Thompson: Um, that diagram has probably been the biggest, uh, value for us because it shows the teams that we work with. How complex the tech is, but also what can be done. So usually what happens is as soon as we start drawing the diagram out, the internal team realizes Sherbert, we are stuck. We need to build a system internally so that the bot can then do the thing it actually needs to do, and then they end up building their systems so that then we can pass the information back to them.
[00:15:57] Nick Thompson: So what's very helpful is when we [00:16:00] are doing the diagrams and we are drawing and we are plotting, um. Their own teams are part of the process. And then the technical teams start to very early see, they, they need to now work with their marketing team. The, the dev team has to work with the marketing team because, and that's the issue that we we're sometimes seeing is that there's so many different.
[00:16:21] Nick Thompson: Teams that are trying to collaborate with one another that it's very easy to miscommunicate or type up a very long email that no one reads that has the set of instructions right in the middle of the email that everyone missed. Um, try, I think the, trying to just make sure on a diagram level, this is what we are doing.
[00:16:40] Nick Thompson: Is this, are we all on the same page? Because that's, I think where the team starts to see, okay, we can break this down into different, um. Uh, kind of timelines and then just tracking all of that and the communication back through, um, this is where we at, because sometimes the progress doesn't look very quick because you're building architecture or [00:17:00] you're getting APIs connected and there's actually backend work that is needing to be done before the bot can give the answers.
[00:17:06] Nick Thompson: But I think the most important thing is with that diagram, what it usually does is it's. Pulls everyone to the, this is what we are trying to actually accomplish. So without that, I think we've probably, as soon we, as soon as we implemented that, we saved massive amounts of times, a massive amounts of time because there's far less backwards and forwards and trying to see what we're actually talking about.
[00:17:30] Nick Thompson: It's quite clear on the collaborative documents.
[00:17:33] Lauren Goerz: Yeah. That would also be my recommendation to anyone that's, that's building a conversational interface. Today is at the end of the day, you need one single source of truth. No matter how hardcoded or how agentic it is, you need some kind of overview of the different user journeys that are available to your users, even if one of them is a long tail search.
[00:17:51] Lauren Goerz: Put it on a piece of paper so people know that it's there. Because once these agents start sprawling into different teams and different subject matter experts and different [00:18:00] development teams backend, it, it becomes impossible to keep track of all of it. So I think that's, that's for me also, I think a very consistent part of being a dialogue architect at the end of the day is, is having these, these single sources of truth.
[00:18:12] Lauren Goerz: I think this is the case for any vendor that's working in this space. A lot of your roadmap today is driven in many ways by customer demand. Um, and, and I think. We've got customers that really wanna use it, and it does solve an organizational problem. I think MCP at the end of the day, someone still has to build all of these integrations.
[00:18:26] Lauren Goerz: Exactly. But having a protocol that unifies them in one place is an organizational solution. So I think MCP, it solves an organizational problem at the end of the day. It doesn't, it doesn't Revolutionarily. It doesn't change the fact that you still need to build all of these integrations. Um, and so at the end of the day, our customers still wanna use it and I think it does add some efficiencies to, let's say, types of tool calling that you might have within an agent.
[00:18:48] Lauren Goerz: I think for me, what I think is even more challenging than MCP is actually a to a so agent to agent protocol because at the end of the day, now you need to reach out to an external agent, which is [00:19:00] entirely a black box. You have no internal controls over. What that agent can do and the types of things that it can send back to you.
[00:19:06] Lauren Goerz: So I think for me, that's where I see MCP, for me, at least in some ways could be guarded within an organization. But as you, as you mentioned, once you think about MCP servers for vibe coders, people that are, you know, actually generating code and. Frankly, people like myself who, you know, I'm not, I'm not a, a studied developer necessarily.
[00:19:24] Lauren Goerz: I just happen to have peeled the onion back far enough that I end up in, in, in an IDE at some point. Um, so I think, I think there's definitely gonna be a lot more people like me who, who probably don't have the know-how to immediately say, Ooh, this is a dangerous command to be running right now.
[00:19:39] Nick Thompson: So when I hear agent to agent, what we are trying to solve is, if you imagine like, uh, Nissan, South Africa for example, they have a global, they have uh, South Africa bots.
[00:19:51] Nick Thompson: You go to the South Africa bots. But what would be really awesome is if, um, there was a ability for the agent down the streets over here, or the [00:20:00] agent who's in the middle of the upcountry with very. Very little, um, infrastructure around them. Would it be possible for us to potentially hand a user who is talking to the main bot over to an agent who is, uh, offsite, potentially on a different location?
[00:20:20] Nick Thompson: Because the, the workflows within got bots. Uh, we are seeing. Is a need. There's, there's definitely always a need to connect humans to other humans, but sometimes the needs far more granular than just, uh, I need to talk to a representative of, of South Africa. It could be something down to, I need to talk to the person who's in my five kilometer vicinity.
[00:20:42] Nick Thompson: Um, and being able to route the conversation to a much smaller network. So trying to figure out how we can build an architecture, that's what I mean by agent.
[00:20:53] Lauren Goerz: Are you talking live agents then? This is always the vocabulary challenge? Yes. Yes. Okay. I'm talking yes.
[00:20:58] Nick Thompson: Yes.
[00:20:59] Lauren Goerz: Agent [00:21:00] meaning, yes, let's call it bot.
[00:21:01] Lauren Goerz: Bot to bot, yes, that's what I was talking about, agent to agent. I think that's cool. That's another piece of the puzzle I would say in live agent. To live agent is another piece of the puzzle. But I see what you mean. Having that, that local, especially in south, I mean, how many languages do you have in that country alone?
[00:21:16] Lauren Goerz: So many. I can imagine the local, the level of localization that you would need to provide to provide a good service is, is quite high. So, um, I can see that being huge.
[00:21:26] Nick Thompson: What you just said about the bot to bot is, is within Got bot. There's definitely a huge focus on agents, but there's also that the, the bigger South Africa to the more granular regional.
[00:21:41] Nick Thompson: Bot to bot as well, which that's not at all in, um, it's not at all in production, but it is something that, um, that's the next thing that we're solving with our release that is coming out in February next year. So the, the basis of that is to, uh, it's being built around that. The, the [00:22:00] bigger node to the smaller branch is being able to, uh, essentially do a workflow, not just within one bot, but being able to orchestrate.
[00:22:09] Nick Thompson: The actually the handing of the par, the parcel of information between the one bot to another bot connector that could be in there as well. I mean, it's the same thing. It's just where do you store that wallet of information, which is the context that the bot then answers its questions from.
[00:22:24] Lauren Goerz: That's, that's an interesting, though, it's an orchestration, uh, challenge that's bubbling up, I think more today than yesterday because now we have, like, what we're seeing at customers is not necessarily like.
[00:22:35] Lauren Goerz: Let's say there, there is this bot to bot element where maybe you're a car financing bot in your bank and you wanna be able to connect to the dealership bot. You know, there's kind of that, that kind of use case. But on the flip side, I think we're also seeing across an individual organization. Lots of different individual teams are getting budget to work on agents and building on different vendors, building on different systems, building with different goals, and I think that's the [00:23:00] really interesting orchestration problem that's popping up that we're really trying to solve for here at Raza is how do we make this all.
[00:23:06] Lauren Goerz: Behave like one unified customer experience. So that end user does not have to chat to five different agents that are branded differently, have a different voice and, and unify that. And that's, that's actually a pretty tricky technological problem. 'cause all of them have context. Some are more agentic than others.
[00:23:24] Lauren Goerz: It's, it's really, um, a challenge. And I think that it, but it's an interesting one nonetheless. And I think that's where, again, this whole theme of dialogue architecture comes in. How do we set this up and document it?
[00:23:33] Nick Thompson: I think the. That is such a important thing. One of our most, one of our clients this year had that exact problem where their problem from a brand perspective was that they had, each of their own departments almost had their own bot with their own branding and their own style.
[00:23:50] Nick Thompson: And the issue is that they don't, they needed the, they needed experts to really guide them on like, what is the [00:24:00] best way that we could pull them all into the same thread and then accomplish. Multiple goals through the same thing, instead of trying to each do their own little thing and then only touch 2% of the audience.
[00:24:13] Nick Thompson: So we definitely are seeing that that's a really big thing. 'cause I think the what's I think that's happening because. Company departments are becoming a lot more connected. And I mentioned that earlier just with, um, marketing and advertising and marketing teams are seeing I can automate things and then there's the in-house teams, which are, we need to somehow find a way to handle the volume of things that are coming in.
[00:24:39] Nick Thompson: And there's the two different sides of this. And I think that what we're at least seeing is that there's a lot more internal communication where there needs to be alignment. And where we find ourselves sometimes having to be the mediator between internal teams saying, Hey, we see what you're doing here.
[00:24:55] Nick Thompson: We're seeing what you're doing here. What happens if we brought you guys together and did that? [00:25:00] So they, and that's where the diagrams come in, is we say, okay, well, who's side wins? Let's go this way. What do you think? And it's really just this negotiation. Yeah. Internally with the clients, with them saying, we want to do this thing, and then just really using us as the sanity of That's a great idea.
[00:25:16] Nick Thompson: That's a bad idea, or, that's excellent. Let's do that more.
[00:25:21] Lauren Goerz: And what I, what I'd love to hear from you, um, Nick, in the next kind of section is like, if you have any really good, compelling stories about things that went wrong that you solved, or interesting problems that you've had, I remember you talked about empathy.
[00:25:32] Lauren Goerz: That might be an interesting one. Um, and I'll kind of, uh, tee it off here slowly and let you mul it over a little bit. But, um, Nick, I, I'd really love to learn kind of to, to close out the session today as well. I'd love to learn. About some of the customer side stories that you've had recently, you know, things, challenges that have popped up that are either new or you had to work hard to resolve.
[00:25:54] Lauren Goerz: What, what's been challenging that, that you've been working to overcome? [00:26:00]
[00:26:00] Nick Thompson: I sure.
[00:26:04] Lauren Goerz: Or everything's been easy, that's also good.
[00:26:07] Nick Thompson: Most of the problems that are, and this is something that you probably can't even air, is, it's like really tiny things. Like one of our biggest issues in the last two weeks is talking to a client who's having the default fallback in 10 to get hit less than 2% of the time.
[00:26:23] Nick Thompson: So we're haggling over how to make the final 0.5%, so it's slightly better. And this. In their mind is quite a serious problem and it's trying to place the success of, but it's successful 97.5% of the time. And trying to communicate that in a way, again, it's a communication thing of how we then can provide feedback.
[00:26:45] Nick Thompson: 'cause I think that that's the most important thing as well, is being able to. I very quickly see data that's, that's something that's been very helpful for us. Black Friday for example, is we had a retailer do a Black Friday special through [00:27:00] WhatsApp and us very quickly, their website took too much strain, so we needed to very quickly cancel the broadcast because we didn't wanna send more users to the websites if the website's done.
[00:27:11] Nick Thompson: Um, so that, that's the, the quick turning around of working with third parties, like WhatsApp or, um, business solution providers is really a bit of a, the, the types of problems that we have, Facebook accounts, um, us needing to, uh, do the correct. Process of, um, applying for a WhatsApp number, getting it connected to the user's.
[00:27:36] Nick Thompson: What, uh, to the brand's WhatsApp accounts? Yeah. To their Facebook page is a lot of the protocols that we are needing to guide you, uh, guide clients through so that their bots can stay connected to the platforms because they're always changing. They've always got these new things. And the big problems usually will be when there's a broadcast that is sent that has phrasing that, um, meta.
[00:27:57] Nick Thompson: Uh, says we don't like this for some reason, and [00:28:00] then it gets banned, and then we need to try and unban or unblock. Oh, the, the main problems that we used to have were really from a, from where we were at, I would say two years ago with our architecture and we've been able to patch quite a lot of the problems.
[00:28:15] Nick Thompson: Um, the biggest. The biggest learnings were from in 2025 when I, um, when we were expecting a hundred thousand, um, messages in a period of a month. And we got that in a period of a day. And it's, it's the, it's just, it's when the system, like load management needs to make a quick adjustment and having to get all hands on deck so that the service downtime.
[00:28:39] Nick Thompson: Um, doesn't affect the end user. It's really those types of things. What also happens, what also usually happens is us being asked to switch certain workflows off because the client's APIs can't handle the volume. So for like a loan application, for example, if there's, it's some type of generative, we are gonna find these the [00:29:00] best match for you.
[00:29:01] Nick Thompson: 10,000 users hit that thing in the first like hour. Then the system takes strain and then we need to switch the system off. So that's the backend. API doesn't have all done. So it's those types of things. I mean, it's not really ever anything super catastrophic because of. It only really does what we ask it to do.
[00:29:19] Nick Thompson: So it's not like we are ever really surprised by copy. That's also one of the things that I feel safe about not embracing gen AI as much, is there's just less heartache and pain of what happens if someone does prompt engineer the thing to say something really bad.
[00:29:36] Lauren Goerz: Yeah. Okay. Yeah, the, the brand reputation
[00:29:39] Nick Thompson: element of it
[00:29:40] Lauren Goerz: that makes sense.
[00:29:42] Lauren Goerz: And I think you were mentioning in general, um. The, the high volumes. How, how do you, how do you manage the load there? What are, what are kind of your approaches? Because I think that's something that, you know, in some ways that's the best case scenario, right? Lots of people are losing your product. But on the flip side, obviously it's, it's something that [00:30:00] needs to be managed.
[00:30:01] Lauren Goerz: I was curious 'cause I struggle sometimes with containment rate, even though it, it's a classic contact center. KPI. But at the end of the day, containment, like all of these people that are working in the contact center, who end up also sometimes working on these agents, their whole life mantra and their, their bonus, it's all, it's all tied into containment, which at the end of the day, containment can also just be simply refusing to serve the user.
[00:30:25] Lauren Goerz: But, you know, giving them some answer, you know? No, exactly. So I think, I think that. That's that focus on success metrics for me is so much more interesting in revealing than containment alone, which which could simply mean I've just either dumped them this random link that may or may not have been helpful, or I've, I've dumped them into this random queue with a hotline that's gonna take 20 minutes.
[00:30:46] Lauren Goerz: You know, and, and I think that's finding ways to measure success for me. I feel like, I feel like that needs to be part of our future versus kind of these classic. Maybe slightly more old school call center metrics, although I know they won't go away nonetheless. [00:31:00]
[00:31:00] Nick Thompson: Yeah. How do we avoid that? Please rate my feedback.
[00:31:03] Nick Thompson: Yeah. Outta five.
[00:31:05] Lauren Goerz: True. Which, which mostly I, we noticed this as well, like in project in. A high majority of the people that fill out that form are people who are not happy. The people that get solutions, like objectively from, you know, reading the transcript, don't fill out that form because they're, they're done.
[00:31:19] Lauren Goerz: They're gone. The people that do fill it out are really angry. So that's something I've noticed. Um, and last question for today. I'd love, you know, we're, we're, we're on, on the, the cusp of a new year. So Nick, we're in a new year. It's 2026. What's your prediction? What do you think is gonna happen this year?
[00:31:36] Lauren Goerz: Any hot takes,
[00:31:37] Nick Thompson: I think that people are gonna lose their faith in agents running the world. I think that we're gonna see far, far more studies of agents that didn't actually do what they were promised. Or what they're promised to do. And then I think that there's going to be a bit of a hesitation as to just connect an agent into your environment because the reality is that these [00:32:00] things are expensive or they can be expensive.
[00:32:02] Nick Thompson: They, they open you up to vulnerabilities. I think that there are gonna be far more stories of people who incorrectly install things and get their computer contents deleted and their cloud credentials harvested. And it's obviously not something that is good in any way, but I think that's. That has to happen for people to realize that when you do give an agent the ability to run.
[00:32:25] Nick Thompson: As an administrator on your computer, without putting it in a protected environment, you really are opening yourself up to vulnerabilities. And I think that the influences are the ones realistically, or who are gonna bite that bullet first. Maybe bite that bullet is not a good.
[00:32:40] Lauren Goerz: No. Fair, fair, fair. There is a lot of influencers, a lot of hype grifters out there.
[00:32:45] Lauren Goerz: One could argue, but I, I would agree. I think, I think my, my twist on it is like I, and I think I, I credit also my colleague Rod in, uh, dere for this prediction is like he's calling 2026 the economic recogni, the economic reckoning when ROI becomes [00:33:00] non-negotiable. Yes. And I think that's, that's fair. And I think that also in a sense is the precursor to your prediction.
[00:33:06] Lauren Goerz: Folks are not going to continue to fund things that don't work. Only things that work survive. And I think, and I'm open to anything, you know, however, on wherever it is, on the agentic scale, I'm happy if it's working. And safe, safe, if can do it safe and customers are happy. So I think that's, that's also where I'm, I'm, I'm feeling the same direction.
[00:33:22] Lauren Goerz: Uh, no more frivolous agent projects has to work. Has to work in production.
[00:33:26] Nick Thompson: Yeah, definitely.
[00:33:27] Lauren Goerz: Alright, thank you so much Nick. It's been an absolute pleasure. I wish you the best. I love listening to your stories, especially 'cause you have hands on keyboard experience, working with customers side by side. All the best to you and your customers in 2026, and we hope to see you again.
[00:33:39] Nick Thompson: Yeah, thanks Lauren. Same to you.