自社のビジネスは「パーソナルエージェント」に備えられているか？

Hello there. I'm joined here by Nicola Merkic, the CEO of PolyAI here at CCW Europe in Amsterdam. Two things I'd be interested to talk to you about. For those of you that tune in regularly, you'll know that Nicola was on the podcast fairly recently. We had a really good conversation about Raven, your fine-tuned language model at PolyAI, the kind of approach to that research-led kind of innovation. Since then, two interesting things have happened. One is that you now have REN, which is the kind of self-improving agents kind of idea. And the second thing is we've started to see the beginnings of kind of agent-to-agent communication, which was always on the agenda, but with Muse and Dots and Grokbot in the last sort of two, three weeks, it seems to have just really, it's there waiting to happen now, so to speak. So maybe we'll start with that and then we'll get on to the idea of the self-improving agents. So what do you make of the state of agent-to-agent communication?

What do you make of Muse, Grokbot, Dots, and how are you starting to think now at PolyAI about this potential world where me as a consumer are going to have my own agents doing my own stuff and how the business is preparing for that? How are you starting to think about that kind of stuff? No, no, look, I'm really excited about that. I mean, I started Poly after leaving Siri because it wasn't amounting to what people expected of it fast enough. So I've been hugely passionate about both personal assistants and voice assistants, especially where they overlap, for a very long time. I think that ever since the claw-bought mania of about, you know, now six months ago-ish, we could kind of see the moment coming. And I think, you know, the valley has decided, the hyper-funding is coming in, and, you know, we're going to take a crack at it for the first time properly since Alexa was a thing, right? So I think it's huge. I think we see the number of calls growing, admittedly from a very small basis, but we still don't have one full month for me to tell you how much it's jumped, but it's at least like 10 times.

Back in 2020, we had the early sign of this with Google Duplex calling one of our agents. I think to us, it was one of the first Dr. Livingston, I presume, moments of AI talking to AI, and it wasn't a very good conversation back then. I think agents on both sides are far better equipped now to have those good conversations. I find it hilarious that they're communicating with human language, right? That they're burning these tokens to produce voice, to understand voice. You know, it might be someone speaking with, you know, Georgian accent calling and someone with a Geordie accent picking up, and we're doing all that for really no reason, and that they should be communicating at least with, like, text, if not voice. And it's also funny in that in the CX strategy of companies, voice has always been meant as the escalation point away from it, right? So now that you kind of get parity on the caller side with the automation that was mostly facing inbound calls by enterprises, it's a whole new world of having to, like, have an arms race between what you can do in terms of provisioning demand

and the demand being created. But I think we'll reach a steady state where a solid chunk of the calls are agentic. I think we did another kind of survey of those calls that were able to detect as automated. And we thought it would be dominated by scammers. And there are a lot of like scam outbound calls, but it's not. I think already with these launches now well over half if not quite a bit more are legitimate real calls So I think companies are going to have to accept this as facts on the ground They might have a slightly different level of engagement and handoff to AI agents versus the non ones But I think that Jevons paradox where, you know, instead of just getting to a level of service and stopping, we're now going to overproduce this, like, labor automation on both, you know, the demand side and the supply side. Interesting. is there anything in particular that you do in order to detect that it's a an agent calling

and secondly this could be something that happens quite quickly you know chat gpt went from zero to a million users in like days so there's always a potential that this thing can really take off pretty quickly one how do you go about detecting it and then two as a business how do you how should you be thinking about dealing with it is there any difference between how you should treat an agent to agent interaction versus the human to agent interaction or not yeah there are many unanswered questions here so far right so i think one key question is like how are they authenticated and i think one of the better things when using instinct and you know is that well or at least like the grade of agents that will become used at scale like that especially muse is that in theory I should know that it is Cain Sims and that I can trust that it's you. And therefore, whether it's human or not, like if I pre-authenticated you, then we can skip a part of the conversation. But that should be true in CX already, and it's not really implemented at scale. So I think it just adds another variable to something that, sadly, as a community,

we've not really solved at scale yet. So maybe it increases the need to do a lot of the digitalization and standardization in order to get to a point where this is Cain. I know it's Kane. I know why he called before. A lot that we're doing with our customers already lends itself well to keeping... We refer to it as a dialogue that sits in the ontology above a conversation. It's like an ongoing set of interactions about you, what I know about you, your habits, your history of interactions, so that I can just kind of get to the point a lot more quickly. Ideally, know what you're calling about immediately. It's really what a lot of true omnichannel has always been about, but never really reached. So I think as the technology reaches a point where we can do a lot of that more, you know, effortlessly, that's where I think these things just give us a reason to do it all the more. Because otherwise you'll have context centers collapsing, and you won't be able to, you know, provision enough humans or AI potentially to deal with the demand.

Of course you can get enough AI, but like if it's not able to do anything, then, well, I mean, we'll love it because we'll get paid, as will the album called Originators, but it won't really lead to improved customer satisfaction at the end of the day. And what does that mean for PolyAI, where there is an increase in kind of like that agent-to-agent conversation type of thing? Do you need to do anything differently? Is that good news for you? Because as you just said, you know, Voice was the last resort channel. Now maybe if I can get Muse to make a call, that might be a preferred channel. Therefore, calls might rise. Therefore, the need to automate more might rise. So what does that mean for PolyAI in terms of... Yeah, I mean, that's back to the Jevons paradox, which I think is one of the best things that has historically happened in every industrial revolution. So rather than people just driving to work they buy two cars move further out because the fuel prices went down Similarly here you do more with AI So you know you automate and then people provide their own agents to deal with your automation

So it's kind of like just a necessity rather than necessarily an improvement. Of course, it will be a better experience when we're done doing all that. I think agents should talk to each other, you know, in text. They don't really have to do it in voice. Do they even need text? wouldn't kind of like a series of API calls just being made behind the scenes solve this problem? Well, that depends on how gentrified and AI-pilled you are. I think where deep learning has triumphed, as we always knew it would, is in the unstructured data being passed back and forth. LLMs allow you to not have to pre-specify like, you know, API fields and stuff. No, that's what MCP is about. In reality, what we see in practice is that most MCP or A2A connectors are not yet solid. and then, you know, that language around that interaction is something that happens because, because, you know, if you just had clear API connectors, you'd probably have an app that did it anyway, and you don't. So that's where it's just, you know, one question is the enterprise adoption overall.

The other is just what do we need to do? What do we need to build to make it all work? Most MCP right now is quite slow, and agents using APIs fare a lot better. It's a lot faster, a lot more effective. Those are also usually far more battle-tested. This is true outside of CX. This is true for using Gmail through Claw, right? So, yeah, I think, like, there's a lot. Like, it's really exciting because we're doing so many things that we could only Gmail before. On the other hand, you know, the taxing work of standardization, like, actually, we just see, like, the Wild West. It's full of opportunity, but it's also unregulated. And that's, I think, okay for the most part. Interesting. Finally, I wanted to chat with you about the idea of self-improving agents. As, you know, if we're saying that there is a world in which personal agents create more demand, businesses are automating more, more and more kind of conversation automation happening, it then becomes part of the kind of job of scaling. That means that you're not only building new stuff, but you're also needing to improve what you've just done.

I kind of had a bit of a sort of ramble at the beginning of the year where I was saying that I think there's a world, actually, where AI agents design themselves, build themselves, test themselves, analyze themselves, improve themselves, and therefore, you know, it doesn't really need kind of people to be involved because the AI's got more than we have. And this year we've seen quite a lot of that happening. You know, there's another, some of your competitors have released something similar. You've released REN, self-improving agents. Talk to us about what's the concept of self-improving agents and how does it kind of work behind the scenes. Yeah, yeah. I mean, I think there are two levels of REN, right? Like the first level is a coding agent where you finally bridge that like self-service for, you know, the business side where they're finally able to do things. You know, we've got people sending 2,000, some have reached 3,000 messages a month with REN. Now, I am terminally addicted to cloud code and I don't do that many in an average month. so like there's a real kind of like ai pilling of the contact center that coincides with the adoption of run by our customers where those guys are finally that like self-service you know human

layer above the sea of ai agents dealing with your customers that's really good because it's badly needed because the combined motion of you know hyperscaler brings in a gs right to deliver something has not really ever gotten to the point where it iterated fast enough to build like a robust thing that could do most of the things that your contact center does like it your contact center that must encode those rules into your agent so that's level one level two is um you've launched it and then like how do you get it self-improve well you know another agent looks at all your calls and suggests oh i'm seeing this in 10 of the calls i'm seeing this and 5% of the calls. It basically goes away in very kind of long horizon tasks and just delivers something that is 10 proposed fixes for the morning, 10 where it got there almost but is unsure about the context. You go and you go, oh, I love that. Click, click, click, click, click, accept, right? For the other ones, you add a bit more. That goes into Ren's memory. Next day when it's looking for new things, it has a richer context.

So you iterating with it every day is to build up the context layer that as it gets better and better and better, and you connect rent to your Google Meets, Zoom, Teams, to the channels where you're discussing it internally, and that always just feeds that context. The moment you reach a sufficiently well-built-out context layer, you can let it go into level three, which is like full autonomy, where some of those fixes can just go in. A-B test, A-B test, A-B test. If you're running, say, 10,000 calls a day, you can go up to at least five, potentially ten parallel A-B tests and still, for the most part, get enough data to within a day or two, say this worked, this worked, this didn't, and then you can take it back to the human, or for those that are unambiguous, like flipping the voice to data voice or changing the phrasing to this phrasing, where we know and the LLM judge knows that it works, then you just go merge, right? So that level three is in beta with you customers. It will be released later this year. but I'm super excited because

it was always true that there was this law of diminishing returns of like an extra change and an extra change and an extra change and when IT had to work combined with CX teams this was a very expensive maneuver when the CX teams can do it on their own they're going to go a lot further than any forward deployed motion ever could and you know we've like died on the hill of pioneering and defending the FD motions I kind of feel like I'm backstabbing myself by saying hey that age is over because we will never. And, you know, I've got customers like FedEx who have been my customers for four years. I know everything there is to know about their CX. I'm not in a position to make daily calls about their business in a way that their people can. This is why it's really important for them to get AI pilled so that they can go to a higher and higher level of autonomy in using REN to help themselves because, you know, maybe it takes 10,000 changes in tickets to go from like 30% to 80% automation. And with humans, you might have stopped at the first 100, and hopefully you've gotten 100 of those that add the most.

Maybe you would have gone from like 30 to 50, right? But why not do the remaining 10,000, right? We finally can. And I think where I also sleep better at night is, you know, we see people rising through the ranks and being the most AI-pilled people in these companies because they are now harvesting this data that they have, and other departments do not have this level of data to work off of. This is oil that they're extracting, right? And through that, I think we are training the next generation of not just CX leaders. I think the next COOs of large companies come from the AI-pilled CX managers of today. Nice. Brilliant. Nicola, absolute pleasure as always. Thank you so much. Thanks for having me. Nice one.