292 Audio.mp3: Audio automatically transcribed by Sonix

292 Audio.mp3: this mp3 audio file was automatically transcribed by Sonix with the best speech-to-text algorithms. This transcript may contain errors.

Peeyush: The number one thing which we really invest in, in Nurix is actually in making sure that the latency is really low. Let's say you're talking to a model which is going to perform certain tasks for you. That is in chat and all. It's very clear you can have more latency even in voice. When it comes over, there's an expectation built. But when you call into a business and you are talking to a person, there's no expectation latency. It's like almost human like behavior requires as I finish, you talk. And not only that, there is a little bit of, you know, parallel conversation going as well. For example, if I'm speaking for a little bit longer and you're saying and all those things like, you know, those are markers of like, are you nodding along and you're following me? Those are also part of the conversation. And if you just keep quiet for too long, then also I feel like, oh, are you even listening? Are you there? My name is Piyush. I'm a technologist at heart. Uh, you know, and uh, have been working in a variety of different, uh, problems which had like an intersection of technical depth and worldwide impact thanks to, uh, long time association with a company called Google, uh, where I joined, like 19 years ago.

Peeyush: I left them, uh, just end of March. Um, and over the period of time, uh, you know, I've worked on a variety of problems, from search to, uh, you know, workspace and most recent and, uh, fintech and most recently past three years, I was working on AI, uh, as part of Google Assistant and the Gemini app. Um, and, uh, as of March, uh, you know, I left Google to join, uh, with her ex colleague and a friend for the last ten years, uh, in, uh, creating, uh, in partnering in what is called Meraki Labs, which is, uh, about incubating and building, uh, you know, it. Deep AI companies, uh, you know, we all see that it's changing the world. And Nurix is, uh, you know, first of those companies which, uh, you know, I have been involved with, uh, I'm on the board and obviously, uh, giving, uh, a lot of, uh, technical input and architectural input on how things can work and how they can scale, uh, new self. Uh, yeah. Go ahead.

Craig: No. Go ahead. Uh, so Nurix is one of the companies incubated?

Peeyush: Um, yes. Yes. And, uh, you know, I'm just starting I mean, this is this is the, uh, first in a, in a really important space, which is, you know, of conversational agents. So if you ask me, like, uh, about nurix itself, I think the the toughest problem, which I feel like Nurix is handling, which is required, uh, is actually having a world class voice AI solution. You know, most of the conversational agents, uh, there are many different ways conversations are had. Right? You can have, uh, text and email based or chat based and voice based, uh, you know, and of course, in future, like video and other things. But, uh, currently, uh, voice is the cutting edge of that, uh, which has the hardest set of problems within it. Uh, that is one big space which Nurix is going deeper into, uh, in a variety of ways through new innovations. Um, and then there is, uh, of course, uh, the other area is how do you make this agent work really well for enterprise use cases. So there's a voice set of problems, and then there's enterprise set of problems. And the goal which Nurix has is to, through this be the smartest, uh, you know, uh, operator for the brand, like, you know, uh, when you are talking to Nurix for, you know, when deployed inside a company, It is essentially a representative of the brand that you are talking to them, whether it is from starting from sales all the way to support, and also at the same time, it's not just that you are talking and getting information. It's the smartest agent, which you can talk to because it integrates deeply into the enterprise and is able to help you through all your workflows. So those are the two big, uh, facets of it.

Craig: Yeah. Uh, I've been talking to a number of people about voice and about, uh, translation. Also, uh, I just talked to a company called deep l. I don't know if you know them. Uh, but they do, uh, they do. Translation. Uh, and then I, I earlier I had on the podcast a company from, uh, I always get their name mixed up because there's so many similar names. I think it's Speechmatics. Eric, does that sound? Yeah, they do very, uh, natural sounding. Their emphasis is on very natural sounding speech. Uh, so one of my questions is, um, you know, the underlying tech, uh, is exists. It came out with, uh, with the advent of Transformers open AI does. I talk to OpenAI's ChatGPT when I'm in the car, and, um. Yeah, it's remarkable. Uh, even the standard voice. How natural it sounds. Uh, so how do you how does a new startup fit into that crowded market? What what what differentiates.

Peeyush: I guess that's that's a that's a great question. I think that there are a couple of things which, uh, uh, have to be kept in mind. So let me first talk about the voice part of it, the voice part of it. The number one thing which, uh, we really invest in, in UX is actually in making sure that the latency is really low. Uh, you know, when you are talking to, uh, let's say you're talking to, uh, a model, uh, which is going to perform certain tasks, uh, for you there is in chat and all, it's very clear you can have more latency, even in voice. When it comes over, there's expectation built that when I ask something, it is going to take a while for it to get to the answer. But when you call into a business and you are talking to a person, uh, there's no expectation of latency. It's like almost human like behavior requires as I finish, you talk. And not only that, there is a little bit of, uh, you know, parallel conversation going as well. Uh, for example, if I'm, uh, speaking for a little bit longer and you're saying, and all those things like, you know, those are markers of like, yeah, you're nodding along and you're following me. Uh, those are also part of the conversation. And if you just keep quiet for too long, then also I feel like, oh, are you even listening? Are you there? Right. So there are these kind of psychological aspects of it, uh, which are above and beyond the actual, uh, likeliness to a human speech.

Peeyush: This is actually about conversation. So we invest a lot of time in making sure that the latency does not drop. And one of the reasons why it is important is when you are calling into an agent. Well, two things. One is when you're calling into agent, you might ask the agent to go do something right. Therefore, your your pipeline of activities can have latency introduced in many places. But we don't want your voice to be your voice interaction to have any kind of latency. So we have invested a lot of, uh, engineering in there to actually be able to respond to you super fast, irrespective of what is happening behind that is one. The second thing is what I was talking about. That human interaction and dialogue between two people is actually a little more nuanced than the, uh, you know, over and out. Roger. You know, kind of like walkie talkie style. Um, so here we have our own proprietary dialogue manager, which also is trained to understand that, okay, this conversation which is going on is the person stopping and thinking about because you suddenly ask them, hey, what are your last four? Or what is your driving license number? And the person is quiet. It's probably because they are fishing for their driving license as opposed to, you know, uh, it's your turn to talk again.

Peeyush: Or if that is happening, then that's what that means. So we have that is the second, uh, uh, investment in there. Uh, and the third thing, which is beyond a single person to person conversation, is like, imagine a call center right now there are like, uh, 500 people calling simultaneously it naturally from system design, right? Engineering wise, it can have impact on latency of each one of them, depending on how you architect it. So you have to think about that architecture as well, that when the load goes up, it does not mean every people, every person feels that their agent suddenly becomes slower. So all of these are aspects, you know, this is the, uh, one other thing which I feel we are feeling is, is the more you get deeper into the domain of how the models are being applied, the more these nuances start to show up and you have to go solve them, because the models are very, very capable and they'll only become more capable later. But you have to understand these nuances, and you have to solve them properly so that you can deliver a world class experience on the other side. So, so the point you made about these capabilities, which are there? Yes, they are there. And we leverage them wherever they are. And then we solve these problems so that the person calling into the that business feels like the other person is, you know, really as human like as possible.

Craig: Yeah. And one of the things you're talking about his end point detection. Right. Knowing when the other side has completed a sentence or something and it. And what are the underlying models or do you are you is is sort of model agnostic because, you know, there are new models coming out all the time. Uh, or or are you working off of open source models and fine tuning open source models? Um, yeah. I'm curious about the architecture.

Peeyush: Yeah. So there are parts which are our own proprietary models, like the stern taking piece is our own proprietary model. Um, you know, we need to really make sure that we understand the conversation which is happening, which are many times business specific conversations. And, uh, also, we understand, uh, you know, when is it that because we also operate in a variety of noisy environments and all that. So we have to make sure that we understand when really there's an interruption versus there is not. So that is proprietary model. But then when you start deploying that, uh, into the, uh, you know, a particular customer, uh, then there are, uh, specific models depending on a, uh, what is the task which they want to apply it for? Uh, you know, we are, uh, able to integrate with, uh, OpenAI. We are able to integrate with Azure implementation of that. We are able to integrate with Gemini over GCP through vertex. Uh, all of these are available and they are all integrations depending on the deployment which we are going after. Uh, there are other places where we also have, uh, custom models like, uh, the speech to text. I think I mentioned that, like, you know, the real world noise detection and saying, okay, what exactly is this person saying and understanding? Uh, the speaker is talking, uh, into the phone as opposed to somebody else, or there is two other people in the background talking. All of that is actually done using a proprietary model, because we want that experience to be perfect. So that and the dialogue back and forth is done by our own proprietary model. And when deploying into the business, then we can choose what is the best model for that particular use case.

Craig: Yeah. And and this, uh, this product, it's not a consumer product. It's it's going into the tech stack for various, uh, other applications as, as the voice engine.

Peeyush: Yes. It is actually an enterprise product. It is still an end user product in the sense that the end user interacts directly, they'll dial into or they will call into, or they'll message a nurix agent, but that nurix agent is deployed for a customer. Like if it's a retail customer, uh, we'll deploy it and the, the retail business will deploy for and the end customer of that retail will call in and say, where is my order? And that call will be fielded by Newark's agent. So that solution is built by us and it is available, but they feel like they're calling into the business. And then it is Newark's agent, which then picks it up, talks to them, and based on how it has been configured and deployed, it will actually go look up in the order management system or something and then be able to give them the answer back or, you know, act on that order depending on what the operating procedure is.

Craig: Yeah. And and again, um, you know, am I wrong that this is an increasingly crowded space? I mean, I just from the number of people that contact me or the various conversations I've had, uh, it seems like there are a lot of people out there trying to tackle this problem. And is is the market large enough that, uh, that it'll support many, many solutions. Or are companies going to start up? Well, one of the other questions is these guys that are doing translation between language pairs. Um, uh, and they're not doing, uh, actually they're not doing, uh, voice to voice. Uh, they're doing text to text and voice to text. But, uh, presumably you need, uh, models fine tuned for each language. Uh, is nurix focus solely on English or are they, um, uh, looking at other languages?

Peeyush: Um, Nurix is focused on multiple languages. We are currently available in 20 plus languages. And, you know, um, we have customers in US and in India and in both of these countries, multiple languages are needed. You know, especially like in the US, you at least have English and Spanish. And in India, you know, almost every state has its own language. So, you know, it's multilingual. I will say one thing. Uh, it's not a language translation experience. It is actually a. Conversational agent experience. So you can talk to this new agent in any language. And primary value you get out of it is the fact that it can actually act on the business's behalf as your customer support or your customer sales agent while you are talking to it. And you can talk through like a chat or a voice or whatever. Now, like you said, it's a very, uh, you know, happening space. A lot of, uh, people are entering, uh, generally the two things which I will say that. Yes, uh, it kind of shows that the market is ready to accept solutions. And we are seeing the same thing, like we said, like we have, uh, over a quarter million, uh, you know, calls which were done, uh, just, uh, you know, this year and we have five x quarter over quarter growth, right? So seeing this kind of growth, it's not surprising that a lot of people are coming because they're like market is ready.

Peeyush: Now the question is just like we have seen it many times in the past, that when a market starts to become ready, a lot of people are there. Uh, but right now, I would not say that the market is saturated because there are so many people who actually have call centers and voice based, uh, you know, uh, representation or their representatives, both outbound and inbound, which still are, uh, you know, not AI agents and that that whole thing, uh, can be much better. Uh, the cost for the business will be lesser, uh, the error, uh, because these are very repetitive, at times, tedious jobs. The error rates can go down. There's churn in terms of users. Productivity can be up because you don't have to train as much. At the same time, simple things like I'm sure Craig, you have experienced this. You call a number like, all right, you're on the hold music, right? Then it's not going to be a hold music anymore, right? Yeah, hopefully. So those kind of things.

Peeyush: And I think that, uh, the world will look different if we just, uh, you know, and I'm sure that you will agree with me in AI, uh, era that we are world looks different. You know, six months from now, right? So there will be a different world. But right now, uh, people are entering it. It's validating the market, and it's not done yet. Um, I actually feel very confident that we are building a solution which actually is at the edge of this, like this voice problem we were talking about, like making human like voice possible out of the system is non-trivial. Uh, there is a lot more psychology involved in it. We spend a lot of time making sure squeezing out every bit of latency out of it, so you feel like you are talking to a real person. There's a lot more dialogue management involved. This is why our proprietary models are there. So a lot of these, the science is going on and it's obviously hopefully, you know, the fact that we're investing so much in the science will help us, you know, see traction. And I think we are starting to see that and hope this quarter over quarter growth continues. Right. So yeah.

Craig: Yeah. And then how um, uh, do you think the market will then eventually coalesce around a few big players or, or, or do you think the companies will end up specializing in, uh, like there will be the, um, the dominant player for India or the dominant player for China, the dominant player for South America. Um, or do you think one company will cover all that up and become dominant globally?

Peeyush: Um.

Peeyush: I don't know how it eventually will be, but I can tell you the, uh, current heterogeneity that exists and that heterogeneity, like somebody who covers that really well can become dominant or it can become the way the market gets segmented. Right. So the biggest heterogeneity is that, you know, and this we have learned from our scaling that you really have to go in and, you know, be uh like get into the business and deploy. Right. It's not that you're from outside. You throw something over the wall and the business says, all right, let me go. Click, click, click and be done. Um, because if you make mistake, it actually affects the operations of the business. It affects the profitability and things like that. Customer retention. So you have to go deep into it and and deploy. And there's a lot of learning which is happening in that place. Like I will give you an Give you an example, just to give you examples of how current technology cannot just be thrown over the wall. It tells me that you cannot today have a business which goes, all right, I got it. Go everybody and take it over. Here is an example. You must know about rag retrieval augmented generation. Now people take documents and they kind of stick that inside that. It's a very standard technique. However, if you're going inside an insurance business and you have all the policies in there, right, it's not as trivial to tell a customer that, yes, your current claim is supported or not supported, because if you make a mistake in your rag, if you did not pull the right chunk out, you might end up denying something which should have been covered, or you might end up covering something which should have been excluded in the fine print.

Peeyush: Right? So we invest a lot of time in understanding the structure of the document based on the domain that is, so that we can chunk it properly and we can retrieve it properly. You know, we even spend time in rewriting the query to like, you know, when the person comes in and says, well, is this covered by policy? Then we know, how exactly do we rewrite? Now this is all domain specific work. Now the reason I give you this example is if you take all over the world this work has. This is not easily generalizable. And this is what we are seeing with everyone, not just in UX like everybody else, is that they have to go in almost Palantir style, like they have to go into their customers, you know, building and kind of work with them. And that means the answer to your question that will there be one which will win all, I think till technology gets to that place. And maybe I mean, Nurix is building a platform called New Play, right? We will have a platform which will make it super easy for you to pick and choose. And when those kind of platforms start emerging, we are starting to offer one and those become very capable. That is when we will be able to answer this question. It's hard to tell right now, but right now it's to keep the quality high. It's a lot of work. We have been able to scale the deployment and that is why we are pretty excited about it.

Craig: So and and I'm just curious your sales operation.

Peeyush: Mhm.

Craig: How do you figure out who might need the solution. And and then uh yeah I mean because uh there, there are all these different sectors and all these different players. Um, I mean, as you said, customer service, customer service alone is uh, is a very, uh, fragmented market. So, yeah, I mean, what's the strategy? Do you go after one vertical? Do you, uh, you sort of have a massive sales team that's calling every buddy who could possibly need voice.

Peeyush: Yeah, well, uh, Craig, we are still a startup, right? So we are like, uh, maybe, uh.

Peeyush: I think six months or a.

Peeyush: Year.

Peeyush: Uh, my involvement has been less than six months. But the thing is that we are still a startup. So there are two main things which I will say, uh, you're not turned down any customer who comes in and says, we want your stuff, right? But at the same time, when reaching out, we got to go where momentum is and where we are actually like we have referenceable customers and we are seeing a lot of traction in specifically like in e-commerce market, uh, and in financial services market. The example I gave you, insurance was a financial services and e-commerce is another example. I gave you the order return thing. We are seeing a lot of, uh, you know, traction in there and, you know, but I'm thinking that given the growth pattern we are in and we are also not like, you know, that doesn't mean that all our revenue is coming from just those two. Uh, you know, we are a startup. Why would we say no to more customers coming in, right? Like, scale as fast as you can. So that is the answer to your focus and sales question. But we are primarily seeing traction in two big markets. And uh, I think, uh, we are not in a state where we can have, like, you know, salespeople everywhere. Our founders are actually knocking on the door, showing up in the conferences, talking to people. Right. We don't, uh, you know, we have found our sales right now. So that is how we are. Yeah, yeah, yeah.

Craig: Um, and the dominant player currently seems to be, uh, 11 labs. Uh, how how do you view them as a competitor? Um, and how do you, uh, distinguish nurix from 11 labs?

Peeyush: So 11 labs is, is a great, uh.

Peeyush: Technology provider, uh, which we can use. Uh, the basic idea is that they do a great job of generating human like voice for for any kind of parameters, right? Um, but if you notice, we start from, like, fielding a phone call and having a conversation. Now, in having a conversation, we have our own, you know, speech to text models, uh, with all the noise filtering and the dialogue management. But if you have to generate a response, we can use 11 layers. It depends like we use Google's TTS as well. We can use 11 labs. We can use others. Uh, they all technology choices to us. Um, the overall approach is where is it that the problems have not been solved. We want to go solve them and wherever they have been solved, we want to utilize them so we can focus on the layers where things have been solved. So that is how we see it. We don't see it as like 11 labs as a competitor. It is actually our supplier and a partner, if you will.

Craig: I see yeah, yeah, yeah. This is fascinating how these, uh, these new industries are developing and stratifying.

Peeyush: Yeah, absolutely.

Craig: Yeah. Yeah. So, um, you mentioned that we someday we won't have to listen to old music. It still drives me crazy. Yesterday I was calling somebody, uh uh, and it's like, uh, you know, listen closely as our menu options have changed and, you know, why is there a menu? You know.

Peeyush: You don't have to do that. Yeah.

Craig: So what's what's holding, uh, enterprises back? I was wondering, is it because these guys have bought a system, uh, and and, you know, they they want to wait until they've amortized it down to nothing. Or is it that, uh, uh, companies are just, uh, risk averse and they want to see how the, the market evolves. I mean, what what will it take for those, uh, what are they called? I, I can't remember. Yeah, yeah, yeah, yeah. For all of that to go away. Where you call up and you speak to somebody, uh, and you can't really tell whether it's a human or not, and they handle the call fluidly. Well, you think that's a year away or ten years away?

Peeyush: Oh.

Peeyush: I definitely don't think it is ten years away. Uh, let me look at the amortization thing first, and then I can talk about what might hold somebody back. I don't think it's amortization is going to be the biggest, uh, issue because, um, the savings, you know, not only the cost savings but also reduction in errors and mistakes, uh, increased opportunity of better cross-selling and upselling when somebody calls in. And above all, all of this because it is run by AI. We can provide analytics saying, look, these are the kind of things which you could do with the calls today. Call analytics is actually very, very hard. But we can do a much better job because everything is running through our digital system. So all of this will have enough business value that you will actually justify the new investment. So that is not the uh, primary, uh, blocker in my view. But you know, the primary, uh, blocker I think would be the businesses building confidence in these non-deterministic systems, right in the IVR. It's like, you know what I mean, right? It's a very, very clear IVR tree you're going through. And then there's like, okay, I can do a set of things and then a human comes in. But here, if you really wanted to remove all that tree, you would call. And immediately it would be like, hey Craig, this is, you know, Bob from target, right? If you're calling target and then it's like, okay, what do you want? Now you have a non-deterministic system. What are the expected outcomes? What are the the operating procedures? What are the, uh, guidelines and guardrails and making sure that this system runs within that they have to build that confidence.

Peeyush: And this is one of the spaces, by the way, we invest a lot in like I talked about the rag, we have a lot of the simpler parts here are that, hey, you have a set of back end services. Can we integrate with that? That is system level problem. We can integrate with that. That's easy. You know MCP is available there like out-of-the-box integrations LMS can do tool use all that is there. But making sure that the LM actually does not deny a claim when there was actually a possibility or does not, uh, say, oh yeah, go fill out this form without calling out that no, you had an exclusion or a series of such things, or does not, uh, misunderstand an acronym which is specific to a particular domain. These kind of things actually are, problems which are being solved in the industry. We are investing a lot in that as well. And I think that that because it's as new and being solved, there is a level of comfort which has to be built. But we are seeing a lot of traction and people trying it out. Right. So the thing is that the businesses, once they try out and they see the difference, oh yeah, this is great. My errors have gone down, my business has gone up. I'm able to transparently see what exactly is happening in this part of my call center. Now naturally. All right. Let's do more of those. So I think that that adoption will will happen and fairly soon because this is their business. They don't want to risk that.

Craig: Yeah, yeah. Um, and so, uh, you guys build not only the voice generator. Mhm. Um, you, you you build the, uh. Well, yeah. Describe again, I mean you're not simply voice generation. You, you build a higher level solution. So describe sort of end to end what what that solution is.

Peeyush: Yeah, absolutely.

Peeyush: So now imagine that. Imagine you are a retailer, you know, and you say that, hey I would like to try out, you know, uh, your, uh, service for or, you know, people who call in to find out where their order is or want to cancel their order or like, you know, uh, status of the order. Right. Very simple. Three things. And you have a back end, you have order management system, which has, let's say HTTP interface or some other sort of internal interface. So what we do is first is that we and we say, okay, what kind of endpoints will you have? Will you allow people to, you know, call you in? Would they want to check in through a chatbot on your website, or do you want to allow them to check on WhatsApp or SMS or whatever? Those are the ways they can talk to you when they call? The calling to the voice is the most technically savvy part. Of course.

Peeyush: Here.

Peeyush: Because of the human thing we talked about. When you call in, are the phone lines obviously end up with us, and then we immediately, uh, you know, figure out what you are saying using our own custom speech to text model. Uh, right now, uh, and nobody in the industry, not just us, is using a multimodal native voice to voice model because those things are harder to engineer to increase the precision which we want in an enterprise setting. They will get there. We will get there with them. Uh, but right now. So we quickly take whatever you have said, we filter out the noise, we understand who's talking, and we bring it to a texting. But now you are sitting inside a dialogue management system where actually it knows that somebody has called in. And then whatever you have said goes on to the, uh, you know, essentially the agent brain. But that Agent Brain is pulling in context from the Rag system. Now, the Rag system, there are a series of techniques of rags, of chunking and querying different kind of things, which depends on the domain which you are in. We apply in this example. Probably we pull policies regarding cancellation and return, which is, you know, very custom chunking done.

Peeyush: Depending on the documents you have given us, like, okay, where exactly, you know, these policies are and now it goes into the rack system, pulls that up, and then it goes to the model and which actually kind of then does a tool call, gets the status of the order, makes the decision on what has to be done and response when it responds. Then we actually the dialog manager knows now that the model wants to respond. So the dialog manager turns that into voice and sends it up. But in the meantime, if suppose there's an interruption which is happening from the user, it's the dialog manager sitting in there listening to the user, which actually says, all right, wait a second. Or, you know, passes on the interruption, whatever it is. So that is the end to end in a very simplistic way, how this whole thing works. Uh, now the complexity on the front end, we already talked about, like, you know, how you have to be really human like, and on the back end, You really have to, uh, you know, stick to what the business wants, right? And that is where a lot of that engineering also goes. So those are the ends of it.

Craig: Yeah. And then, uh, if if the model can't answer it, hands off to a human.

Peeyush: Yes.

Peeyush: If a model cannot answer, it can always deflect and say, all right, well, you know, it's like how tier one versus tier two support can happen. Right. So suppose you end up asking something else that hey, yeah, cancel that and you cancel it. And someone says that what I want a different replacement. Right. Well, suppose the model is not designed to take orders. They'll say, okay. All right, let me get you to somebody. Yeah, obviously.

Peeyush: Yeah.

Craig: And and is this, uh, are on that handoff then is it going to a BPO call center?

Peeyush: Uh, it.

Peeyush: Would I mean, the assumption is that the businesses already have BPO, right? Uh, because the call centre is where these phone calls were coming in before. Uh, so that already exists and the handoff will be structured accordingly. Uh, you could always come up with other ways of handoff, like, hey, let me text you a link to our app where you can perform this action or something like that. Yeah.

Craig: Yeah. On the on that handoff piece, I, I had a company on a while ago called crescendo. I don't know if you know them.

Peeyush: Yeah I know.

Peeyush: I know crescendo. Yeah.

Craig: Oh do you. Yeah. Yeah.

Peeyush: So from like prior life.

Craig: Oh. Uh. And then they talk a lot about Sierra as being a big competitor. Crescendo. Their, uh, thesis is that that handoff is critical and it's difficult unless everybody's under one roof. So they they, you know, they bought Product And. And they have their own call centers that are trained with their AI. So everyone, um, knows what's what's happening. Uh, and indeed, I've run into cases where, uh, uh, you know, you talk to a, an agent, uh, voice agent and you or certainly on text, uh, you give it all your information, you describe the problem, and then you get transferred to a live agent, and they start from the very beginning. Yes. You know, it's frustrating. So how do you avoid that problem?

Peeyush: Yeah, actually, this is very interesting because the thing that you said is not introduced by AI. This happens human to human transfer as well. Uh, you know, I was talking to Xfinity once about something which was going on, and they kept transferring me and every new person started from the top saying, oh, let me verify you are a customer. I'm like, I'm talking to the sixth person transferred inside. So this is a systems problem, which is like when you get transferred. So the question really is that when the handoff is happening, is the context being passed around. And the beauty which I feel is that if you design the system right, the model will always do what you have told it to do, right? So if you say that when hands off prepare a, you know, a three page summary and pass it on to the human, then on the human screen, if the three page summary is this is what has been done so far, then that experience which you get is really based on the competency of the human agent who you are talking to, that have they read through that or not? Uh, so I think that this is a systems problem. This is not a AI to human problem, because we see this in human to human as well, and it's how you have structured it. So and we are very capable of generating any kind of summary for any kind of call. As I mentioned earlier, we do analytics just for internal consumptions as well of how these things are and being embedded in the team. It actually helps us also make sure that all these, uh, connections are or the impedance mismatch is actually handled really well.

Craig: Yeah. Yeah. Uh, and what was it about this group that gave you, uh, enough confidence to join the board?

Peeyush: Uh, well.

Peeyush: You know, it is fascinating because these days, the thing which I end up feeling which makes a winning combination is two things. Um, one is very, very strong clarity about what is the problem which the team wants to solve. Right. Uh, that clarity that this problem and the problem has to be worth solving. But that clarity rather than there's so many things possible that you can go try everything like we talked about, like 11 labs, you know, not being a competitor, but something we could use. It comes from a clarity that, hey, this is the problem you're solving. Let's use everything which everybody in the world is doing for other problems. So very strong clarity. I felt that they had amazing clarity and it is starting to show in the traction they are getting on the two sides. And the second thing is the quality of the, uh, you know, the, the team technical and sales. Um, you know, it's not surprising. I mean, these guys are based out of Bangalore and, you know, uh, in Bangalore as an ecosystem has started to finally spin up. I mean, you know, it's it's not it's second to Silicon Valley. I mean, it's not Silicon Valley, but second only to Silicon Valley, right? And I saw amazing collection of these, like, you know, whatever, uh, engineers they are. When I was talking to them, I was like, wow, this is really the bar. Getting such a collection of people in one place in Silicon Valley would actually take, uh, significant effort. And I felt like you are focused on the problem and you have the right people in your camp. So, you know, it's all about execution now. So I think that that is what actually, uh, you know, gave me that confidence.

Craig: Yeah. Um, can you talk at all about the other, uh, companies coming out of the incubator, or do you really want to restrict yourself to.

Peeyush: Uh, give me a few months?

Peeyush: I think the other one is, like, just and not not for any other reason. I'm not being coy. It's because just today, as a matter of fact, I came out of a two hour conversation of like, should we do this? Or should we do that? So we are in the like, what problem should we solve phase of it right now? Uh, I think that, uh, we will, uh, sometime this week be able to at least put a stake in the ground and then start building a prototype. So give me give me a few months, I will, I promise I'll be back.

Craig: Yeah. And, uh, how does someone use Nurix? I mean, um, it's it's a SaaS product. Uh, do they, uh, is there a I mean, how is it priced? Is there a self-serve, uh, element to it on on the web?

Peeyush: Yeah. Uh, if you go to the web, you can, uh, experience the the real human likeness of the voice experience, which I was talking about, by the way, I think we are the only voice agent company in the world which puts it out on the web because we are so confident we have the best solution in the world. So you can go and you can experience like you can say, hey, uh, like, I don't know, a collections agent who's calling you, saying, hey, are you going to pay your credit card bill? And you can have a conversation saying, well, you know, uh, I'm living paycheck to paycheck. What do I do now? Right? And you can, like, talk through it, and it actually will have a conversation with you. So that is one way. But but as a business, we are actually going to launch our platform. So far all the deals are like, you know, uh, we go in, as I said, like, you know, forward deployed engineers go in and kind of build things out. That's how we have gotten all the deployments so far. But we have been taking that learning and we are building a platform whereby in which you will see, I think when the demo happens, maybe they'll be able to give you a demo of, uh, you know, the platform itself, a sneak peek, uh, but you can choose various kind of agent templates, which we have, like, you know, you want a customer service agent versus sales agent, like, you can choose various templates or you can create your own, like you say, okay, this is my agent.

Peeyush: And this agent will connect to these particular endpoints. This is my rag setup and this is my, uh, you know, we connect to 150 different kind of tools in the backend. So these are 100 tools. Or you can create your own custom, uh, MCP server which we can connect to. And, you know, all of that. And then you can go try it out that you can try out. And of course, you know, there is, uh, this is something we have learned and a lot of industry is learning is like there's a lot of, uh, work which has to be done between standing up an agent and making it run in production and be, you know, face of your business. So but we do all of that in the platform. You will see. Definitely will give you a sense of how to stand one up.

Craig: Yeah. And then, uh, to integrate it into another solution. It's an API call.

Peeyush: To integrate into another solution. It is going to be an API call. Uh, we have like 150 different type of solutions, ticketing systems and all, which we integrate it right out of the bat. Uh, but we also support MCP protocols. So if you have a different, uh, service and you have MCP server, which can be called by the LLM, we will do that. Or uh, if you want a custom solution, then we can do code generation and we can call that API that way.

Craig: Yeah. And is it, uh, how how expensive is it? I'm just thinking for myself. I'm building a a chatbot so you can ask about all of the podcasts that I've had. Uh, yeah.

Peeyush: So, uh, that is something which, uh, maybe the sales team can tell you, uh, specifically, depending on your case. Right now, we are doing a deal by deal. Uh, so, uh, depending on on how involved your, uh, product is, and, you know, they'll be I'm happy to connect you with, uh, somebody there. Um, it's, you know, it's not going to be super expensive. We are. I mean, this is the thing which we are seeing that having a human on the other side is more expensive and also more error prone sometimes. But, uh, I'm happy to get you, uh, you know, your exact scenario looked at. I think you will. You will, you will like it.

Craig: Um, yeah. No, I'll go on the website after this and take a look.

Peeyush: Yeah. Please. Uh, yeah. Let me know if there's something which you feel is not working or anything like, you know, I would love any feedback so I can pass it on to the team.

Craig: Is there anything that I haven't asked that you think listeners should know?

Peeyush: Uh, no, I think, I mean, you know, the biggest thing which I will leave you with is which you will see for yourself that it's amazing voice experience, and we've invested a lot in making sure it is human like and low latency. Um, and the other thing is it's proven technology in the sense that we have, uh, you know, uh, over a quarter million calls happening through it right now in, uh, you know, uh, therefore, the company is growing at a very rapid clip. Uh, so I don't have a whole lot to add. Uh, it's amazing technology. And these are amazing times we live in. I mean, even scaling the thing which I was talking about, like, just seeing how this thing needs to scale is, like, fascinating technical problems. So we are having a lot of fun here.

Craig: Yeah. No, it's an exciting world. So, um, I'm looking forward to the day when, uh, when everyone is using Neurex.

Peeyush: And I thank you, Craig, so am I. Yeah. No more hold music and telling another agent all your history as you get transferred.

Sonix is the world’s most advanced automated transcription, translation, and subtitling platform. Fast, accurate, and affordable.

Automatically convert your mp3 files to text (txt file), Microsoft Word (docx file), and SubRip Subtitle (srt file) in minutes.

Sonix has many features that you'd love including collaboration tools, share transcripts, transcribe multiple languages, advanced search, and easily transcribe your Zoom meetings. Try Sonix for free today.