Financial Modeler's Corner
00:02:10 · Giles Male, Paul Barnhurst
[00:02:10] S4: Just working. I don't have a life outside of work at the moment. It's one of those things where I'm happy to be busy, but even like this week on its own, I'm doing copilot training tomorrow with a team of about a 100, doing some collaborative claw training on Friday with some other quite well known trainer with a large beard. That's interesting, isn't it, Paul? And then we've got The UK XL Esports Finals in London on Saturday. So, yeah, crazily busy and also trying to keep up with everything that's actually happening in AI world as well. [00:02:41] S2: And I can confirm his comment and no live because the time he decided to meet with me last week, because I moved our meeting, was 10:30 his time on a Friday night to prep for some training. So that tells you he's working around the clock. I can vouch for that. It's the big bearded guy he talked about that he's gonna do a training [00:02:59] S4: I should be rich. [00:03:01] S2: Alright. Well, we're thrilled this week to have a guest with us. We have with us Pete Fuller. He's the CEO of Tracelight. Some of you may have heard of it. It was the first... I believe it was the first tool we tested on the Mod Squad series back in September about a year ago. That platform has expanded and grown quite a bit since then, so we wanted to bring him on and just talk about the journey, a little bit of his background, and where he sees modeling going. But why don't we start with just giving you a minute to just tell us a little bit about yourselves? Tell our audience who you are and how you ended up where you're at.
00:03:01 · Paul Barnhurst, Peter Fuller
[00:03:01] S2: Alright. Well, we're thrilled this week to have a guest with us. We have with us Pete Fuller. He's the CEO of Tracelight. Some of you may have heard of it. It was the first... I believe it was the first tool we tested on the Mod Squad series back in September about a year ago. That platform has expanded and grown quite a bit since then, so we wanted to bring him on and just talk about the journey, a little bit of his background, and where he sees modeling going. But why don't we start with just giving you a minute to just tell us a little bit about yourselves? Tell our audience who you are and how you ended up where you're at. [00:03:31] S1: Well, yeah, thank you very much for having me. I'm very excited to join you guys. So, yeah, I'm Pete. I'm the CEO, and I'm one of the three cofounders of Tracelight. So we founded the business in mid twenty twenty four when the LLMs could barely write valid formula in a spreadsheet. And before founding Tracelight, I was a venture capital investor, very, very early stage VC investor here in London at a place called Entrepreneurs First. And before that, I was at McKinsey five years, obviously did a lot of modeling there and was also part of QuantumBlack, which is McKinsey's AI practice, basically. Before McKinsey, I mean, a bunch of weird and wonderful things. I ran a a charity in East Africa. I pounded spreadsheets. Amazon briefly as well. One or two other things. So, yeah, that's me.
00:03:31 · Peter Fuller, Paul Barnhurst
[00:03:31] S1: Well, yeah, thank you very much for having me. I'm very excited to join you guys. So, yeah, I'm Pete. I'm the CEO, and I'm one of the three cofounders of Tracelight. So we founded the business in mid twenty twenty four when the LLMs could barely write valid formula in a spreadsheet. And before founding Tracelight, I was a venture capital investor, very, very early stage VC investor here in London at a place called Entrepreneurs First. And before that, I was at McKinsey five years, obviously did a lot of modeling there and was also part of QuantumBlack, which is McKinsey's AI practice, basically. Before McKinsey, I mean, a bunch of weird and wonderful things. I ran a a charity in East Africa. I pounded spreadsheets. Amazon briefly as well. One or two other things. So, yeah, that's me. [00:04:12] S2: Love it. Fun journey. Well, why don't we start... Can you tell our audience start by telling a little bit about Tracelight, kinda how it came about, a little bit of the backstory, what you're doing today, and we'll just go from there.
00:04:24 · Peter Fuller
[00:04:24] S1: Yeah. For sure. So I started working with Alex and Janek in mid twenty twenty four. So our backgrounds, I mean, I've just told you mine. Alex, our CTO, was a software engineer at Jane Street before Tracelight. And before that, he was at at Cambridge, which is where he met Janek. So Janek's a machine guy. He did that at Cambridge and then did that in a bank for a while. So we got together and we were exploring different ideas, actually. I think it'd be fun to kind of build AI for Excel. At that point, no one was doing it. Right? There was this funny little research paper from Microsoft. It wasn't anyone significant at Microsoft, but the research paper basically said, like, yeah, LLMs have a really hard time with two dimensional data structures in general, obviously, including spreadsheets. But if you were going to kind of represent a spreadsheet to an LLM, this is kind of how you might think about it, how you do it. That's where we started. Alex implemented that over the course of a few days, and obviously, we built on it very significantly. And, yeah, the sort of the key thing for us at the beginning, which is now completely irrelevant, by the way, we've actually thrown out the database entirely. Right? This is the journey for many AI startups. But the key thing for us was that middleware, I guess, between the spreadsheet and the LLM that made the problem more comprehensible to kind of GPT-4 at the time. And we really built from there. I mean, our motivation to build for financial models in the first place, I'm sure you guys would agree with this. Right? It's like, you know, I feel like people build financial models whenever they have a really big and important decision to make. Right? And we're very ambitious. Right? We wanna make our mark on the world, and we wanna build a company that helps the biggest and most important decisions get made. And so since kind of launching that Excel agent, we've really expanded the product. You know, we're now really kind of all in one AI workspace for our customers. So they can do all of their work in Tracelight. It's like a central web app, and we have add ins to all of the Microsoft Office Suite. But, obviously, we still have that heritage as an Excel company. Right? So, you know, we're really, really outperforming in kind of spreadsheets and spreadsheet related tasks. So, yeah, that's been the journey.
00:06:22 · Paul Barnhurst, Giles Male, Peter Fuller
[00:06:22] S2: Alright. I'll let Giles are in, ask some questions so I don't hog all the mic. [00:06:25] S4: I got a... Just an initial thought when you were describing... Is it Yanik you're saying you're the other founder, machine learning at Cambridge. I can imagine somebody like that must look around now at all the AI experts popping up left, right and center and just be like, good God, you know, machine learning Cambridge. I said this some some point, like a year ago, was like, there is a world of actual, like, AI experts. He must be so annoyed with this. [00:06:55] S1: I don't think Yannick feels that way about you guys, but he definitely did about me, I think, at the at the beginning, for sure. I think I've learned this. [00:07:01] S4: You won him over. [00:07:03] S1: No. He's he's an incredible guy. Right? So he has this, obviously, deeply technical backgrounds. But, you know, he also loves, like, front end and, like, design. He's just, like, unicorn of an engineer who can do the kind of ins and outs of machine learning, but also loves an interface. And and also, you know, a lot of building with LLMs is is not very sexy. Right? Like, it's... You know, so it is a lot of prompt prompt engineering. Right? It certainly was. And it's a lot of evals and there's a lot of hill climbing and and you need a kind of tenacity and a certain mindset to be really, really good at that and and Giles has that. Right? So it's... Yeah. I think he's very, very well suited to to what we do. [00:07:50] S4: I've got another question, but I I don't wanna take over. Go for Ian.
00:07:50 · Giles Male, Ian Schnoor, Paul Barnhurst
[00:07:50] S4: I've got another question, but I I don't wanna take over. Go for Ian. [00:07:53] S3: No. Go ahead, Giles. You go ahead. You can get five in a row. The [00:07:57] S2: I'll take it. I'm gonna limit you. [00:07:59] S4: I don't know if this is jumping ahead to, like, the meat of what we're gonna get into, but, obviously, I guess what was interesting for us when we started last year with the Mod Squad, we tested Tracelight first and a bunch of other tools. And then suddenly, you know, Microsoft came out with their first agent in web and and Anthropic did all of this. I'd be really intrigued to hear what that journey's been like for you. And and I guess, like, for me, did you expect those, you know, the LLM providers like Anthropic and OpenAI and Microsoft to do what they did when they did it? Or was it a bit of a pride?