Poetic raises $50M to automate complex enterprise workflows at 99%+ accuracy, backed by Founders Fund and Kleiner Perkins

Speaker 13: What if

Speaker 2: forks not look like these. We know how to make good ads.

Speaker 1: What if forks were spoons?

Speaker 2: What if forks were spoons?

Speaker 13: Go to

Speaker 1: cutlery.ai.

Speaker 2: What's people been asking that question recently? Anyway, very fun. Let me tell you about Cisco. Where is Cisco? Cisco. Critical infrastructure for the AI era. Unlock seamless real time experiences and new value with Cisco. Our next guest is Markie Wagner from Poetic. She's the founder and CEO

Speaker 1: Future hall of

Speaker 2: prolific mafia player. What's your favorite role in mafia?

Speaker 8: Oh, mafia. I think who doesn't love to be fascist in Mafia? I you know, you always gotta hope you're getting the fascist card but Who is the fascist I in

Speaker 2: thought it was just Mafia Townsperson Oh,

Speaker 8: I'm the secret head larc.

Speaker 2: You're secret head larc.

Speaker 9: Yes. Yes.

Speaker 8: Yeah. I mean, mafia is always one of mafia. Yeah. You want single time.

Speaker 2: It's always power. It's it's less empowering to be the townsperson because you feel like you're just getting killed. You have no superpowers. But running angel or sheriff, that can be fun. But then if you get killed off early, it's the end. I'm just thinking of it because the the latest episode of Mafia episode two from Founders Fund dropped and you're backed by Founders Fund. But since this is your first time on the show, why don't you introduce yourself? Tell us how you wound up in a position to raise money from Founders Fund.

Speaker 8: Cool. Yeah. So I'm the CEO of and wait. I think I'm okay. Yeah. So I'm the CEO and founder of Poetic. Yeah. And Poetic's an AI system that will learn and execute super complicated processes Mhmm. In some of the biggest companies in the world at over 99% accuracy which is Okay. Which is quite hard.

Speaker 2: Yeah. So what is the process for obtaining and documenting the workflow? This feels like you could do something very database driven. You could build an ontology. You could just wait and maybe the models get better and stop hallucinating. There's been debates over the various approaches like what did you pick and why?

Speaker 1: Wait, before we get into that, like, talk more about the kinds of workflows Yeah. Where act like, you know, we we caught up a few weeks ago and and you were saying like, some of the customers that you're talking to, even if even if somebody came through and they were like, our AI system is 98.5% accurate, that that would actually create, you know, hundreds or thousands of hours of like issues in an organization. And it would actually like rolling that kind of system out would have sort of like negative enterprise value.

Speaker 2: That's just a pitch problem. If you're pitching a software like that, you just gotta tell someone, our system has 9,000 basis points of accuracy. Yeah. Is the goal.

Speaker 1: Put it in basis points.

Speaker 5: Put it in

Speaker 2: basis points also.

Speaker 1: Anyways, talk talk more about the problem before we talk about the solution.

Speaker 8: Yeah. So I think the problem is, you know, one of things you've seen is, you know, obviously AI is incredible at writing code Mhmm. And it has really crushed that. But, you know, a lot of the main processes that are at the heart of these giant businesses have remained pretty untouched by AI. Mhmm. And the reason why is that the rules that govern them, you know, the 10,000 secret rules, they live in people's heads.

Speaker 4: Mhmm.

Speaker 8: Right? And these rules need to be followed every single time. You know, we work on things like anti money laundering and underwriting and fraud investigations where every single step matters. And to actually get from where we are now to those running on machines, you need two things. One is a system that can learn the process. Not the 100 pages of written down stuff, but the 10,000 rules that live in people's head that they've never written down before. So that's part one. And then you have to be able to run them with many nines of accuracy. Not, you know I was talking with one CEO, he's like, know, 80% on an eval is great, but in underwriting, it's unusable.

Speaker 2: Mhmm.

Speaker 8: And I think that's the u for a lot of these biz processes that are at the heart of these, like, really big and old businesses. So you gotta do two things. You got a system that can learn all the rules and then run them with nines. And if you have that, you can get from where we are now to this version of the future that I think everybody's really excited about, but you need to build that bridge.

Speaker 2: Mhmm. Not everyone's excited about it. AI has very low approval rate, But tech leaders are certainly excited about it. But so why have you started with such big companies? Like, I feel like you've been you've been, you know, at the heart of the startup ecosystem for so long. If you came on here and said, oh, we have so many, you know, my friends' companies on board. These are the named customers SoFi, Chime, AIG, like these are large institutions at this point. Why start at the top? Feels harder.

Speaker 8: Yeah. I think our view was when you're building something like this, if you build something that's less powerful, it's hard to sometimes make it more powerful. Mhmm. Like, lot of these drag and drop tools, they were simpler, they were easier, they could do simpler things faster, but they just couldn't handle super complex things. Mhmm. And so, you kind of get kneecapped in terms of what you can represent and build. And the view is, hey, AI is gonna be doing a lot of this, like, writing of the software. You'd be in a better place optimizing for the power of the thing. Mhmm. Can it express and run these five hour processes require those nines and then everything else becomes really easy actually. Mhmm. And I don't think that people are going to be having a platform for the easy stuff and the hard stuff. I think they're just gonna be running all of their processes in one spot.

Speaker 2: Mhmm. I mean, you mentioned like tens of thousands of hours of information stuck in people's heads. Like what is data collection? What does data collection look like? Conversations? Like it feels like, yeah, like is it the McKinsey model or is it the self serve software model? Like where do you want to sit?

Speaker 8: Yeah. I mean, what's interesting is it's evolved over time, but the place that it has ended up going is looking closer to data labeling. So what happens is a big com company will say, here's my biggest process. It's a 100 pages of documentation, and you know that that's only 20% of it. So the question is like, how do you get that other 80? Mhmm. Well, what we'll do is we'll take that operating procedure, we'll generate the AI operating procedure, it's written in step by step English. What our system does is turn that into code under the hood, and you run it. Mhmm. And when you run it, and you put it in front of those experts, they have a ton of opinions. They have a lot of feedback to say, you you forgot that the threshold's actually a million, not 10,000. Right? All these little things

Speaker 2: Sure.

Speaker 8: Which get merged back into that document, and you're sort of doing that more and more automatically so that it looks almost like training a program or something like that, rather than sort of like long calls or or process mining in, like, the the normal sense. And so, more and more, it looks like people giving feedback into the system directly and that updates the rules that are written in it.

Speaker 1: Yeah. And so you're using AI models to generate that code that is then deterministic, which gets you the reliability that these companies need. Correct?

Speaker 8: Yep. Yep. Exactly. So the, you know, the source of truth is that AI operating procedure. It's English, but what are some of those turn into code. So when it runs, if the if the world's the same as yesterday, it's just going to run as code. Great. Nothing to see here. But if something changes, like the column name changes from month to month, or the save button moves, only then will AI go in, repair it, look at what the English goal was, and then update it. And so if you do that, you can get the best of, hey, it's code, it's precise when it runs. But if something changes, instead of breaking, it will actually just kick back and recover.

Speaker 2: Mhmm.

Speaker 8: And that's important because a lot of this work, code couldn't do alone, and agents couldn't do alone. So code is very static. Right? It's like very brittle. So even one small date change or something could break the whole thing. And so that's one side of it. Agents on the other hand are pretty improvisational and they think step by step and, you know, when you're figuring out what to do as you go, eventually you're going make a mistake. This is something that's kind of in the middle where it's code of things the same, AI is there to test, heal, recover if things are different, and that's how you can kind of get those nines.

Speaker 2: So are you hiring forward deployed engineers? Like, what is the role of engineering in your organization at this point?

Speaker 8: Yeah. So we do we hire tons of forward deployed engineers from all the best spots, you know, whether it's, you know, a place like Palantir or Mhmm. You know, even like, retool or scale and all these other sort of new places that have their own versions of forward deployed. And, yeah, I think it's interesting. It has over time looked less like extremely just only focusing on engineering, like hard engineering. It requires being able to change how people operate. Right?

Speaker 2: Yeah.

Speaker 8: And I can write the best code now, but even if you have the most incredible piece of software, you still have to change how the business organizes around it. And so, the people who understand like business and can think about, hey, like, what is the best possible fraud process going to look like? And, you know, what how should we reorganize the business around this new kind of thing? Mhmm. And they understand AI are the ones that are just, like, totally crushing it.

Speaker 2: Yeah. That feels like an entirely new skill set, like, much more people driven, but also, like

Speaker 8: Yeah.

Speaker 2: Forward thinking in technology. I don't know. Mhmm.

Speaker 11: It's a

Speaker 2: it's a it's an interesting new

Speaker 1: How has enterprise sentiment around just AI changed during the course of building the company? Right? Because like every, you know, it is I would say it's a roller coaster in some ways. It's like going up Yeah. Up into the right. Right? There's generally more excitement about the potential but at the same time there's these of like period troughs of disillusionment. And you guys are coming out of stealth at a time when again, I think companies are more excited than ever but at the same understand the overall shortcomings and and we had Karp on the show last week and you know, he was just saying like a lot of these deploy codes coming in, they're just trying to like they're they're they're trying to deploy their their goal is to deploy AI, but they don't fully understand all of this like business process under under the hood. And he makes some good points.

Speaker 8: Yeah. I think sentiment has evolved quite a bit. You know, I think it was extremely exciting earlier in the year. And then, you know, around the board meeting times, more and more CEOs would come to me and say, hey, like, you know, how do I get ROI here? And and, you know, this is what your other customers are seeing in these domains. And so, I think now people have realized, like, you cannot just throw an agent at a problem and expect to see the result that you want. Right? For an agent to to do a useful bit of work, it needs to learn how to do that work and run it, like, quite accurately. And that knowledge transfer between how's the work done today and getting it written down enough to where AI can run it, it's just hard. And it requires, you know, we sort of jokingly call it the great migration internally. Like, you have to go and migrate these, like, tremendous amounts of rules into something that AI can touch and improve and involve. And if AI can't touch it, it's not going to be able to help it. Mhmm. And so, you know, I think deployment is really important because in yeah, until that transition happens, it's going to be hard to just throw tokens to to see better outcomes.

Speaker 2: Give us some backstory on what you were doing before, how you wound up here.

Speaker 8: Yeah. So I got my start. I got extremely into AI in middle school after reading too much sci fi, you know. A lot of Dune. A lot of mainly Dune.

Speaker 2: Is that the message in Dune? I thought Dune was the you

Speaker 13: know?

Speaker 2: I guess, yeah.

Speaker 8: Yeah. You wanna avoid the Dune outcome.

Speaker 2: Well, I

Speaker 8: just felt like it was gonna be really important during my life, Yeah. You know, and you know, you read and you watch sci fi, you know, the biggest difference between the future and today, it's like mostly machines thinking. Like that is sort of the main a d sort of b c moment

Speaker 2: In hard sci In soft sci fi, it's like time travel and faster than light speed and like aliens. But I moon

Speaker 1: is made of cheese.

Speaker 2: That's the type of sci fi I'm trying to read.

Speaker 10: That's the

Speaker 2: white pill. So then walk me through the consulting work that you did and how this like evolved out of that. Was there like a clear moment where you're like I'm stopping that and starting a company or is this an evolution or a change of structure?

Speaker 8: Yeah. So I was initially got my start in research. So I was

Speaker 6: at I

Speaker 8: was at Stanford working in AI at like Waymo and Google. Yeah. And then, you know, one day I sort of realized that, you know, all the things I built like, you know, didn't didn't matter too much. And that was Friday and I ended up dropping out on Monday. And the idea was like, hey, you know, we've had software for decades. What are people still doing and and why? And I felt like I didn't really understand anything about how the world works. So Mhmm. To your point, started consulting and Yeah. The idea was like, let's just go into some of the oldest companies around and understand, like, what his software is still not touched and and what And happened when you do that, and you start doing some of the work yourself, and like going into, you know, I went to North Carolina, and you're people who've done this stuff for like decades, you realize that a huge amount of the work is really just operating procedures documents

Speaker 2: Mhmm.

Speaker 8: And people are just following them. Mhmm. And that this class of work everywhere, and you know, whether it's underwriting and claims and insurance, or onboarding customers and fraud and banks, it's just still sort of done by by people and software hasn't been able to go there. The reason why is because the second you write all this code to do that process, something will change. Right? A button will move, a column will change, or maybe even the the process changes. You want yearly instead of monthly transactions. And when you, you know, automate and see that happen enough, you you realize like, hey, there's a missing kind of material here that can flex but still have guarantees. And I really just waited for the models to get better. I knew some of the researchers and said, the models of today are not it. Please let me know when they get good enough to get stuff. And I truly just waited. So

Speaker 2: That's great. Well, congratulations on the round. How much did you raise? I wanna hit the gong.

Speaker 8: Oh, yeah. So you raised $50,000,000. Congratulations.

Speaker 1: And thanks so much. Who besides FF is in?

Speaker 8: Yeah. Kleiner Perkins Kleiner Perkins. First Harmonic, Genius Ventures Cool. All all participated in the round.

Speaker 1: Round of applause for Genius. Love Greg and Ben and Adam.

Speaker 8: We love Genius.

Speaker 2: It's great news. Well, have a great rest of your day. So great rest

Speaker 1: of your have you on the show. Congratulations on coming out into into the world. Yeah. And I'm sure you'll be back on very soon.

Speaker 2: We'll talk to you soon, Mark.

Speaker 8: Thank you. Appreciate it.

Speaker 7: You all.

Speaker 1: Cheers. Goodbye.

Speaker 2: Let's see. Canva AI. We got to talk about the dog. The dog walker and the dentist. The bitter feud between a dog walker and a dentist over who owns the beach. A lakefront owner likened his neighbor's shoreline walks to a home invasion in a dispute that could be headed for the Wisconsin Supreme Court. Who you got, Jordy? Knowing nothing about this story, are you going dentist or dog walker? Pure Vibes.

Speaker 1: Pure Vibes?

Speaker 2: Flip a coin. Which one I don't know. Who you got? You don't know. It's your job now.

Speaker 1: Is the dentist a day trader?

Speaker 2: See, it's your job to pick someone wildly and then defend it throughout this article. Recent trial in Shorewood, Wisconsin had all the trappings of a minor legal dispute, disgruntled neighbor. A defendant representing himself who called his own father as a character witness. You love that. Hey, dad. Tell them I'm a good person. 130, 100 and, $313 were at stake. $313. That's 31300¢, if you're paying attention. If it, but an if academic and devoted dog walker Paul Florsheim gets his way, the case will go all the way up to the Supreme Court, Wisconsin Supreme Court that is, and reshape the contours of shoreline access to one of the Great Lakes. It started when Florsheim started walking his two dogs past the Lake Michigan property of dentist Daniel Domagala, locally known for the time he spends in a tiki style boathouse and deck that doubles as a surveillance post. From there, Domagala monitors traffic and sets off alarms to scare walkers, swimmers, and kayakers away. He's got an air horn. He's got an air horn. He sets it off when somebody comes Woah.