RSS feed
Andrew Warner: How cool is this? You’re about to meet a broker who got sick of making cold calls, so he created an AI automation that made calls for him and it worked, so he started selling it as a service to other brokers. And that took off. And so today he’s creating software that will automate it for any broker who wants to sign up.
This story is so good because it could be replicated in so many other industries, not just brokers. Listen up. Yevgeniy Matsay and Aidan Richards are the co-founders of Rezora, which does outbound cold calls for real estate brokers
presented by Zapier, the AI automation company. You guys started selling. Gimme the revenue from the first few days,
Aidan Richards: 40,040 days.
Andrew Warner: What do people pay for at that time?
Yevgeniy Matsay: So we would charge anywhere from an initial thousand to $2,500 setup fee, depending on the complexity and workflow, plus an ongoing $500 month monthly fee, plus 20 cents per conversational minute that the AI did as well.
Andrew Warner: How much of it was working
Yevgeniy Matsay: in term? Everything was, was working. In general, but it was, I want to say first the demand was too high, so the whole entire solution was not scalable long term and at the end of the day it was just a GPT.
Andrew Warner: Mm-hmm.
Yevgeniy Matsay: With the Texas speech model.
Andrew Warner: Let’s go back, understand how you got here.
You of Guinea were doing real estate. What’d you do in real estate that led you to find this problem?
Yevgeniy Matsay: Most of my day, consistent when I was a real estate agent, actually consisted of me waking up. Getting into the office at around 8:00 AM 8:30 AM having my cups of coffee and going into a tiny room and start cold calling homeowners at 9:00 AM have my lunch break at 12 or one, and then continue cold calling until four or 5:00 PM Cold.
Hoping and praying. Mm-hmm. That I. Can get a lead and uh, get a listing appointment.
Andrew Warner: Wait, were you just calling strangers in a neighborhood and saying, can I li list your property?
Yevgeniy Matsay: So you could do, that’s one way to do it, but my specialty was actually expired listing leads. So what that is, is homeowners who tried selling what a realtor before and their listing went expired, meaning that it didn’t sell.
So I would cold call those people because they have a higher chance of relisting.
Andrew Warner: That makes sense. I imagine that you must have gotten a big conversion rate, right? These are people who tried to sell their home, it didn’t work. They might not be happy with their current real estate person. Boom, you come in.
Yevgeniy Matsay: Unfortunately, it wasn’t that easy. Uh, I would say they have a typical conversion rate as any other cold call, especially since they have, they had a very negative experience with the whole entire process, not being able to list, I mean, not being able to sell their home with an agent before, and they’re more.
Reserved to that idea of relisting. Again, even if a person is desperate, they just don’t want to deal, they just, since that, their agent basically, uh, screwed them over. They want to deal with another agent again as well.
Andrew Warner: What was your conversion rate back then when you were making these calls?
Yevgeniy Matsay: I want, what do I wanna say?
I don’t have a hard metric, but if I were to estimate one to 2%.
Andrew Warner: 1%, okay. That sounds pretty good. No. A hundred calls. You’re spending all day making calls. Not good. You were still frustrated by it. Why?
Yevgeniy Matsay: Yeah. It’s not like I would make a hundred calls and then boom, 1% conversion. First, you have to actually get connected to a person that picks up on you.
Okay? That’s not where you can call 200 people before you actually get connected to someone that is the correct, uh, homeowner.
Andrew Warner: Okay.
Yevgeniy Matsay: And it’s not like. It’s not like it was a hard set, uh, one, 2%. It’s not like I would call, let’s say a thousand people and definitely would get 10 listing appointments. It’s all very variable.
Andrew Warner: How did you decide to start with software?
Yevgeniy Matsay: I actually started real estate straight out of college and I graduated in computer science and cybersecurity.
Andrew Warner: Mm-hmm.
Yevgeniy Matsay: And, and I just wanted to dip my toes into real estate. Always just wanted to give it a try, but honestly, after two years of cold calling, cold calling, I got very fed up with it.
It was very draining.
Andrew Warner: Yeah.
Yevgeniy Matsay: And I couldn’t take it anymore. And this was at the time when AI voice agents were becoming a thing. So I’m like, oh wait, I can definitely implement this, this into my workflow, because why wouldn’t I? Why wouldn’t an AI agent, AI agent be able to just call and qualify? So I used a couple of platforms.
All of them suck because first of all, this is when AI voice agents were first becoming a thing. All, all of them were not the best compared to what they are now. But second of all. There was no model that was designed specifically for sales conversations, phone conversations. So I’m hyper realistic or too, so to speak.
And that’s when I got the idea of, oh wait, let me just do this for myself. Let make it, let me at least prompt it out to be very realistic or very rigid workflow. And when I did that, I actually got my first listing appointment, went to the first day,
Andrew Warner: wait a minute, your first. AI voice agent got you a sale within a day,
Yevgeniy Matsay: not a sale.
A listing appointment?
Andrew Warner: Yes. A listing. A listing within a day. Yes. And that’s the thing that you were getting only 1%, uh, response on. Right. That was the 1% conversion rate from the calls?
Yevgeniy Matsay: Correct.
Andrew Warner: Okay. Correct. Alright, that’s exciting. So then how far did you get with that?
Yevgeniy Matsay: So first of all, I wanted to optimize to make it sound as much, uh, as best as possible.
So what I did is I kept, um. This is when I was just getting comfortable with LMS and large, uh, and machine learning, all that stuff. And I realized with prompt that you can only take it so
Aidan Richards: far.
Yevgeniy Matsay: But, uh, I actually thought to myself, wait, I didn’t get that far with it. ’cause I thought, so wait, what if other people want something like this?
And that’s when we launched Facebook ads and that’s when it took off. And I even didn’t have time to listings or run it for myself whatsoever.
Andrew Warner: Okay. So you are immediately thinking, I’ve gotta create this as software. I would think Genny, that you would think, why don’t I become the real estate king of this whole neighborhood?
I’m going to do nothing but automate this and I’m going to get myself all kinds of listings and then I’ll bring people in under me who are going to run these listings for me and I’m gonna make a ton in real estate. Why not think that way?
Yevgeniy Matsay: That’s a very good question, and I’ll be completely honest with you.
I just got fed up with it. Uh, there was no. One thing about my personality type, I love, uh, implementing new things, working on new things, and real estate is the complete opposite of that. It is the same repetitive thing and it has been that way for over 20, 30 years.
Andrew Warner: I see you’re a software guy. You’re a problem solver.
You’re not a real estate. Let’s make money, let’s make deals type of person. You just got into that ’cause you wanted to make a little bit of money for yourself to get started.
Yevgeniy Matsay: Correct? Don’t get me wrong, I was doing. I was doing great when it came to real estate. First two years, I learned a lot. I learned it taught me a lot specifically about business negotiations, all these things.
I did excellent in it, but just in the two year mark, I just couldn’t take it anymore because there was no room for, oh, let’s try this new system. Let’s try. I saw that everything in real estate, and you could probably a ask most realtors, they’ll say the same thing. All the processes are the exact same thing as they were 30 years ago.
So.
Andrew Warner: And I could see some people might enjoy that, that this is an area that they could keep improving on. Yeah, of course. This is something that they could, uh, just keep building on because it’s not going to change dramatically day to day the way software might. You, on the other hand said, all right, I’m going into software.
You started immediately thinking about how to turn this into software, how long before you got your first customer?
Yevgeniy Matsay: So I wanna say I took at least a good month on it before I even decide to do Facebook ads or anything.
Andrew Warner: Mm-hmm.
Yevgeniy Matsay: Just to, ’cause there’s a plethora of, uh, agent types people need. So expired listing it’s buyers, et cetera.
But I wanna say as soon as we launched the Facebook ad campaign, it took us less than, what was it? Four days I think. Yeah. I think it was less than four days to get our first customer. Then it was, it was the easiest. ’cause I’ve never done something like this before and it was the, I was so shocked of how easy it, it was take leads and to convert them into paying customers.
’cause we did a paper lead campaign.
Andrew Warner: And so that means that you were using their lead capture form right on on meta?
Yevgeniy Matsay: Correct.
Andrew Warner: You work, basically, you didn’t need to have a landing page, you didn’t need to have anything built out. All you needed to do was have an ad and a lead capture form that meta put together for you.
S That’s impressive.
Yevgeniy Matsay: Correct.
Andrew Warner: Who created the ad?
Yevgeniy Matsay: I mean, I did.
Andrew Warner: What was the ad? Do you remember? Describe it.
Yevgeniy Matsay: It was a video recording with the wave loop of the AI talking to a lead. And, uh, that’s pretty much it. And, uh, with a call to action.
Andrew Warner: I see it’s basically doing cold calling. There’s not even a human being.
There’s not someone acting like a realtor. It’s just a wave of a person. Getting a phone call from a, from a, like, not even a realtor. It was an ai.
Yevgeniy Matsay: Yes.
Andrew Warner: Damn. That’s, and they couldn’t tell. They could not tell because it sounded so good.
Yevgeniy Matsay: Yeah.
Andrew Warner: All right.
Yevgeniy Matsay: Yes. I mean, of course some people are gonna be able to tell, some other won’t.
You’re gonna obviously realize it’s a little, it’s a little monotone, but for the most part, that’s why people clicked on the ad.
Andrew Warner: So then how do you go from them filling in their information on Meta’s pages to giving you some cash?
Yevgeniy Matsay: Of course, honestly, I didn’t even look at it at the way, oh, uh, for them to give me cash, it would be more so I will call them because on the capture leave form, they would basically also schedule an appointment.
So I would call them confirm, uh, the Google meet, we would have, get on the Google meet with them, explain to them what the system is, how it works. If it is even for them, that was the main thing because there were some realtors that were completely new in the game or have never done cold calling, and they would want this, and I would tell them, no, this is not for you.
Why? Because they wouldn’t be, they wouldn’t know how to handle those leads when it came time for the listing appointments, so they’d be wasting money. So it was more so of, listen, this is what it can do. If you’re already calling or you have someone calling on your be uh, uh, on your behalf, this can replace it.
All it is, it’s ai. It’s also not perfect. It can make mistakes. Of course. That’s all I have to offer. And shockingly enough, we had above 80% conversion rate.
Andrew Warner: But it’s you actually doing, um, Google Meet with them, walking them through this and closing the sale yourself?
Yevgeniy Matsay: Correct.
Andrew Warner: All right. Was the software ready to go to actually take care of them once they paid?
Yevgeniy Matsay: That’s the thing I would tell them, listen, since we are having a huge backlog, it’ll be anywhere from four to five weeks wait time.
Andrew Warner: Okay. And what were you planning on doing per person? And you could actually set them up within those four to five weeks, or was this just a starting mechanism? You could, because you were doing personally each one.
You were custom coding each person.
Yevgeniy Matsay: Yes, exactly. I was, uh, it’s not even custom calling at that point. It was just custom prompting for each one and a specific workflows. But, uh, it was generally I needed the four or five weeks because we already ha we were having customers, uh, one after the other. I do a lot of tests.
I can’t, if someone even give pays for our product. The worst thing you can possibly do in my opinion, is give them an okay version and not a perfect version. Okay. So a lot of that time went to me testing it a lot because if someone trusted with their money, it’s your responsibility to actually deliver the best product.
Andrew Warner: Okay. So tell me, what’s the workflow? What did you use to create this for them?
Yevgeniy Matsay: At the time I was using Vapi to just prompt it out. Have the, the LM connected to the text tope model and the transcriber. Then I also had a front, uh, front end, um, connected to Vapi, API, where we just showed the user the recordings, appointments, and that’s pretty much it.
Andrew Warner: Let’s, yeah, let’s talk about what you, how you set this up. What was the workflow that you set up for them?
Yevgeniy Matsay: So I would use a low code automation tool, um, such as Zapier.
Andrew Warner: Mm-hmm.
Yevgeniy Matsay: And it was a very janky, uh, the whole entire ecosystem overall. Not the automation tool, but the whole entire ecosystem, um, was not a full backend like you would expect, like a full stack web app.
It was just something to have a workflow running for these customers and mm-hmm. Basically see if this is what people wanted. But it was not my intention to fully deploy and have this as the main, uh, as the main code, so to speak.
Andrew Warner: I get it. You know what’s interesting though, essentially what you’re telling me is.
I could probably do something like this for people right now using, let’s say, Zapier, where I create an individual workflow for a customer that makes outbound calls for them, that is using nothing but Zapier and Zay, and what other tools would I be able to use to build this for people individually?
Yevgeniy Matsay: I think that you’re gonna be pretty much set to go with Vapi, Zapier, and maybe a CRM connection because Zapier can connect to people’s CRM directly.
Andrew Warner: Okay,
Yevgeniy Matsay: so.
Andrew Warner: So they use clothes or HubSpot or whatever. You pull their contacts out of there. There’s a zap that then connects with Vapi. Vapi uses, uh, is is the voice agent. Zapier would make the call out on behalf of the real estate broker. Mm-hmm. And then say, do you wanna book this meeting? If they do, how does the meeting get booked?
How does it get on the calendar of the real estate person?
Yevgeniy Matsay: So on Vapi, you have a tool call or you can make your own tool call of course, of connecting it to cal.com or another calendar, uh, app.
Andrew Warner: Okay.
Yevgeniy Matsay: And, and that will automatically, once you configure it, I can’t, I won’t go into the details ’cause it is very mundane of how to fully set it up, but in directly books into the person’s calendar.
Schedules it. Yep. And they’ll get a Google, Google notification, Hey, you have a meeting booked.
Andrew Warner: I see. So that’s what Aiden was saying earlier. Aiden was saying earlier, look, a lot of people are doing this as agencies. You’re saying this is essentially what you did in the beginning before you created SaaS that was self-serve.
But the big takeaway before we continue with your story is it seems like there’s an opportunity for somebody to go and do this right now to say, you know what? I’m going to do this for plumbers. These guys you gaining and 80 Aiden are doing this? Absolutely. This realtors, I’m gonna do it for plumbers.
Everybody’s got some kind of plumbing need that they need, but they don’t have time to call. I’m gonna do outbound calls on behalf of plumbers and I’ll do it for them as a custom setup for every single company. Maybe a thousand bucks a pop. And if it’s not plumbers, maybe it’s electrician, probably plumbing, actually, as I think about it, there’s more plumbing needs than there is anything else.
That’s the kind of stuff that we’re talking. Oh, I know. What else? Um. Lawn and garden. Do you need some landscaping work done? I happen to be in the neighborhood. Got it. That’s essentially what you’re saying can be done
Yevgeniy Matsay: right,
Andrew Warner: Aiden? That’s what you said. Most people do this as agencies. You guys start as agencies, but at some point you’ve gained, you said, I know I need this to be SaaS.
Am I understanding it right?
Yevgeniy Matsay: Yeah, it’s SaaS, but it’s also development of an actual large language model. That has a high enough EQ for phone and sales conversations. Got it. That was the biggest thing, not the agency model. Getting ring of the agency model was the icing on the cake. But the main thing is there’s no LLM, there’s no chat GPT, there’s no CLA that is specifically meant to respond for sales or humanlike conversations.
So how do you do that too Verbose.
Andrew Warner: How do
Yevgeniy Matsay: you do fine tuning?
Andrew Warner: You personally would fine
Yevgeniy Matsay: tune. Not back then. So that’s when after six weeks of launch mm-hmm. That’s when I stopped and I worked on the development of, uh, actually making the LM sound ultra realistic and also condensing down from an agency model to something people can just launch right away, which makes it cheaper for the end consumer as well.
Right. But at the same time, more scalable for us. But currently what we’re doing is. We take real conversations. We turn that into fine tuning data to be specific, supervised fine tuning data, and we run supervised fine tuning on a large language model, which in end results in the language model actually sounded more human and more, has more quote unquote salesmanship in it to responses.
Andrew Warner: I got it. Do you think that the agency model can ever, or at this point with technology as it is today, use any of that fine tuning or you think that’s a limitation of the, uh, automated workflows that we’re talking about? Oh
Yevgeniy Matsay: yeah. So agencies right now, they’re not. And I don’t mean this in a bad way, but they’re not the most tech savvy.
Yep. These are just people doing automatic auto mutuals through Zapier, connecting it through an API, whatever, whatever.
Andrew Warner: If I were gonna do this for plumbers, if I were gonna do this for landscapers, would I be able to fine tune the model, fine tune the way that the AI voice agent talks using recordings of other calls?
Or do you think that’s a limitation of that model? I could.
Yevgeniy Matsay: No, no. It’s, anyone can fine tune. Anybody can fine tune, but you have to know what you’re doing. That’s the thing. It’s not like, got it. By fine tuning, I don’t mean plum, I mean data orchestration of current audio recordings. Mm-hmm. Transcribed. So you take the audio recording, you transcribe it, then you run it through.
And judge LM that grade every single conversation. Make sure there’s no artifacts. Then you also assign a scaler score to each, uh, conversation. So you rank, uh, on different parameters. Those d different parameters are added up. There’s a scaler score, and then you go through each conversation. Okay. And you choose which ones get ended up in the supervised fine tuning data set, and that’s when you run your fine tuning cycles.
But there’s a lot of nuances to it. You have to know like the learning factor of what to run it out, that epochs all these things. Okay. It’s, uh, it comes through a lot of trial and error, you learning these things and interestingly enough, I was telling Aiden this the other day, there’s literally no research out there on this topic.
Zero.
Andrew Warner: I could understand that, and I’m getting what you’re saying. Somehow we need to analyze real conversations and see what makes them magical, what makes them great so that we can recreate them through these voice agents. And that’s what you’re working on. And you’re saying it’s hard even at your stage, it’s possible even at the stage of somebody who’s doing some kind of, um, coordination.
Correct. Alright. You then. Getting sales. How do you transition from doing this? Like an agency owner who’s customizing for each person to a SaaS builder? What’s the next step?
Yevgeniy Matsay: Well, the transition wasn’t that hard for me ’cause that’s, I knew going in, that’s what I wanted to do.
Andrew Warner: Okay.
Yevgeniy Matsay: This was just meant to confirm the market for me.
Andrew Warner: Okay.
Yevgeniy Matsay: This was meant to see, should I even allocate all my time and energy into this? And once we did our six week run, I got that confirmation. I told my customers at the time, listen, we’re pausing during the time and I just got to work on, um, coding a whole entire front end backend testing different flows and, and doing a lot of research of how large language models work because there’s all, this is very new.
Sure, there’s still some studies on machine learning algorithms, but it. Took up a lot of research and it was a lot of brainstorming thinking, okay, there’s no solution on the market right now where it allows a non-technical user to launch their AI agent and get it going in less than 10 minutes. There’s absolutely nothing.
So it was just a lot of trial and error of testing and how to do it and. That’s all I basically did. So I went from an agency, owner agency, you know, AI agents to right away I was excited to start thinking, okay, how can I streamline this whole process? It got me ready, ramped up and going.
Andrew Warner: Okay.
Yevgeniy Matsay: The idea of it,
Andrew Warner: tell me how you and Aiden connected then.
Yevgeniy Matsay: Absolutely. So at the time I was coding, I still am over 12 hours a day and I was think to myself. Oh shit, how am I gonna even be able to onboard customers? How am I be able to sort out business nuances, just handle everything else? Because just a loan coding takes up forever. So I thought to him, maybe I do, I do need a co-founder.
I went on the Y Combinator co-founder matching platform. I just want to see like, you know, maybe there was, um, like-minded individuals out there.
Aidan Richards: Can I just put my profile,
Yevgeniy Matsay: profile out there? I got. Message from a few people did interviews with them. Uh, and I just think to myself, yeah, definitely not. Then Aiden reached out to me.
We did an interview. We instantly hit it off. We talked, uh, for our first Zoom meeting or our Google meet meeting, we talked for hours, not hours, but more than expected. We met in person and we ended up talking for hours, and it was an instant click.
Andrew Warner: Why? Why did you click with him?
Yevgeniy Matsay: W his hair. Yeah. Yeah. His hair was just so amazing.
He, I clicked on him because he was. Very, not very, I don’t wanna say very direct, but he knew what he was talking about. He is very motivated, very ambitious and has that drive. That’s one of the most important thing, uh, things in a person is drive and ambition and motivation. Without that, I don’t care how smart you are, how what you know how to do, you’re not gonna get anywhere.
And Aiden had 200% of all of that.
Andrew Warner: What was the role breakdown going to be? Aiden, let’s bring you in here.
Aidan Richards: Um hmm. Yeah, GU is pretty much responsible for everything on the product and engineering side, as you’ve just heard. And then of course, I kind of, you know, give my feedback and we, we collaborate on where we want the product to head and what we think is next.
But obviously he has a better understanding of, you know, what’s possible and what should be done and what comes next. Uh, so my responsibility really lie on the sales and marketing side, so I’m doing all of the outreach and kind of brand creation, brand promotion. Then handling everything on the operations side.
Things around like, you know, legal and setting up new software and making sure that we’re kind of maintaining relationships with people that we need both on the client side and just regular colleagues like that.
Andrew Warner: And people like me. I mean, you basically messaged me exactly endlessly and when I said it’s a good fit, you kept sticking on me until we f found a way to make it work.
That’s, that’s, yeah, exactly. That’s why
Yevgeniy Matsay: I love him.
Andrew Warner: I do respect that. I do like that a lot. Um, what about the ads? Are you taking that on now, Aiden?
Aidan Richards: We’re not running any ads right now. We’re launching access to our wait list tomorrow, and that’s gonna be a little bit of a smaller campaign just in terms of kind of act, activating everybody that we’ve already spoken to and then, uh, kind of getting the ball rolling on our initial go-to-market strategy.
We do want to run some ads in the next few weeks, but we’re still kind of trying to figure out exactly where they’re gonna fit in terms of resource allocation and time.
Yevgeniy Matsay: Such as SEO, uh, everything else piled in on top of the ads,
Andrew Warner: the original, uh, people who are paying you a thousand dollars for the service, are they still paying you?
Is that part of the revenue that you’re bringing in?
Yevgeniy Matsay: No. No. So I got six. Oh yeah. I stopped it all because, uh, it was a lot of work just to. I’ll put it like this. Let’s say I have a AI voice agent per you, and you needed something tweaked. Mm-hmm. That means you come to me, we have to have a meeting, and then I have to go over everything Exactly.
Which you need specifically fixed or change all these things. Now imagine with 40 plus people, you don’t have time to do anything else.
Andrew Warner: I see you. So you didn’t even set them up. How many people did you actually set up?
Yevgeniy Matsay: No. No. I set them all up. That’s thing. So if
Andrew Warner: you’re setting up set all up, once you set up, isn’t it ready to just go on its own?
Yevgeniy Matsay: Not necessarily, because like I said, people, a lot of people need tweaks. A lot of people need changes and there was no customization to it. Our front, our front dashboard, the only thing you could see was audio recordings and uh, yeah, just audio recordings and that’s it. You couldn’t tweak it whatsoever.
There was no customizability at all for the end user.
Andrew Warner: What type of tweaks were people asking for?
Yevgeniy Matsay: I wanted to say this instead of that. Um. Can, uh, can it go through, uh, can it go, go through tasks 1, 2, 3, but skip five instead of, uh, things like this. It was just everyone wanted such a different style. And people, once they hear it, everyone, even if it got the appointment, people want.
Improvement. Oh, but can I do this? Can I do that? Can I do this? And I just, and that’s when I talked to myself, oh shit, okay. I need a platform where people can do this, everything themselves, but they can, they don’t have to have the technical knowledge to do so. And my mind frame at the time was, why isn’t there anything like this right now?
That’s what got me the most excited.
Andrew Warner: I see. And if you were running an agency, you’d be able to keep servicing them. We’re not talking about big, complicated tweaks, it’s just little tweaks. But it does take time to interact with them. It does take time to go and do the work yourself.
Yevgeniy Matsay: No, it’s not even, it’s not even little tweaks because some people would want to a whole redo of, oh, okay.
I don’t want, uh, it’s not even a whole redo. Let’s say for example, I want a mortgage guy wants an agent. That means I have to go, I have to research the scripts. I have to tell him, send me his scripts. But I would never, even when I was doing the agency model, I would never script my AI agents. I would never say, uh, step one, say parentheses 1, 2, 3, 4, 5, 6.
I would never script that. I would actually instruct it step by step. So that’s what takes up a lot of time and then back testing that or testing it non until it sounds good.
Andrew Warner: I got it. All right. Do you, I do still think though, this would work as an agency and someone who did it as an agency.
Yevgeniy Matsay: No, it would,
Andrew Warner: right.
If you’re, if you’re looking at $40,000 within 40 days, my hunch is that you’d probably be able to do 50,000 a month in agency business with this. Right. Recurring revenue. Just keep taking of your customers deal churn by bringing in some new ones. It would just mean constantly tweaking people’s, uh, automations.
Yevgeniy Matsay: Yes, absolutely. And that’s how a lot of companies do and they’re very successful, uh, with us. Why we couldn’t, we weren’t able to is because usually these ai, AI agencies, they have a team or it’s two or three people and they’re constantly tweaking it. They’re listen to their customers, they tweak it, whatever, whatever.
So it’s ongoing work, but it’s go it think about almost like a marketing agency, right? Yeah. A marketing agency is running ads. They’re gonna be constantly tweaking ads for the person. Like the person say, no, I don’t like this. Or, the type of customer I’m bringing in is not good. So they’re gonna be tweaking, is the exact same concept.
Andrew Warner: And the, the challenge also if, if you were running an agency is somebody is going to sify this, it’s just a, it’s just a natural next step. And so an agency doing this would have to keep running fast because there would be some, someone in the background who’s coming in. Tell me about how you turn this into, into software.
Yevgeniy Matsay: Oh, um, sure. So I broke it down to the bare. I didn’t even break it down to the bare bone. I want to say, I thought to myself of how I can let users deploy their own AI voice agent that is good that they don’t have to prompt out, because prompting is a full extension in itself. So that’s the first thing I thought, and the first thought that came to my mind is, of course you need a
Andrew Warner: dashboard, sign up.
Yevgeniy Matsay: So what I did, I started, um, coding and just testing a lot. And one of the first things we did was, um, build out individual AI agents mm-hmm. That we already know people wanted. So specifically an expired listing, uh, wait, say agent, a host, uh, real estate wholesale agent. All these things, but these AI voice agents are connected to our fine tuned LM which is our biggest mode because anyone can go ahead and, uh, prompt out a few agents and whatnot and, uh, sify as well.
So what we did, we fine tuned the LM, we built out a bunch of agents
Andrew Warner: and we already know
Yevgeniy Matsay: people want, and we put those agents on the platform. We then expose those agents, uh, those agent parameters of. The prompt, the voice styles, the type of voice, all these things on the platform itself. So the user has the option to choose, oh, I don’t like this voice.
Okay, cool. You can change the voice, change the speed of the voice, all of these things. And also at the same time, input parameters into the AI agent. For example, you can name your AI voice agent. You can give a background about yourself, and mind you, not through prompting, but just through text input that we had exposed on our website.
You can hit deploy, then you can launch your own campaign and it’ll start calling for you. So everything is done. And this is all connected via backend of course. So that’s how we turn it from an agency model to a, uh, SaaS model basically, of thinking it, what’s the best way to let, let it be customizable, but at the same time sound exceptionally good.
And that’s where the fine tuning also comes in.
Andrew Warner: Talk to me about that, about the work involved in it. I think when I talked to you, it seemed like, well, there’s Claude code, there’s cursor, everything’s so easy. And you said, yeah, it’s easier, but I’m still spending 12 hours a day working. I’ve never worked so hard in my life.
What’s making it easy? And then where’s the difficulty?
Yevgeniy Matsay: Okay, so this is, uh, if we’re just talking specifically about full stack development, right?
Andrew Warner: Sure.
Yevgeniy Matsay: The thing that people have to understand is cloud. With claw code or any of these coding tools, they’re just that, they’re tools. If you don’t know how to swing a hammer, the nails could go in a bent.
Yeah. If you know how to swing a hammer, the nails going in straight, right? Mm-hmm. And is the, the exact thing, uh, why I say that? Sure. You can tell, you can vibe, code with clock or you could tell, oh, please implement this. And it’ll build you some things up. The thing is, if you don’t understand what you’re coding, if you don’t know the framework, if you don’t know the architecture or the workflows behind it, or that need to be in place, you’re gonna have a lot of error.
You’re gonna have a lot of bugs, and you’re gonna have a lot of issues with it. So clock code is exceptionally excellent at if you tell it specifically out of what you need implemented, how you need it implemented. You have a whole plan in place. Claude code is exceptional for that. But if a person doesn’t know the framework, doesn’t know how a connection from a to be happens or how it should look like, then they wouldn’t even know what to look for when Claude, if Claude generate good code or back code as well.
Andrew Warner: Talk to me about what’s possible today. I remember talking to Gary Tan, uh, president of Y Combinator, and he basically said, look, smaller teams are able to create so much more than they’ve ever done before. It feels like that’s where you are right now. You’re a one person operation creating the software.
Yevgeniy Matsay: Uh, yeah, no, absolutely. You can definitely create a, I can’t imagine doing this all manually.
Andrew Warner: Mm-hmm.
Yevgeniy Matsay: I really can’t. So, think about, think about it like this. Either you could write the essay yourself.
Andrew Warner: Yeah.
Yevgeniy Matsay: Or you can get, uh. GPT write that say for you, and then you make tweaks to it to make sure it sounds good, right?
Andrew Warner: Yeah.
Yevgeniy Matsay: So I can’t imagine without them that I would be to do, be able to do it at a scale that I have done it at. Yes, absolutely. People could do a lot more than they kind of even a year ago.
Andrew Warner: I see. So it’s just, if you know what to ask for, you can get it and it’s faster than doing it yourself, but you still need to know what to ask for, is what you’re saying.
Yevgeniy Matsay: Yes. You have to know how the art, the architecture, should be of that set framework or code, whatever you’re working on.
Andrew Warner: All right, so right now, how much of the $40,000 did you guys get to keep you? Did 40,000 in sales, how much of it did you get?
Yevgeniy Matsay: I’m going to say we kept straight profit. 34. Around 34,000 bucks.
Andrew Warner: Okay.
Yevgeniy Matsay: $35,000.
Andrew Warner: What kept you from keeping the rest and what allowed you to keep that part?
Yevgeniy Matsay: Facebook ads. That was basically our only,
Andrew Warner: oh, that’s it. So you did get paid, you built the automations, you just couldn’t take on more automations for more customers.
Yevgeniy Matsay: Yeah.
Andrew Warner: I see.
Yevgeniy Matsay: And I just, I, and I was itching. I was itching.
So finally, okay, lemme start. Fine too. Let me start this whole entire, I was literally trying to already start that.
Andrew Warner: And what about the people who paid you and needed tweaks? Were you still tweaking it or did you finish, you say, look, I’m not doing it anymore. No, I was,
Yevgeniy Matsay: I was still tweaking it for them and um, I still took care of them until I told them, Hey, listen, I’m gonna build this out, rebuild and make it a lot better.
You obviously get a, uh, you’re, you’re gonna obviously get, I’m say you’re gonna get a free, free few months, all of these things when we relaunch. Okay.
Andrew Warner: Got it.
Yevgeniy Matsay: And it’s gonna sound a lot better for you as well.
Andrew Warner: It does seem like real estate brokers are willing to try new technology more than others. I don’t know about plumbers, but I do know that when there’s a new tablet, I would see it on a real estate broker’s desk.
There’s, when there’s some new app, they’re likely to play with it and even talk to you about it. I don’t know what it is. I don’t know if it’s, they’re all entrepreneurs. I don’t know if they have a lot of time on their hands. What do you think it is?
Yevgeniy Matsay: You know what? I’ll be honest with you, it’s a, it’s a very, it’s a 50 50 mix.
Some real estate. Brokers agents, especially the older ones.
Andrew Warner: Mm-hmm.
Yevgeniy Matsay: They’re very against anything new. Okay. It’s uh, it’s like if you breed up, you personally offend them, essentially, while others are very excited to try. And currently what’s happening, brokerages across the United States real estate brokerages, and this was prominent in my brokerage two, was now they have classes on ai.
They have classes of how to utilize for your business. So. So I guess that’s also what helped us out a a lot too, was since a lot of these realtors were their own brokers, were telling them, listen, you have to utilize ai, you have to utilize ai, uh, AI’s textbooks, best thing. They’re being constantly set this.
I guess that also helped with, uh, onboarding the first, uh, first users that we ever onboarded.
Andrew Warner: I see. I do get that too. They have always been really good at training. They’ve always been good at doing, um. Motivational speakers, and so now they’re teaching people how to do ai. All right. Why’d you come up with a name?
Let’s close it out without, why’d you come up? How’d you come up with a name?
Yevgeniy Matsay: Re is, of course, real estate. Zora is in a lot of Slavic languages, a new beginnings, and that’s when I was, uh, finishing real estate and going into this new field essentially.
Andrew Warner: I see. All right. Fantastic. Thank you gentlemen. Good luck.
If I
Yevgeniy Matsay: Thank you so much, much, Andrew. Thank you for having us.
