Building Legal Agents When You Can't See the Data - Jacob Lauritzen, CTO of Legora

Legora can’t read a single trace of what its agent does for a lawyer. The data belongs to the law firm’s clients. How do you build and test an agent when you can’t see its work? Jacob Lauritzen is the CTO of Legora, one of the fastest-growing companies...

• 0:00Speaker 00

  People were asking us about mythos and everything, even though I think realistically a lot of legal work does not require mythos level intelligence. Paralegals gone. Yep. Junior lawyers gone, I don't need them. That's actually not what we're seeing. We had one problem where it wouldn't cite properly. And so like next model release solved, it went from like seventy percent to like ninety nine. It's like we did nothing and like, great. But if you're doing a four hundred million dollar M and A transaction, you're gonna want Legora. We're just gonna be twenty engineers for the rest of the company's history. And like, we're gonna beat everyone who's much bigger. And we're hundred engineers now and it feels like we're way too small. But it's something that I'm toying with is like how much of our product can just be the agent. We're solely all this stuff.

• 0:39Speaker 01

  Okay, we're here in a studio with special guests, Jacob Lohren, CTO of Legora. Did I get it right, Lohren?

• 0:45Speaker 00

  That's fine. Yeah, that's okay. I'm not super passionate about how it's Danish. Yeah, exactly.

• 0:49Speaker 01

  Does it have a special history?

• 0:50Speaker 00

  It just no, Sen is like sun, sun of.

• 0:52Speaker 01

  Sun of Lohren?

• 0:53Speaker 00

  You have sun and yeah, so son of Lohren, that's my name.

• 0:56Speaker 01

  Nice. We've crossed paths here and there. You spoke at AI a few times and obviously Legora is one of the fastest growing legal tech in history.

• 1:05Speaker 00

  Yep.

• 1:05Speaker 01

  And you said something at the start in a pre-show that I thought was really interesting. You said that your origin is very European, even though obviously you're expanding in New York and SF. What feels different about your culture?

• 1:17Speaker 00

  I think we are just at the core, probably very humble about what we're doing. Because we've always been the underdog from the very beginning. No one believed the small startup in a basement in Stockholm was gonna outcompete this huge behemoth that was like way ahead of us in the US. So I think we've always been underdogs since we've always been very humble. We've always sort of had to fight for our existence. I think it's something we've had to learn as we've also become more and more, as we've entered the US and been in the US a lot more, is to be a little bit more bold and like tell the world how great we are. Because it doesn't come naturally to, I think, some of us.

• 1:54Speaker 02

  I kind of wanna start by going over your guys' product. Because I feel like with a lot of these like legal products, you know, they're kind of like under wraps. Like, you know, you're not supposed to like show it. But yeah, if you could just talk about like, what does the product look like? And maybe like, how did you guys get there? Like, what have been the product iterations that got you to where you are today? I think that would be really interesting.

• 2:13Speaker 00

  Yeah, absolutely. The way everything started was chat GPT with Swedish laws. It's a search tool in it. That was literally the entire, everything. And so that's where we started. We started with legal research, which is like a huge market, basically, in the world, where lawyers spend a lot of time figuring out what are previous cases that looked like this? What's the legal precedent like? Is this, you know, what have previous people done in these situations? That's extremely important. And so that has always been part of our product. Basically, we started from like an agent, you could ask questions and it would query laws. That was a very simple beginning. And then from that, it's expanded. And so it's expanded in like, what can the agent do? It will now, you know, draft a lot of stuff really well. It will edit Word files.

• 2:55Speaker 00

  It will, you know, move your files away, organize everything, run really complex analyses. And we've added just a bunch more features to it. So one of our features is called Tabular Review, which is now a name that's being used in industry. And we're very happy to see Claude for legal using our terminology for what they're building. We gotta talk about that. We gotta talk about that. Which is essentially like a way to just bulk extract and bulk review many, many, many agreements, which you do in due diligence when you raise money or whatever. So that's part of it. It's like, we help lawyers just do their work much more efficiently, much, much better. And then outside of just doing the work, we're also now helping orchestrate the work a lot more than we were just even a year ago.

• 3:35Speaker 00

  So we have different sort of, we have a thing called lists, which is sort of like linear for us. And we have intake, which is a way to collaborate with clients. And we have portal, which is also sort of a way to collaborate, you know, lawyer to lawyer, client to lawyer, lawyer to agent, agent to agent, maybe. We're spending a lot of time there because there's just frankly, the way that you work with a lawyer ten years ago, or maybe even today, is really painful. And there's loads of room to do that in a much better way, to be honest. And so those are like, I think the two things, it's doing the work and it's also like orchestrating the work.

• 4:12Speaker 02

  When did you guys start doing or building the agent?

• 4:15Speaker 00

  So I mean, we've all, we basically had this switch from the assistant to the agent.

• 4:18Speaker 02

  Yeah.

• 4:18Speaker 00

  We call it, right? I guess that the agent, I don't know, I wanna say a year ago, probably.

• 4:25Speaker 01

  Yeah. So this is a rough timeline for people who are understanding YC twenty twenty three.

• 4:30Speaker 00

  Yes.

• 4:30Speaker 01

  And then you were, you were a YC founder as well.

• 4:32Speaker 00

  YC twenty four.

• 4:33Speaker 01

  YC twenty four.

• 4:33Speaker 00

  Yeah, I was in YC twenty three. Legora was twenty four.

• 4:36Speaker 01

  Okay. And then, so there is, this is like a little bit pre, like agents really taking off.

• 4:41Speaker 00

  Exactly.

• 4:42Speaker 01

  And then like reasoning models obviously change everything. I mean, you know, in one, in one sense, today, you know, we had a preview of the products. It does look, well, preview, we had a private thing, well, we will put up a video on YouTube. It's mostly like chat GPT for lawyers, right? Like a very, like very fair to say that. But then like the sidebar has a lot of nice custom tools, like the tabular view, like the intake, which I really liked, and you know, a bunch of other things.

• 5:07Speaker 00

  Exactly. That's, that's exactly what it is. It's coworker or chat GPT, just like really, really good for legal work.

• 5:13Speaker 01

  And yeah, the workflow for like either like in-house corporate lawyers, like people like looking for upcoming regulations, all these things. And we can talk about more of the products there.

• 5:23Speaker 02

  Yeah. What models are you guys using underneath? Like, can you talk about that?

• 5:27Speaker 00

  I mean, we're using a bunch of different ones depending on task, right?

• 5:30Speaker 02

  Okay. And then that's not available to the lawyer to see. You guys pick yourselves.

• 5:36Speaker 00

  Yeah, well, we've been back and forth on this.

• 5:38Speaker 02

  Yeah.

• 5:39Speaker 00

  Just like everyone else, I think. In the agent, there's a model selector for the primary model. But there are certain tools that we use different models in. And there's like tabular view and like, we try. I think we found it most effective to subdivide the problem and route on like, as we subdivide the task. But we do right now have a picker in the agent. I'm not sure if that's gonna stay there always, to be honest. So yeah.

• 6:03Speaker 01

  Yeah, I mean, so I bring a little bit of context to this because I'm advisor for Cognition.

• 6:07Speaker 00

  Yep.

• 6:08Speaker 01

  And when I joined, you know, part of my thesis for what an agent lab is, and agent lab is, you know, ideally a domain-specific GPT wrapper, right? Like we, we, we run the, we are the domain experts. We will pay attention to you. We will serve your needs way, way more than the frontier labs. And we'll give you the best of the frontier labs, according to our judgment. So our job is to decide for you because you're not, your job is not to.

• 6:31Speaker 00

  Exactly. We'll always keep you on the Pareto frontier and make sure that it's just, it's great all the time. And you don't have to dive into all the details. Because like, one of the things that I've, exactly to this point, if you go to a lawyer and you ask them, oh, you're gonna, you know, draft this contract based on this precedent. Do you think that's a sonnet high or an Opus mid task? They, they won't know.

• 6:50Speaker 01

  Just give me this model.

• 6:51Speaker 00

  Just like make sure it works.

• 6:52Speaker 01

  My hourly rate is a thousand dollars an hour.

• 6:53Speaker 00

  Exactly. Just like, make it work.

• 6:57Speaker 01

  So yes, I originally came in with that. I was like, oh yeah, this is, this is what Devin does differently. And now we have five things in the model picker, including Fable and Opus and Astra. And people wanna experiment with the fancy new model. Is that the same?

• 7:11Speaker 00

  I think so. I think it's probably, it's definitely way less in legal than it is in.

• 7:16Speaker 01

  Coding.

• 7:16Speaker 00

  Engineering.

• 7:17Speaker 01

  Yeah.

• 7:17Speaker 00

  But there are definitely people that just want Fable one right away. And you know, people were asking us about mythos and everything. Even though I think realistically a lot of legal work does not require mythos level intelligence.

• 7:29Speaker 01

  Yeah. So exactly, right? Like, I think basically you're like, okay, we'll give you the option. You, you asked for this, but you're gonna run down your credits like ten X faster than.

• 7:39Speaker 00

  Yeah, I would have loved, we, we fought introducing it for a very long time. And then in the end, we just kind of caved in. We're like, okay, if you want this level of control, you know, then we'll give it to you.

• 7:48Speaker 02

  So you think the models are already like as good as lawyers need? Like, there is no need for them to get better?

• 7:53Speaker 00

  It's, I think it's a power distribution. So like, there's probably like sixty percent of the work.

• 7:58Speaker 02

  Yeah.

• 7:58Speaker 00

  We can do really well right now. And the, you know, from now on, it's like a cost and latency thing. But then there's the rest of the thing where, especially for like very complex analysis, we still need more intelligence. And then I think there's also just the work expands kind of. It's like, that's the work that we have right now, but also the work for the lawyer who thus probably expands with intelligence.

• 8:20Speaker 02

  Yeah.

• 8:20Speaker 00

  I imagine.

• 8:21Speaker 02

  Early on, like when you guys first started, I guess, transitioning to the agents or building the agents, like what were, like what models were you guys using? I guess it would have been like Opus four six or something?

• 8:31Speaker 00

  That would have been, yeah, sonnet four six, open four six is probably right.

• 8:37Speaker 02

  What were the agents like not good at at that point? That they're much better at now, even though it's only like nine months later?

• 8:44Speaker 00

  Sub-agent delegation was one of them that we've gotten working really well now for like fan out type retrieval queries, works extremely well for us now. That was difficult before. We basically track, so we have a team that's just doing evals. And so we track all of the model's performance in different practice areas, which is like subgroups of legal and different tasks across all those. So we basically have like a big roadmap and we're like, and then we can see them move. And it's like, usually they improve most stuff. But there's actually a lot of model releases where they improve some and regress in others.

• 9:15Speaker 02

  Okay.

• 9:16Speaker 00

  And that actually happens a lot more than you'd think.

• 9:18Speaker 02

  Like, what are some of those tasks? Like, are you familiar with how you guys are running a lot of the evals? Like, what are those different subsegments, I guess, that you look at?

• 9:25Speaker 00

  So like, there's, there's different just like framing stuff. So we have different, basically like worlds, like R environments essentially, which is like, here's a, because lawyers work in projects always, more or less. So it's like, here's ten thousand file data room. You're doing a due diligence. In the end, a great report looks like this. Like, it contains all these right red flags and like, it doesn't contain whatever weird stuff. And like, we want it to be concise, et cetera, et cetera. That's kind of how we've built it. So there's different tasks, which is like, part of it is drafting a report. Like, does the draft look good? Does it contain all the right stuff? Is the wording sound, the analysis sound? There's also the part of finding the red flags, like the analysis before that. So we can kind of like subdivide it a little bit. And that's how we run the evals.

• 10:07Speaker 02

  Interesting. Like, what does your evals team look like? Like, do you hire lawyers to like do that?

• 10:11Speaker 00

  So yes, it's a mix. We have engineers and then we have lawyers. And it's one team. So there's like three engineers and like three lawyers right now. And then we have a pool of what we call legal engineers, which is people that have worked in big law for like three or four years. Typically, maybe they have a CS degree and like they're very tech forward. And then they come to us and because they wanna like help change the industry.

• 10:34Speaker 01

  Are they IT in big law?

• 10:36Speaker 00

  No.

• 10:37Speaker 01

  Are they lawyers in big law?

• 10:38Speaker 00

  They're lawyers in big law.

• 10:39Speaker 01

  With CS degrees?

• 10:40Speaker 00

  Yes.

• 10:40Speaker 01

  Oh my god.

• 10:41Speaker 02

  Must be really hard to find those.

• 10:42Speaker 00

  Yeah, exactly. That's like our hardest person to hire for. But they're also such a force multiplier because we can pull on them for the eval stuff and for the product development. It was just like you have a pool of a hundred experts that use the product every day and go and talk to clients every day. And also like they live this and have lived this and we just pull on them to do evals and like help us shape the product and it's such a such an advantage.

• 11:03Speaker 02

  And curious, like, when did you guys start that team?

• 11:05Speaker 00

  Eval grew out of the assistant agent team at some point. I think there was a point up until recently where it was like, honestly, it's just not really worth it because like all models just got better. So it was like, do we want to spend a lot of our time doing really complex evals or do we just like wanna build? Because there was so much to be gained from building a better harness and like just sort of leaning into everything's gonna improve and everything kind of just improved.

• 11:30Speaker 01

  Yeah, like every two, three months you get a different model.

• 11:33Speaker 00

  Yeah, exactly.

• 11:33Speaker 01

  Just pass it through, right?

• 11:34Speaker 00

  Exactly. I mean, we had one problem where like it wouldn't cite properly and so it would be difficult to follow and it was like, next model release solved, it went from like seventy percent to like ninety nine. It's just like we did nothing and like, great.

• 11:44Speaker 01

  Yeah, maybe the the the real work is, you know, keeping all the data private, making it tagable, sortable, adding new features like the the tabular view. Is that the, you know?

• 11:55Speaker 00

  You mean over and above chat G P T?

• 11:57Speaker 01

  Yes, but obviously now you're also doing evals. I assume your your use of open models is also increasing. We can talk about that. So, yeah, I don't know what I'm saying here apart from like, you know, what is the job? The job is maybe not, in the early days, it was not so much to do do evals because it was mostly expose model capability to lawyers.

• 12:18Speaker 00

  Yeah, the huge part of it is just figuring out what does the legal profession look like in five years, ten years with all of this stuff? Like coding is maybe a year or two ahead, so that we can kind of look to that a little bit, but like what are the primitives? How do people work? How do you collaborate if it's not a two hundred thread email with like V five word files back and forth? Like, what does that look like? And that's like, not even necessarily purely A I. That's just like build a much better product experience.

• 12:45Speaker 02

  Yeah.

• 12:45Speaker 00

  And make sure you do it with like audit logs and data retention and all of those sort of really important things in regulated industry. And then there's the the A I part, which is like make the work faster and better and proactive agents that react to stuff when it comes in. So you don't have to, you know, kick off everything. So I think a lot of the work is just figuring out what do we think it's gonna look like in five years? If, you know, model capabilities keep increasing, if price keeps coming down, what could we do? Can you log in and it's like command center where it's just like you need to react to these five things that the agents have been doing lately? And like review and check and improve the system. Maybe that's where we're going or it is where we're going.

• 13:20Speaker 02

  Yeah, yeah. Yeah, I was gonna ask, like, could you go into that in a little more depth? Like, yeah, what is the like law profession gonna look like in a few years?

• 13:32Speaker 00

  I should preface this by saying I don't know. I mean, who knows really? But I think we can look to coding a lot. I think all lawyers are gonna be way more productive than they were before. They're gonna be able to do a lot more stuff at a higher quality for a lower cost. I think the profession itself, the work itself, is gonna improve a lot. It's gonna be a lot more. I think lawyers are gonna spend more of their time doing the stuff that they became lawyers to do. You know, figuring out what's the right risk profile, what's manageable risk, what's like the all of their judgment, strategic judgment and like working with clients. They're gonna do that a lot more and much less of the like trolling through big documents to like find the smoking gun

• 14:14Speaker 00

  or like do all this meanil, super annoying work that a lot of lawyers have been doing.

• 14:18Speaker 02

  What do you think is gonna happen in the partnership model? Like, do you think that stays or like what happens?

• 14:22Speaker 00

  I gave this, I actually gave this a lot of thought just like last week.

• 14:25Speaker 02

  Yeah.

• 14:25Speaker 00

  Because the the partnership model, I don't wanna get into too much of the details, but like the partnership model kind of exists because the only type of capital that these companies have is human capital. So like, it's not like, you know, us or like a software engineering firm or like a manufacturing, whatever. You you have physical assets or like some sort of intangible assets that that you accrue over time and and they pay dividends to the shareholders. But if you work in an industry like professional services and it's the same for like consultancies and whatever else, all of your value is in your people. And you can't really own human capital. You know, you you can't, you know, slavery is abolished. You can't own people, but you can rent them. You can pay them money.

• 15:05Speaker 00

  And so partnerships essentially is a structure where you make the human capital the owners of the company so that they stay.

• 15:12Speaker 02

  Yeah.

• 15:12Speaker 00

  Would that change? Like, I don't, it doesn't have to. But I think what we really wanna do with the lawyers, we actually want lawyers to be able, law firms to be able to build some sort of intangible capital, some durable capital and like you can build a system that learns of how you work. A lot of firms right now think about like, well, there's the ex law firm way of doing things and we can codify that, I think. And we can build a system and whether that's like a self improving knowledge graph or whatever it is and like precedent files and documents, where there's like a way of working that produces a really good output and that can be their I P. And so it's like a way to codify the human expertise and judgment into a system.

• 15:54Speaker 00

  That I think is, now I'm just rambling completely, but like, that's something that we want to help empower. And does that change the partnership model then? Because then incentives are different in the partnership model. You just gotta bring more clients and you don't wanna take away time from bringing in clients to codify your information, basically. Because like you get rewarded from, you know, eat what you kill or maybe there's lockstep, whatever. That needs to change a little. We need to figure out incentive structure where partnerships, partners are incentivized to codify things for to build an asset for the company. But right now there aren't because assuming as they leave the partnership, they don't get any dividends from the assets that they built.

• 16:32Speaker 02

  Yeah.

• 16:32Speaker 00

  So there's like a, yeah, I think the the the whole business model is, we'll we'll see.

• 16:38Speaker 01

  Yeah, it's all it's all in question right now. Yeah, my actual other take, you know, so on the partnership level, that's like the top end of the the industry. Actually, my take is more on the bottom end, right?

• 16:49Speaker 00

  What happened there?

• 16:50Speaker 01

  Paralegals gone, right? Like junior lawyers gone. I don't need them.

• 16:55Speaker 00

  That's actually not what we're seeing. So yeah, it's, I think it's, I don't know, would you, would you say that we're seeing that in engineering?

• 17:01Speaker 01

  Ah, yeah. So junior engineers are really kind of cooked. You kind of have to come out of, drop out of university, fully baked, or else you're.

• 17:11Speaker 00

  You're not gonna make it.

• 17:15Speaker 01

  I feel like I'm not, I'm being a bit dramatic for for comedic purpose. But like, yeah, I know a lot of lawyers. They started as paralegal. They go through law school, all these things, right? And now they don't, they're not needed. They're just seriously just not needed.

• 17:26Speaker 00

  Yeah, yeah. Yeah, it's interesting what happens to the partnership model, like the pyramid. I think generally a lot of lawyers, you still need, you need the next generation. And at least for engineering, the way I think about it is you have a good engineer today, they're worth a lot more even than they were two years ago because they can produce so much more stuff, like if they're good. And I think it's the same thing in legal where they can actually do a lot of really good work if they're good. So I think it's more that like really good lawyers or junior lawyers are worth a lot more.

• 17:55Speaker 01

  Yeah, it's always been the case, right?

• 17:57Speaker 00

  Yeah.

• 17:57Speaker 01

  Even more so.

• 17:58Speaker 00

  It's, yeah, it's polarizing even more so.

• 18:00Speaker 02

  I'm actually curious about that. So like, the whole like law business is basically like charging per hour. So, you know, if each project now can be done a lot faster, is it going to be like way cheaper like?

• 18:13Speaker 00

  This was actually, so fun story, I was, I was reading Max's Y C application and like helping him getting into Y C, Leia as it was called back then in Y C. And this was my one thing I was like.

• 18:24Speaker 01

  And curious, Leia is a Danish thing for something?

• 18:26Speaker 00

  No, a Swedish. No, also it means nothing. There's this really funny story and I think it was a Spanish newspaper that wrote about us in the early days, Leia. And then they they explained that the abbreviation was legally efficient Yoda assistant.

• 18:43Speaker 01

  Why Yoda?

• 18:44Speaker 00

  Yeah, I don't know. I was like, why, why?

• 18:46Speaker 01

  See, hallucinations are not just from L L.

• 18:48Speaker 00

  No, I think journalists hallucinate.

• 18:51Speaker 01

  But no, it doesn't mean anything. So he wrote the application.

• 18:54Speaker 00

  He wrote, and my feedback to him was, you know, people have tried this a million times. Legal tech has never been a thing because like there's no incentive for lawyers to to, why would they be more efficient? They earn less money, like it doesn't make any sense. But I think the reason that lawyers do wanna adopt this is that they understand the gravity of the situation. They know that like the business model and everything is under pressure and it's like they need to change because the competitive pressures are high. The billing model itself, I think, is also gonna change. We've, we're already seeing that particularly in the U S that a bunch of stuff is actually being priced on like a project fee and not on an hours fee. Particularly like sort of lower end stuff on the spectrum, like whatever it is, like small reviews and whatever. Some of it honestly is being done for free and some of it is just being priced on a flat rate.

• 19:39Speaker 02

  So where is the money being made then? Is it?

• 19:41Speaker 00

  Because the strategic work.

• 19:43Speaker 02

  Yeah, I feel like a lot of what you guys talk about is M and A specifically, like that's where all the money is made.

• 19:47Speaker 00

  A very easy example. Yeah, litigation is also, the big work still is there and it's very valuable. And so they'll, they'll spend, lawyers will spend more of their time there. Client relationship is also super important.

• 19:59Speaker 01

  Like a CRM?

• 20:00Speaker 00

  No, just like spending more time with the client. Like, a lot of law firms will, or historically have basically done stuff for free, just to have their relationship with the client.

• 20:07Speaker 01

  Yeah, yeah.

• 20:08Speaker 00

  And so now they can do that, but they don't have to lose a lot of money.

• 20:11Speaker 01

  I thought, I thought I just have to pay the lawyer money just to be my friend. Like, isn't that the retainer thing?

• 20:17Speaker 00

  Yeah, yeah.

• 20:18Speaker 01

  You tell me I can do it for free, like?

• 20:20Speaker 00

  Yeah, you just have to find the right lawyers.

• 20:22Speaker 01

  Oh, goddammit.

• 20:25Speaker 01

  Okay, cool.

• 20:26Speaker 00

  Or land space has to grow much bigger, I don't know.

• 20:27Speaker 01

  Yeah, yeah, we're trying.

• 20:30Speaker 01

  You know, yeah, so, okay, so, so you're saying, you know, obviously the strategic work and all these high value add is still there. But our legal fees are not going down. But you also said paralegals are not affected, or like, they're, they're just shifting. And, and this is something that we also did worry about with cognition, like, people worry about the phrasing of like, we will replace your junior engineer, because nobody likes that kind of statement. But in actual fact, yes, like, some, some part of it does happen. Other junior engineers embrace it and they become more productive, exactly like you just said. So I guess, like, is, is there a new term for this role or this, this job that is taking, that is having traction with your customers?

• 21:10Speaker 00

  You mean the, the super AI-pilled junior legal? Nothing I've found yet. Maybe we should coin one.

• 21:15Speaker 02

  Isn't it legal, legal engineer?

• 21:17Speaker 00

  That's our, and, and also now an industry thing.

• 21:20Speaker 01

  Yeah, CSJDs.

• 21:22Speaker 00

  Exactly, yeah, yeah, yeah. And maybe that's, there are those other people that are best positioned to do this kind of stuff.

• 21:28Speaker 01

  I think that, that the derogatory term of meat proxy, where you just like sit in front of the machine and type in something that someone else tells you to type, and then you repeat what the machine tells you to say. But like, I do think a very good meat proxy is just like, well, you know agents very well. And you, you know Legora very well, and you know how to like, like, this is my toolkit. And, you know, every industry has a toolkit. And I can use my tools to do the thing that you need me to do.

• 21:52Speaker 00

  But I, I guess then you're not really a proxy, right? You're actually just doing meaningful work.

• 21:57Speaker 01

  Yeah, it's, it's just like, I no longer, like, you know, uh, well, I'll talk about tabular review, because that's, that's a thing that happens a lot. I have hundreds, thousands, millions, thousands.

• 22:06Speaker 00

  We do up to a million cells, I think.

• 22:08Speaker 01

  In a, in a single, that's impressive. We should talk about the, the, the table and the windowing. Yeah, you know, I, I'm working on a big case, I have a million documents, I type it in. Usually I'll throw a pair, throw like a team of paralegals, lock them in the room.

• 22:21Speaker 00

  So like 4:00 AM.

• 22:23Speaker 01

  Like, that, that doesn't need to happen, right? Because now they can extract it and you can go and re-prompt everything. So like, yeah, I, I think now I don't need a paralegal for that. But like, a, a, a good, like, super AI-pilled paralegal would do something else, you know?

• 22:36Speaker 00

  Yes, yeah, exactly. Yeah, they can do more stuff, or like spend more time on the things that they, you know, didn't have time for before. Or actually sleep, who knows?

• 22:44Speaker 02

  I have a question. So you guys bought a company, Kira.

• 22:47Speaker 00

  Yes.

• 22:48Speaker 02

  Is that how you say it? And you, you guys used your own product to do the M and A?

• 22:51Speaker 00

  Yes, we do that all the time.

• 22:52Speaker 02

  So how did that work?

• 22:53Speaker 01

  Ooh, dog fooding.

• 22:55Speaker 00

  Yeah, no, that works great. We're doing that a lot. Our legal team is, is, I mean, in say it's been built with our legal team. Because right now we have a Slack workflow where everyone flows their stuff in, and they're like, this is annoying. Right? And it's efficient, so it's like, great, we should do Legora for that.

• 23:08Speaker 02

  Yeah, yeah. Can you talk a little bit about that? Like, you know what that process looked like?

• 23:11Speaker 00

  Yeah, absolutely. So it's, it's, um, we do a lot of the due diligence ourselves, because we can do it with tabular review and other tools. We do still have counsel coming in to like assess certain risks. Or like, you know, there's payroll and so Zokur was simple because I was all in Sweden. But, you know, we've done one in Canada and one in Australia. And so there's like payroll in Australia. Okay, do we want someone to look at this like a bit more strategically? So there we will still use Lawrence for the strategic part, where they can actually be sparring partners and help us a lot on like how to figure out how to structure this the right way. But a lot of the more menial stuff, we could actually just do ourselves. So like, a lot of, yeah, a lot of the early things we would find, and we have had cases where we found something, that's been like a red flag and then we've, we've pulled the brakes.

• 23:55Speaker 02

  Can you talk a little bit about any of those?

• 23:56Speaker 00

  No, I don't think so.

• 23:58Speaker 01

  Yeah.

• 23:59Speaker 02

  All right. Early on, you said you, your early customers were Swedish, like Swedish law firms? Have you seen a difference between working with like Swedish law versus like American law firms? That sort of thing? And you guys are mostly working with like big, big law firms, right?

• 24:14Speaker 00

  Well, we're also, smaller law firms also. No, we, we definitely started really, really big law firms, but 50 Lawrence also. And, and get a lot of value.

• 24:23Speaker 02

  Yeah, so have you seen differences between working with like the Swedish ones versus American ones? Maybe like even, I don't know, Asian ones?

• 24:29Speaker 00

  Yeah, yeah. I think the European ones have been a bit slower to move. The American ones are very forward, move really quickly. I think it's also very high on their agenda of the American companies, more so than the European ones, I think. It's like a strategic, super important thing we need to just like do a lot here. The American companies generally, both corporates and law firms, also have a much higher appetite to like custom build stuff. That's like a thing that they all want to do. Like, hey, we want to build this like huge thing with you guys and like structured in whatever way. Where Europeans are much more like, we'll just take the off the shelf and.

• 25:04Speaker 02

  What's an example of something they would want to build themselves?

• 25:06Speaker 00

  Integrations into their own, like, some of these customers built their own CRM and their own document management system and their own all sorts of stuff. And they want to build that, and then they want to build triggers that like you do a review in, in Salesforce and goes to this one person for whatever reason, and they do something and then it goes into Legora and then it goes back in. And there's, that's like the simple end, and there are some that are extremely ambitious, where it's like a whole new product that they want to build with us. And I, you know, we can't really do that.

• 25:33Speaker 00

  But, but that's definitely a thing where like, American companies really want to build their own more than European ones do.

• 25:39Speaker 02

  And the European ones are like, hey, like, you know, they give you product suggestions or?

• 25:43Speaker 00

  Yeah, for sure. I mean, we have great collaboration with all of them. So they'll, they'll say, hey, this sucks, this is great, we want more of this, and we'll just build a, a product that does that.

• 25:52Speaker 02

  Okay, so they don't see like an existential threat here in their business? Whereas the American ones do, or?

• 25:58Speaker 00

  I don't know if that's the reason that they want to custom build versus not custom build. I think they both know that this is like extremely important and key to their firm's success and their corporate success. So they, it's both extremely important. I think it's just a different way to achieve it.

• 26:12Speaker 02

  Okay. Another question, I think maybe you, you want to bring this up, is like product metrics. Like, how do you know that, like, you know, we're actually doing something good here? Yeah, how do you think about that? I'm assuming that's also related to evals.

• 26:25Speaker 00

  So we have the regular product metrics that we care a lot about. Are people spending a lot of time in our product? Do they seem to get a lot of value out of it? Do they renew it? Do they come back a lot? We have really good numbers for an enterprise software of like our Dow over Mao and our like, you know, our spend per month in the product are extremely high. And then we do some sort of, we do online evals also, where it's like, try to figure out generally, like, do we solve the problem here? Just with like a super cheap, a little message, just try to just like have an online metric. And then we can use that also when we do rollouts of new things. We can just like compare feature flag wise, okay? Does it, did it improve or like, did it catastrophically decline? Because one thing actually that's, might be interesting, that's difficult for our businesses, we can't look at any traces, basically. We can't look at any data because it's all super confidential.

• 27:11Speaker 00

  And that's like extremely frustrating to work with, because you, you basically don't know what people are doing. So it's like, here's an agent and it can do so many amazing things and I have no idea what people are actually doing.

• 27:20Speaker 02

  I would have assumed you guys like signed some sort, sort of agreement with the law firm and they're like, oh, yeah.

• 27:24Speaker 00

  I wish, yeah, I wish. No, but the thing is like, a lot of the data that they have is not even theirs, right? It's their client's and it's super confidential, so we can't look at it. And so basically we have an evals team that's like trying to approximate what we think everyone is doing and like build that into eval sets. So that's just like a super annoying kink of the business.

• 27:41Speaker 01

  Can you do paraphrase? So for example, ChatGPT has like a slash feedback thing that directly fully says such full trajectory. But obviously that, that is not possible for you guys. But you can use an LLM to paraphrase, like, from this real thing, make a synthetic thing that is like close enough, but change all the names, change all the details, but like still.

• 28:03Speaker 00

  Yeah, yeah. We can't, there's, I mean, there's always a, a, a range, right? Of like, if you, if you paraphrase all the way down to like three values and you pick one of them, then obviously that's fine. If you, if you just remove the names, then that's maybe, maybe not fine. It's like, we are generally pick the, the most safe way. It's like, we, we restrict ourselves as most possible because we, you know, there should be no risk at all. But there are things where it's like, okay, we know that the failure modes are probably these 10 or 20, so we can classify it into one of those and that's a helpful signal. We can classify it into the types of tasks and the practice areas also. And then like we have an idea. It's something that we're always trying to, to figure out how to do in a smarter way.

• 28:42Speaker 02

  Also, like on the privacy front, I guess, I'm assuming even two years ago, it must have been like insanely difficult to get the law firms to be okay with this. But like, how do they think about their data being sent over to Anthropic or? It must be like a huge thing.

• 28:56Speaker 00

  All of our infrastructure is on Azure. Primarily for this reason, because like when we started, law firms were like, AWS? No, like, no way.

• 29:05Speaker 01

  Law firms don't trust AWS?

• 29:07Speaker 00

  Yeah, yeah. It's different now. No, but it, they were like Amazon, Google, we can't trust them with any of our data. So we, basically we had to host everything on Microsoft because they already have 365.

• 29:16Speaker 02

  Oh, so they're okay with Microsoft?

• 29:17Speaker 00

  Exactly, because they've already done like whatever security review, et cetera, of all of their documents and all of their Word and whatever. So like, Microsoft is an approved vendor in their mind. And so we had to host everything on, on Azure. And that's changed over the past few years. So like now people understand, okay, we need to get on cloud, we need to do all this kind of stuff. There was also a lot more people talking about on-prem back then. That's also disappeared completely. People understand that like, you should just do it in the cloud and it's, and it's safe and it's probably safer than what you're doing.

• 29:41Speaker 02

  Yeah.

• 29:43Speaker 00

  So that's changed a lot.

• 29:43Speaker 01

  And by the way, it's only been three years, so like, it's actually like.

• 29:47Speaker 00

  Yeah, yeah, it's a huge shift. It's, it's, it's great. I mean, good for you guys, but yeah, I mean, I don't expect the, like, you know, the legal firm, legal industry has somehow ignored this for the last like 10 years.

• 29:56Speaker 01

  Yeah, yeah. I think, I think we needed the AI kicking the butt for everyone to understand that we need to change our ways a little bit.

• 30:03Speaker 00

  Okay, okay.

• 30:04Speaker 02

  So also then on like open source models now are getting really good. So yeah, how are you thinking about that with the?

• 30:10Speaker 00

  Yeah, we're just thinking about, to your point, just bring our clients along on like the Pareto Frontier. And like the map of all the models and what they're good at and their latency and their costs and their

• 30:24Speaker 00

  governance and their regional availability. How do we just optimize across all of that? So some OpenWaze models are great for certain tasks and then we'll use them there. Some will post-train and some will just use the Frontier models.

• 30:36Speaker 01

  Yeah, you call it model arbitrage. You have different favors, you did some research on this, where you were firmly anthropic at the start of the year. Grok is improving a lot. Yeah, you want to give an example of a model that wasn't ranked highly overall, but like you want to shout it out as surprisingly good?

• 30:55Speaker 00

  Yeah, I think not overall good. Gemini, one of the early Geminis, yeah, extremely good for certain types of transcription and speaker attribution. So we use that for transcription.

• 31:07Speaker 01

  Oh, so you have a

• 31:08Speaker 00

  Yeah, like a granola. We don't have, we actually probably will build like a meeting thing. But this is just like talk to speech, speech to text, text to speech, just like in any other app that has this. And we do actually also transcribe files. If you upload hearings or whatever, we'll then like transcribe them, put them into text, and so we can do all of our analysis on it.

• 31:28Speaker 01

  No Eleven Labs?

• 31:29Speaker 00

  No, Eleven Lab, for DPA reasons. Same thing is like the data processing agreement, I should say. So like our data processing agreement has very few vendors on it.

• 31:37Speaker 01

  Yeah.

• 31:38Speaker 00

  Because it's really difficult for us. Exactly, we need to keep it super tight on where any data goes and so.

• 31:43Speaker 01

  I think, no, that is one of the benefits of like a Gemini and OpenAI where you come to us, we have most of the things that you need. And that is actually very valuable, even if it's like, it doesn't have to be like still at the art. It's almost just like mostly good enough for all tasks.

• 31:58Speaker 00

  Yeah.

• 31:58Speaker 01

  Then who cares?

• 31:59Speaker 00

  Yeah. Yeah, absolutely. I should actually shout out also Microsoft's transcription model.

• 32:05Speaker 01

  My Transcribe?

• 32:06Speaker 00

  Yeah.

• 32:07Speaker 01

  Okay.

• 32:07Speaker 00

  It's great.

• 32:08Speaker 01

  Okay.

• 32:08Speaker 00

  It's better than the old Gemini.

• 32:10Speaker 01

  Yeah, yeah, yeah, they did some good results. I don't know, don't even know, like, I think like usually all of them are like top two, top three, top four in terms of like the arena scores and that's good enough.

• 32:20Speaker 00

  Yeah, exactly. And it's like you have all the governance and it's super scalable and it's like, then that's probably good enough.

• 32:24Speaker 02

  Yeah, I was gonna say like, at this point, are pretty much the speech to text models like good enough to where you're like, oh, one word here or there, if it's off, that's fine.

• 32:32Speaker 00

  No, no, no.

• 32:33Speaker 01

  For sure. Like, I've done this a lot.

• 32:35Speaker 00

  And particularly in legal, there's like some, we had this thing where I think it's, I forget if it's like in Australia where there's like a certain name for like a person in court. And it would consistently transcribe it as condom.

• 32:49Speaker 00

  So there, yeah, there's certain things that you don't want there.

• 32:52Speaker 01

  Yeah, but so usually you run an LLM layer on top of it. And then you extract some keywords and then you run the transcription model again with the keywords. Like this is kind of my workflow so far. But yeah, if you've just done this on any large scale, you will pick up tons and tons of transcription errors on any domain that is not like

• 33:11Speaker 01

  average day-to-day conversation.

• 33:12Speaker 00

  Yeah. Yeah, absolutely. If there's any sort of jargon in there, it's gonna be tough.

• 33:17Speaker 01

  Yeah, like I think Whisper and Eleven Labs still transcribe Claude code as cloud code.

• 33:25Speaker 00

  Yeah.

• 33:25Speaker 02

  Yeah, I've actually had that problem.

• 33:27Speaker 01

  Very, very common.

• 33:28Speaker 00

  Yeah.

• 33:29Speaker 01

  So like that's how you know there's like a lot more to improve.

• 33:31Speaker 00

  Yeah, absolutely.

• 33:33Speaker 01

  I do want to cover a little bit on the agent product side. So we've covered a few of the top level stuff, right? We've already named job tabular review, we named jobs intake. And you've got some other stuff that we haven't even touched on yet, but I just want to cover the big two, let's call it. Is that, is that fair to say the big two?

• 33:52Speaker 00

  Agent and tabular review. And our probably, yeah, and our Word add-in.

• 33:57Speaker 01

  Okay.

• 33:57Speaker 00

  It's also something, because that, a lot of people work inside of Word, and so our Word add-in is a huge, an Outlook add-in also.

• 34:03Speaker 01

  Yeah, so I just want to cover like the big ones that everyone must know.

• 34:06Speaker 00

  Yeah.

• 34:07Speaker 01

  So tabular review is basically like fan out of like a lot across each document. You can ask the same question across all documents, collect it on a table and then work back and forth. A million is impressive. What's any other like engineering considerations or performance things? Like what's hard about this?

• 34:24Speaker 02

  Before we do that, can you just like walk through like what is the user experience for a lawyer? And then like

• 34:29Speaker 00

  Okay, so you want to use the top level flow?

• 34:31Speaker 02

  Yeah. Yeah, yeah, like, so like what are they doing like with tabular review? And then we can go into that.

• 34:35Speaker 00

  Sure.

• 34:36Speaker 02

  Yeah.

• 34:36Speaker 00

  So they, it's typically, I mean, a good example is just a due diligence, right? Where it's like, we need to review all employment contracts, all supplier contracts, all of whatever. And so employment contracts, you put 10,000 employment contracts in there and then you

• 34:49Speaker 02

  Like each cell is one employment contract?

• 34:51Speaker 00

  Each row is one employment contract. And then for cells, you ask questions basically. So like the first question, the first, sorry, per column. So the first column might be, what's the termination period? And then it's gonna like fill out for everyone, it's 30 days or whatever it is. And the next question is like, is there an IP assignment clause or whatever? Next one is like, how much, you know, how much do we have to pay them if we fire them? Or whatever it is, like how much are they getting paid? And then it's gonna fill out the entire thing. You can also just ask the agent to do this. Like if you just drop 10,000 files into the agent and say like, do a due diligence on this, it will spin up a tabular review and run all of them and wait for it to be done. And then analyze the results and it can then highlight like red flags. Okay, this, the CEO is getting paid an outrageous amount or there's like this weird bonus structure. Okay, then like obviously we need to look at that.

• 35:36Speaker 00

  And then the agent from that can draft a memo to send to the client. Or it can just do the review and then have, you know, lawyer, the user just be like, okay, let's, let's look at this, here are the red flags. There's also collaboratives that you can comment on it for other people to look at, et cetera.

• 35:51Speaker 02

  And why do you choose that like spreadsheet format?

• 35:54Speaker 00

  Yeah, it's just a lot better to, it's super easy to work with, work in. It's really easy to get an overview super quickly of what's going on and to review it. So all of the stuff that we produce also has citations back to source documents. And so you can basically review it super easily if you want to just make sure that everything's right. You can also like highlight cells, these are reviewed or whatever, these are the ones that are flagged and you can comment and collaborate. That's much easier than any other form factor that we've tried.

• 36:20Speaker 01

  Yeah, I would say that the spreadsheet form factor has, has a lot of pull in some areas, but somehow hasn't really spread. I find it very weird, like Clay is another one on the GTM side that, you know, very known for the spreadsheets. You guys, I don't really know if anyone else does a large spreadsheet AI thing.

• 36:40Speaker 00

  No, no.

• 36:41Speaker 01

  There was like V7 that like tried to launch, there's like Sheets, there's, even in finance domain, I don't really have like a top name that like does spreadsheets.

• 36:51Speaker 00

  Does this really well, yeah. I agree, I think it's like a great, if you, if you have fan out and you do the exact same thing and you're extracting stuff, it's such a great form factor to like understand what's going on.

• 37:01Speaker 01

  Do you find like you must export to Excel or like people are happy to live in your spreadsheet?

• 37:05Speaker 00

  People are happy to live there.

• 37:07Speaker 01

  Do you use AG Grid or your own?

• 37:09Speaker 00

  We do use AG Grid.

• 37:10Speaker 01

  That seems to be like the leading one. I mean, they've done this for like, I don't know, 15 years.

• 37:13Speaker 00

  Yeah, yeah, they know how to, yeah.

• 37:15Speaker 01

  Yeah, so, so, yeah, I mean, I'm happy on that spreadsheet angle. I mean, I think the only other interesting thing for me engineering-wise is the fan outs.

• 37:22Speaker 00

  Yeah.

• 37:23Speaker 01

  Engineers maybe can, are well-equipped to understand the trade-offs of like, well, okay, before you use fan this thing out on a million documents, maybe test it on like two.

• 37:33Speaker 00

  Yeah, yeah, does that work before you go nuts?

• 37:35Speaker 01

  Yeah, do they do that?

• 37:36Speaker 00

  Yeah, they will. So our tabular review actually will run the first 10 rows.

• 37:39Speaker 01

  Yeah, just check, right?

• 37:40Speaker 00

  Yeah, does this make sense? Did it show us what we thought it was gonna show us?

• 37:43Speaker 01

  Yeah.

• 37:44Speaker 00

  That's really good. Oh, but also for people, when people built this, it's just really good for them to iterate quickly on the first 10 rows until like they have a, they're getting the results that they want and then they can go ham.

• 37:53Speaker 01

  Yeah, I am happy to move on to the next thing, intake, which is your Slack bot. Everyone has a Slack bot. What's different about yours?

• 38:00Speaker 00

  So ours is just legal specific. And what, what happens with ours is it's not actually, it might also, we will probably also build one that's just an interface to the agent. But it's actually specifically to basically kick off an agent that then adds a task to our list. So we have this list thing, which is like linear, first, you know, that's the closest equivalent. And so it will add it to a specific intake list. And then lawyers and agents can go into the go or just be like, okay, these are the things that, you know, people are sending to us as our law firm or as our legal team in a big corporate. We can kick off agents for them, we can collaborate on them, and then we can just like mark them as done and then it gets sent back in Slack. So it's more of a, it's not just like kicking off an agent, it's more of a like, I don't know, storefront thing where it's like, here's the ticket, I want this thing reviewed.

• 38:46Speaker 00

  Okay, now it's, now here it is, it's back, no one needs to change anything. And the legal team just sits in LaGor and like manages the agents and everything there.

• 38:52Speaker 01

  I think the, the data structure for this kind of thing is really interesting because it's like basically the inbox, right? For all these kinds of queries that can potentially translate into a thing, into something else, into something else. And like, I don't know, is it hard to integrate all these with all the other features? Or do you just not worry about it?

• 39:11Speaker 00

  It's, no, it's not. I think we have Some primitives that work really well. So like lists is a great primitive because it's essentially, it's like extremely flexible. It's also like a notion database.

• 39:21Speaker 01

  Yeah, a notion database.

• 39:22Speaker 00

  It's like a notion database. And so you can basically configure it for whatever you want. And we of course invest a lot into making this super scalable and work really well. And you can have triggers on them, automations on them. And it's like a great glue to glue everything together. Cause then you can kick off an agent run based on a list if something happens. And then that comes back and populate to a field or whatever, add new documents or whatever it is. And so it's like, just like you might coordinate a bunch of coding agents with linear or some sort of task management tool. We can do it similarly with lists. And so like agents can create lists and lists can create agents and agents can read lists. And so it's like the agent swarm comes alive.

• 39:54Speaker 01

  Yeah. Do people get excited or overwhelmed by that? You know, like I, I feel like this is basically end user programming. You're, you know, you can let people set up crazy automations. Some people get super obsessed by it and they become like influent, like, you know, it'd be cool to have like.

• 40:09Speaker 00

  Yeah, like Clay has influencers.

• 40:11Speaker 01

  Yeah. Is that worth it? To overcomplicate it?

• 40:14Speaker 00

  We need the, the flexibility, even if we don't actually expose it to the end user. Let's say this was just all internal, then it's a really fast way for us to utilize people, people like our legal engineers to basically build a lot of products extremely fast. So like you can build custom like fund management dashboards. You can basically build that on list with like your own a generative UI. And then you basically have a new product that some people are going to love. And we can have a marketplace of just like a bunch of specialized products that we can scale super quickly. Cause all of our legal engineers can just build new ones. If they're out with a client or you want your own, easy, like we'll just fix one for you. So it's like a lovable inside Legora a little bit. And if we don't want to expose it, that's also how we build our own custom features. So we, we made another acquisition in the UK called Wexler.

• 40:57Speaker 00

  And they're doing fact intelligence, which is for litigation mostly, which is like you upload a million documents. They're for a lawsuit or whatever. And then we extract facts from those with like named entities and dates and whatever. And then when you have all the facts, you can basically hold them up against each other and see which ones are corroborated and which ones are, um, what do you call disagreement, they, you know? And that's extremely powerful because then you can also transcribe a court hearing. And you'd be like, oh, he said this thing, but actually the email over here says that he was not there. Uh, and it's like, if you see it live, it's like so fucking cool.

• 41:32Speaker 01

  Yeah.

• 41:33Speaker 00

  And that we can also build on this primitive. And so like, we can build a lot of really cool things on this one primitive, basically. That's how we think about it. It's like, we have to be, as we scale the company, we just have to solve so many things. And like, so, so I think a lot about how do we build a core primitive that we can scale to, to many different end products and create very customizable experiences.

• 41:52Speaker 01

  Okay. So you have, uh, what, what core primitives do you have? Let's just restate for, for people.

• 41:56Speaker 00

  Lists is a core one. Yeah. Super configurable and yeah, projects, it's basically containers of files, file systems. Um, the agent, of course, you can kick that off and run that in very different configurations.

• 42:07Speaker 01

  Do you have a name for the agent by the way?

• 42:09Speaker 00

  No, we don't.

• 42:10Speaker 01

  Just intake.

• 42:10Speaker 00

  No.

• 42:11Speaker 01

  Okay.

• 42:11Speaker 00

  Yeah. No, you mean like they called it like a layer or like we gave it a name?

• 42:15Speaker 01

  Ooh, yeah.

• 42:16Speaker 00

  Yeah. Yeah. Layer would be cool.

• 42:17Speaker 01

  Yeah.

• 42:18Speaker 00

  Um, people used to talk about Leia as like a, a named entity.

• 42:21Speaker 01

  Yeah.

• 42:21Speaker 00

  Um, but yeah, we stopped that. Maybe I'll bring it back.

• 42:25Speaker 01

  It might be confusing. So list, agent.

• 42:27Speaker 00

  Uh, tabular review, which like we're considering, is that actually an instantiation of like, you can take this as far down as you want. Right? But those are probably the big, the big ones. Yeah.

• 42:37Speaker 01

  Yeah. So I actually wanted to talk a little bit about like FTEs. Cause this sounds kind of like that. And I think Max has talked about that a little bit. Now like, okay, when you onboard a new like big customer, you want to get them value like ASAP so that, you know, they stay on, stay on Legora.

• 42:52Speaker 00

  Yeah.

• 42:52Speaker 01

  Yeah. How has that evolved? Like, when did you guys start that forward deploy team?

• 42:56Speaker 00

  So we hired our first forward deployment in New York. That was our first hire in New York, also Y C founder, nine months ago, maybe. I'm not actually sure.

• 43:04Speaker 01

  Are they considered legal engineers or no?

• 43:06Speaker 00

  No, no.

• 43:07Speaker 01

  Okay.

• 43:07Speaker 00

  True engineers, but we do, it, it is something that I think about is like, how do we exactly enable that at scale? Um, and I think a really core thing is like, how can we empower our legal engineers? Like, how can we power our power users and our legal engineers to customize the product in a powerful way? And then of course we, we'll still have forward deploy engineers to like help out, you know, do all the custom integrations and the, the scoping and figuring out what's possible and feed all of that back into core product development. So that's kind of how I think about it's like almost a first line, second line defense. It's like legal engineers should be able to customize a lot of stuff and build a great experience. And then where they can't, or we need to make core product changes or custom integrations or whatever. We have forward deployment engineers who also then cycle in a little bit behind like, sometimes they'll just work on the product and sometimes they'll work with clients.

• 43:52Speaker 01

  Can you walk through like an example, like, okay, so you just got, you just got this new client. Like what's step number one? Like, are you guys like, okay, hey, we have a forward deployed engineer for you guys. They're going to go build, you know, some kind of product for you. Like, how does that work?

• 44:05Speaker 00

  So it's very different client to client, right? But, um, if it's a big client and they're super engaged and they like, we want, they have all these streams of things that they would want to do, or they already have, typically they have already tried to build something and it's failed. And they're like, this is what we, this is a problem that we'd like to solve. Um, then we'll, we'll basically staff them with legal engineers and a forward deployed engineer potentially, depending on what, you know, their thing is. And then we'll just be like, hey, these guys will come, they'll make you successful. They will sit with all your lawyers and teach them how to use it and like figure out all the workflows that you have right now and, and build them into Lagora. And some of that will just be a legal engineer and some of that will require a forward deployed engineer.

• 44:39Speaker 01

  What is that separation? I guess, uh, if you could like talk about that a little bit.

• 44:43Speaker 00

  Legal engineers configure the product as a power user would. They don't write code.

• 44:48Speaker 01

  Yeah.

• 44:48Speaker 00

  And a forward deployed engineer writes code into production, basically. I guess that's the, that's the.

• 44:53Speaker 01

  What kind of background did the forward deployed engineers normally have? He said Y C founder.

• 44:57Speaker 00

  Yeah. Founders, regular engineers.

• 44:59Speaker 01

  Yeah. Like, yeah, Dee was your.

• 45:01Speaker 00

  Yeah, exactly. Dee was our first, yeah.

• 45:03Speaker 01

  Two Y C companies and worked on search at Meta.

• 45:05Speaker 00

  Yeah. She's awesome. Yeah. Yeah.

• 45:08Speaker 01

  Okay. That's a high bar.

• 45:09Speaker 00

  She's great. Yeah. Yeah. First, first boost on the ground in the U S.

• 45:13Speaker 01

  Yeah. So what are some examples of, I don't know, workflows or things that these people are building for the clients? Or do you guys have like, oh, these are like, you know, there's a couple of use cases that like all the law firms are like, you know, this is the first thing that our F Ds are going to do when they, when they go in.

• 45:28Speaker 00

  It's very different. Um, some core workflows everyone have, and we can just build in Lagora. And that could be anything from like, um, this is how we handle these types of N D As or whatever. And then it's just like, you activate it and it's more like skill building really for at least. And most of the F Ds, that's more like, there's something that we can't do yet. Like we need some more flexibility in some of the primitives or whatever it might be. Or we just have this really complex system that we need to integrate into. And then they'll go out there and they'll build the integration against our APIs and maybe expand our APIs or whatever to make that work.

• 45:59Speaker 01

  And how does the like legal structure work there? Because you said you guys yourselves can't even work on deals.

• 46:06Speaker 00

  Yes. Yeah.

• 46:07Speaker 01

  So like, how, how do they work on client projects?

• 46:09Speaker 00

  You mean the law firms, how do they work on client projects?

• 46:12Speaker 01

  Sorry. How do your F Ds work on client projects?

• 46:14Speaker 00

  So they don't touch the data still. So they'll just build the system. Um, but they will also be onboarded like an employee sometimes. So like they might get a laptop and everything.

• 46:22Speaker 01

  Like to the law firm?

• 46:24Speaker 00

  Yeah. Yeah.

• 46:24Speaker 01

  Oh, wow. Interesting.

• 46:26Speaker 00

  That doesn't happen very often because like usually they'll just build an integration and like kind of works. But they, yeah, they can if they need to.

• 46:31Speaker 01

  And you only onboard F T's into a customer, I'm assuming if they're a certain size.

• 46:35Speaker 00

  Yeah. Yeah.

• 46:36Speaker 01

  Okay.

• 46:36Speaker 00

  It needs to make sense. Cause our F Ds can also work on core product, right? So it's like, it's a constant prioritization thing.

• 46:42Speaker 01

  Is there a rule like, uh, I guess, does, uh, every like, you know, so Palantir famously had like, you know, four days you spend onsite. One day you come back and contribute back to products, anything like that?

• 46:53Speaker 00

  No, we don't. I mean, to be fully honest with you guys, it's still, it's still, you know, it's still early days in a lot of this.

• 47:00Speaker 01

  And where do you see it headed maybe over the next year?

• 47:03Speaker 00

  I do think that it's going to be more, maybe not exactly like Palantir, but like we, I think we will have a larger in constant circulation group of F Ds that way we sit with a client for like two months or whatever to build out this one thing. And then they go to the next one, et cetera, et cetera. Yeah. But I do imagine us rolling in with legal engineers and forward deployed engineers to like work on specific projects.

• 47:23Speaker 01

  Hmm. Yeah. The API business is actually very interesting, like, like you said, um, because, uh, you know, that's another rule that you can have where you were CTO, maintainer of the Legora platform.

• 47:34Speaker 00

  Yeah.

• 47:34Speaker 01

  Right? Like we will offer everything that we have in the Legora web app.

• 47:38Speaker 00

  Yeah.

• 47:38Speaker 01

  As an API, and then you guys can use whatever. Is, is that, is that a promise that you make or?

• 47:43Speaker 00

  That's not something we're promising now.

• 47:44Speaker 01

  Yeah.

• 47:44Speaker 00

  Um, we do have APIs that you can build against, but not the entire surface of the product.

• 47:49Speaker 01

  That's the curious thing, like, is that the strategy? Or, and obviously, you know, some people will love it because I, I don't have to learn a new tool. I can just use the existing tool I have, right? And then I just like, yeah, install Legora, for example, with the, the word document stuff. Other than that, you know, I, I do think like then you have to maintain it.

• 48:07Speaker 00

  Exactly. That's, that's, so that's been my thing. That's why we've tried not to do it. Uh, we haven't, we haven't had APIs. I mean, we started our APIs like six months ago or something. We folded for a very long time, mostly because, yeah, I just don't want to, uh, we, we moved so quickly in, in the product that I don't want to be like slowed down by having to maintain all the API versions for like a data model that we've changed. I mean, now we're bigger and things are different. So now it's, it's a cost that we can take on. But like when we're 20 engineers, it's just like, we, we moved so quickly that we can't do this.

• 48:35Speaker 01

  I've toyed with this, right? Like it's just generally good for all companies to have a platform team and a product team. Because the product team, you have one, but then you can easily spin up a second one as long as the platform is not super tied to product.

• 48:47Speaker 00

  Yeah. Yeah.

• 48:47Speaker 01

  Uh, you know, like a, a very simple one is web app, mobile app, right? Or like web app, mobile app, uh, M C P. And then like, you know, whatever, like other, other integrations. Uh, then your F Ds just are one more client to the overall platform anyway.

• 49:01Speaker 00

  Yeah. And I think like even the agent, you can think about it this way. There's like a harness team or like a, that runs the agent. And then you can even, you can build a product around it with like skills and automations and whatever else.

• 49:11Speaker 01

  Yeah. This, this is like very famously the Amazon, uh, web services mandate. Like, uh, Bezos was like, guys, no more backdoor access. You only offer other teams, your APIs, the same APIs you offer customers. If you don't have it, you build it.

• 49:24Speaker 00

  Yeah.

• 49:25Speaker 01

  And then the customers also get it.

• 49:26Speaker 00

  Yeah. I think, I think that's also changing a little bit. A lot of, um, a lot of APIs now, like one thing that we're toying with is like, can the agent be the API? I know it sounds weird, but like for some of this stuff, what they actually want to do is they want to trigger certain things to happen. For some part of this, it could, you could just be, I'm not saying that we're doing this, but it's like a thing that I'm toying with in my head is, could that just be like, okay, you triggered the agent and ask it to do this thing. Like obviously it's way less efficient than if you just had like an API that you always hit. And it's like, you know, but it's something that I'm toying with is like, how much of our product can just be the agent? Or solely other stuff?

• 49:58Speaker 01

  Well, you know, unbounded execution and costs and latency.

• 50:01Speaker 00

  That's the.

• 50:02Speaker 01

  That's, is that the only whole batch?

• 50:04Speaker 00

  Yeah. And then I think deterministic, like maybe in, you know, a hundred out of, or in two out of a hundred times, it's going to do something whack that we didn't want it to do.

• 50:12Speaker 01

  We're going to go into like harness and model, uh, fine tuning in a bit. But I think there's a, there's a product question about restraint, about what you don't do.

• 50:20Speaker 00

  Yeah.

• 50:20Speaker 01

  Because you could do all that. And obviously there's a prioritization issue. Like, are you at more on the point of, let's, uh, say no to most things and then only do a short number of stuff? Or no, actually we want to do more things and we need, just need to hire like 100 people?

• 50:35Speaker 00

  I was, I was very strongly the first thing for a very long time. Let's just say no to everything, like keep the engine team. I, I think, um, I've said this before, but like one of our presentations that like after I've been at Legora for half a year, I, I pulled up this slide of, um, you know, the 300 Spartans and, and for the movie and I was like, we're just gonna be 20 engineers for the rest of the company's history and like, we're gonna beat everyone who's much bigger. And we're 100 engineers now and it feels like we're way too small. I wanted to do that, but I think the, in the real world, we're in like fierce competition. People want so much stuff. It's like, uh, I could be a puritan and just be like, no, we have to stay 20 people and we can only build, you know, whatever, uh, but then we just lose, uh, and like people would go elsewhere. So we have to build more. And so I think my job is to figure out how do I build a system where we can build a lot,

• 51:20Speaker 00

  but actually only like where we can, the, the customer feels like we've built so much stuff, but we've actually only built a few things. That's, that's how I think about my job right now.

• 51:27Speaker 02

  Yeah. I mean, primitives is right, you know?

• 51:29Speaker 00

  Yeah, exactly. I think that's gonna be, that's really powerful.

• 51:31Speaker 02

  Do you testing your products, just seeing if like, hey, there's like any pull here? And then you just kinda like, you're like, no, let's just focus on our main thing.

• 51:38Speaker 00

  Ooh, we haven't made, I mean, we've made certain strategic bets.

• 51:43Speaker 02

  Yeah.

• 51:43Speaker 00

  But we've not tried anything that we don't have a lot of confidence in already. Mostly because we just have like a mountain of demand.

• 51:49Speaker 02

  Yeah.

• 51:50Speaker 00

  It's like, we want all of these things. And so it doesn't, hasn't really made sense for us to try to be like, hey, what, maybe this thing could work. Cause like, there's so many people screaming for the other things. And so we mostly, uh, build those. And then sometimes we'll disagree with clients and we'll be like, actually, I think this thing over here will make a lot of sense strategically, and then we'll try to build that anyway.

• 52:06Speaker 02

  Like strategically for you?

• 52:08Speaker 00

  Yeah, exactly.

• 52:08Speaker 02

  So what are those things?

• 52:10Speaker 00

  So one of those things, um, was, uh, the agent, actually. So like, no one was actually asking for like, I wanted to be, uh, I want the assistant that I'm using to have more agency and do things without me asking it. Like no one, no one ever, but we're just like, this is definitely why the industry is going. This is gonna empower you to do so much cool stuff. Um, collaboration was another one where we're like, we think the industry is going in a place where you can collaborate inside of where you're working, which is Legora and not in like emails and text messages. So yeah, there, there are, there are a few of those.

• 52:38Speaker 02

  And then how, like, once you say, okay, yeah, we want you guys to use agents. I'm assuming like internally at the law firm, you know, it's gonna take a lot for them to actually learn how to do that.

• 52:48Speaker 00

  Yeah.

• 52:48Speaker 02

  And so that's where you kinda like say, hey, FDEs, go in there and teach them what they can do.

• 52:52Speaker 00

  Yeah, legal engineers, mostly.

• 52:53Speaker 02

  Oh, legal engineers.

• 52:54Speaker 00

  Yeah, yeah.

• 52:55Speaker 02

  That makes sense.

• 52:55Speaker 00

  But they're like, some people call them forward deployed legal engineers if you want, but that's essentially what they are. Um, then they go in, yeah, and help, and help them structure their workflows around, uh, the capabilities of the agent.

• 53:05Speaker 02

  You guys said previously, I think Max said this, but that early on specifically, you guys weren't fine tuning your own models. Is that still the case?

• 53:14Speaker 00

  Yeah. So we haven't fine tuned any models up until now. I think now in the past few months, open weights models have become extremely capable. And so we will do it for certain tasks where we think there's a huge delta between what a frontier model can do at the cost and latency versus what we think a, a, a post-trained model can do. Legal research is a great example. It's like a, you have to make, it's a, it's a fan out retrieval problem and you can make a really effective, uh, model to do those queries super quickly and super cheaply at low latency.

• 53:43Speaker 02

  So specifically you're post-training them to be better at?

• 53:47Speaker 00

  Very specific bounded tasks. Yeah, exactly.

• 53:49Speaker 02

  Okay.

• 53:50Speaker 00

  Yeah. We're not trying to like train our own Fable.

• 53:54Speaker 02

  Yeah.

• 53:54Speaker 00

  To like be the main agent. I, I don't think that's like a, we won't win that, you know, versus Anthropic, most likely.

• 54:00Speaker 01

  There's still a lot of us, let's say, search and retrieval research or RAG research to do.

• 54:05Speaker 00

  Yeah.

• 54:05Speaker 01

  Uh, that is like maybe less glamorous. It's not actually even model training sometimes. It's just like architecture and pipelines. You, you, you did a case study with, uh, TurboPuffer, but like, you know, there's also like, uh, do you do late interaction of?

• 54:19Speaker 00

  Yes, absolutely.

• 54:19Speaker 01

  You do that?

• 54:20Speaker 00

  Yeah, uh, we actually don't do that, but it's, uh, you're completely right that this is, uh, so there's one guy on the team, son, who's, uh, he just really cares about search and he, he basically comes to me all the time. And he's like, we should do these things and like, there's these new embedding models and like, we can do this late, and late interaction. He actually talked to TurboPuffer teams to get them to build multi-vector so that we could do these types of things. But no, there's loads of, uh, low hanging fruit generally, even before models. And even in the harness, honestly, like, if you just wanna create a better output for our clients, there's like so much stuff that we can do that has immediate impact before training models.

• 54:51Speaker 02

  Like what makes a good harness for like the law industry, I guess? Like you guys are making, I'm assuming like your own custom harness.

• 54:57Speaker 00

  Yeah, yeah.

• 54:58Speaker 02

  Yeah.

• 54:58Speaker 00

  The way that we edit files is important. The way that we do an analysis is important. Uh, the way you do legal research is all baked into it. So it's like, you might have a problem that comes up or sees something, then it knows how to go and do the legal research to figure out what the answer is, what the precedent is. That's all very important. And then of course, there's all the governance stuff around it as well.

• 55:17Speaker 02

  Yeah, it seems like the search is probably like, would you say the most important tool that you guys are really customizing? Cause if you can't pull in the right information.

• 55:25Speaker 00

  Yeah, and then you're screwed.

• 55:26Speaker 02

  You're screwed.

• 55:27Speaker 00

  Uh, yeah, I think it's, it's, it's.

• 55:29Speaker 02

  You guys are searching like a lot of documents.

• 55:31Speaker 00

  And analysis.

• 55:31Speaker 02

  Yeah.

• 55:32Speaker 00

  It's search, it's analysis and it's drafting, probably. Cause like drafting word, drafting huge contracts is actually also not super trivial.

• 55:39Speaker 02

  Like what about it is not trivial?

• 55:40Speaker 00

  You have to, let's say you're drafting a huge, uh, contract from scratch, then you have to find precedents of like, how did we do this previously? Do we need this type of clause or not?

• 55:49Speaker 02

  A specific law firm, how did they do it previously?

• 55:51Speaker 00

  Yeah. So I'm, I am the law firm and I'm about to draft a huge, uh, whatever. NDA is very simple, but like there's, there are contracts that are way more, uh, complex. And then you need to find the right precedent first. Cause like lawyers just don't, don't like sit and like start typing stuff. They, they figure out what clauses have we used in similar deals. And similar can mean a lot of different things, as I'm sure you know, in search, it could be like same industry, same type of companies, same whatever. Um, and so you need to identify the right precedent. You might have like multiple documents that you then try to figure out which, which part should I take from what document? And that's actually non-trivial. So it's essentially also a search problem.

• 56:25Speaker 01

  Which model's best at drafting?

• 56:27Speaker 00

  Yeah. So I'll say, I told this, this yesterday, uh, definitely Fable and Ofas are extremely chatty. I'm sure you guys have known this, uh, they're very verbose.

• 56:36Speaker 01

  That's not good.

• 56:37Speaker 00

  That's generally not good. No.

• 56:38Speaker 02

  I've noticed Astros is pretty good at writing.

• 56:40Speaker 00

  Astros, uh, yeah, pretty good at writing, much less, more concise.

• 56:43Speaker 01

  Um, are you running like a hundred different prompts to like?

• 56:46Speaker 00

  Yeah.

• 56:46Speaker 01

  Be sure.

• 56:47Speaker 00

  We can, yeah, we can, we can do, we can do certain things, but I think the chattiness, verbores is actually a little bit difficult for us to do. So this is, I think, you know, let's see. But probably the next model from Anthropic is gonna be much better at this. Astros is actually very concise.

• 57:00Speaker 01

  Yeah, yeah. And I, I assume they, they all have a Slack channel with you and you're telling them this, right?

• 57:04Speaker 00

  Yeah, exactly.

• 57:04Speaker 01

  Yeah.

• 57:04Speaker 00

  This is not news to them.

• 57:05Speaker 01

  No, no, no, they know this. Then the other thing that I really care about is hallucination.

• 57:09Speaker 00

  Hmm.

• 57:09Speaker 01

  Do they make stuff up?

• 57:10Speaker 00

  So, uh, we have a system of, a citation system where we basically check what they're writing has a link. So the user has a link they can click and it highlights with a bounding box, like in the PDF or whatever, where, where this information was taken from. And we can sort of make sure that what it says always is citable somewhere, even multiple layers down. So like if the agent writes something based on a tabular review, you know, it can cite the cell in the tabular review or the row in the tabular review. So you can actually like click multiple layers down and find, you know, sort of validate it all the way up.

• 57:41Speaker 02

  Yeah. Are you finding that lawyers are like verifying that these citations are correct or not?

• 57:46Speaker 00

  Initially, initially.

• 57:47Speaker 02

  It's kinda like PR.

• 57:48Speaker 00

  But now, yeah, exactly. It's the same thing.

• 57:50Speaker 02

  Are you actually?

• 57:50Speaker 01

  People shit like hallucinated links to Supreme Court. They don't care.

• 57:54Speaker 00

  That happens. Yeah. Exactly. That happens. Yeah. I, I think it's like coding, you know, you have engineers that just don't give a shit and just like send agents. And you have people that like sit and read every comma. Same.

• 58:02Speaker 02

  There's just like so much that like, how can one even do that, right?

• 58:06Speaker 00

  Yeah, but I think they probably, it's just like, we know in code review what to look for.

• 58:09Speaker 02

  Yeah.

• 58:10Speaker 00

  What is the system or whatever? I think they also know, okay, this is the, the thing, these are the red, like this is the thing that's important. Let me just like double check these things. Then like, these sound reasonable, so it's probably fine.

• 58:18Speaker 02

  Okay. Interesting.

• 58:20Speaker 00

  Just like if you, if you receive something from a junior lawyer, it's the same thing you do, right? Just like, I should double check this and like, this probably is fine.

• 58:25Speaker 01

  Any other elements of, let's call it legal reasoning, or what's the, the legal frontier that, uh, models are not good enough yet that you want from the next generation of models?

• 58:35Speaker 00

  Nothing I can think of specifically right now. I think long document reasoning is still difficult.

• 58:41Speaker 01

  Long, like million token, token contracts is okay?

• 58:43Speaker 00

  Yeah, exactly. You have a huge contract.

• 58:44Speaker 01

  Yeah.

• 58:45Speaker 00

  Um, and like you're making edits across it. It's a difficult thing to do for a model today, even. Uh, and like remember that you changed all these things up here and like the definitions changed and that you, the ordering changed and whatever else.

• 58:55Speaker 01

  Hmm.

• 58:55Speaker 00

  Um, so the simplest would be one shot. You put, feed everything in and then one shot output.

• 58:59Speaker 01

  Yes.

• 59:00Speaker 00

  You don't do that. You break it up into chunks and then you orchestrate edits.

• 59:03Speaker 01

  Yeah, exactly.

• 59:04Speaker 00

  Exactly. And this is like one of those things that are funny, like that are fun to be part of in this industry, right? So our word add in was like, we've done, you know, we've done map reduce and we've changed and there was one big one. And there was like one big one in multiple times. It's like, we keep changing the, the scaffolding that we build around as models change.

• 59:20Speaker 01

  Yes. I, I, I would say I, um, I've, in recent, I do a lot of like news reporting, uh, obviously because of what I do. And I've recently shifted from map reduce to throw everything into context.

• 59:30Speaker 00

  Yeah.

• 59:31Speaker 01

  And it's, it's better.

• 59:32Speaker 00

  Yeah, exactly. But it's also, it's different. I mean, we had this problem with search where it's like, you're searching for certain things in a huge contract and you can map reduce it. But then it might, if you're summarizing any sort of thing, then it might lose some important nuance.

• 59:45Speaker 01

  Yeah.

• 59:46Speaker 00

  In between the chunks, essentially, if you just summarized the individual parts up. And so we've, this has been a problem where it's like, we can do two types of search. We can also do the other one where it's like, um, you, you need to have reasoning in, in the different steps there in between. Uh, so I'm trying to think of a really good example here. Yeah, there's, there's some documents where they talk about something at length over like, let's say two pages or whatever. And then each individual chunk is not necessarily relevant to the search term or what they're trying to figure out, but together it's extremely relevant. And so, yeah, these are some of the, you know, problems where it's.

• 1:00:15Speaker 02

  And it must be hard, like you said earlier, to actually make the models better at that cause you can't even look at the contracts, right? It's the real contracts.

• 1:00:24Speaker 00

  Yeah.

• 1:00:24Speaker 02

  So do you guys ever ask them for like, hey, can you make example contracts that are similar to your real ones?

• 1:00:29Speaker 00

  Yeah, yeah. So we have, we have feedback and can receive feedback from them. And if they're willing to engage.

• 1:00:33Speaker 01

  Yeah, exactly.

• 1:00:34Speaker 00

  Or they're just like, hey, this is like super important to us and it's not working well. And then we're like, okay, great. Can you like anonymize the documents? And like the problem then whatever, and we'll, if we can recreate it, then we can fix it.

• 1:00:43Speaker 01

  Yeah. I mean, so one version of this is you buy a law firm.

• 1:00:47Speaker 00

  Yeah.

• 1:00:48Speaker 01

  Which some people are considering.

• 1:00:49Speaker 00

  Yes, but there's some, there's some stuff there on whether their data is actually their data or if it's the client's data. So if the clients are all gone, then maybe it's fine. I actually don't know.

• 1:01:01Speaker 01

  Interesting.

• 1:01:02Speaker 00

  Yeah, but it's, yes, it's a way to get a lot of data.

• 1:01:05Speaker 01

  Yeah, people like Google is buying Spirit Airlines.

• 1:01:07Speaker 00

  Exactly.

• 1:01:08Speaker 01

  Right?

• 1:01:08Speaker 02

  Say your thing.

• 1:01:09Speaker 01

  Yeah.

• 1:01:10Speaker 00

  Yeah, they bought the, yeah, for like 10 million, 10 million or whatever.

• 1:01:13Speaker 01

  Like, you know, if you have a failed company, you still have your Slack, you can sell your Slack. I think there's like, there's like a YC company that buys your failed company.

• 1:01:20Speaker 00

  Yes, there is. Yeah.

• 1:01:22Speaker 01

  Yeah, cuz like, it's just like, oh, I just want like real people doing work.

• 1:01:25Speaker 00

  Exactly.

• 1:01:26Speaker 01

  And then, yeah, so like.

• 1:01:28Speaker 00

  Exactly.

• 1:01:28Speaker 01

  Cool stuff out.

• 1:01:29Speaker 00

  Exactly. The problem with buying law firm data is, well, you get all the inputs, the real inputs, which is great. The outputs are a little bit more difficult cuz you just get what their end result was and it's difficult to figure out if like the way, you have to basically like reverse engineer how they got there. So in our product, when we get real traces from real users, it's extremely high value. But if we just got this output and we don't know if it's good or bad or how it was created, it's a little bit difficult.

• 1:01:53Speaker 01

  We're gonna wrap up soon. The last thing I'll point people to is also, there's a lot of alpha left on embeddings. If you're a rag heavy workload, you're just looking like MTEB and you're taking like top model. You're leaving a lot on the table. You should look at like Voyage or like some of the custom embeddings.

• 1:02:08Speaker 00

  Yeah.

• 1:02:09Speaker 01

  Yeah. Yeah, so basically, don't take default embeddings, even like OpenAI embeddings, Japanese embeddings, doesn't matter. Customize your embeddings.

• 1:02:15Speaker 00

  Yeah.

• 1:02:15Speaker 01

  Right?

• 1:02:16Speaker 00

  Yes.

• 1:02:16Speaker 01

  You will support that.

• 1:02:17Speaker 00

  Yes, I think that's right. I think that's right. The only thing is, you need to make sure that you're multi-language. So for us, we serve so many languages.

• 1:02:25Speaker 01

  I mean, Europe is a king of this.

• 1:02:27Speaker 00

  Yeah, exactly.

• 1:02:28Speaker 01

  Mr. Awo helpful there?

• 1:02:29Speaker 00

  Uh, no.

• 1:02:33Speaker 02

  Until, well, until now, they just raised a ton of money, right? So maybe.

• 1:02:37Speaker 01

  Yeah.

• 1:02:37Speaker 00

  Let's see.

• 1:02:38Speaker 01

  They also raised a ton of money a year ago.

• 1:02:40Speaker 00

  You're gonna be Europe champions.

• 1:02:41Speaker 01

  I think we need way more model companies out of the, out of Europe.

• 1:02:43Speaker 00

  Yes.

• 1:02:44Speaker 02

  I just wanted to ask you, like, what predictions do you have maybe like over the next year for like the law industry?

• 1:02:50Speaker 01

  We asked a little bit of that earlier.

• 1:02:53Speaker 02

  Yeah.

• 1:02:53Speaker 01

  I'll modify it to your second question, which is, in two years, will lawyers do their work inside Legora? Will they use other tools like Claude or Tragency and call Legora? Like, you know, the API.

• 1:03:04Speaker 00

  Yeah, yeah, yeah, yeah. I think both. It really depends. I think if you're a big enterprise, you might have Claude co-work and then you'll, it's, I think it's similar to like how I use Linear through Claude, but I still go to Linear. I think enterprise will do that. I think law firms will just use Legora.

• 1:03:17Speaker 01

  Yeah.

• 1:03:18Speaker 00

  Because that's simpler and better.

• 1:03:20Speaker 02

  Yeah. It kind of reminds me of like open evidence for like medicine. Like you're basically that for law.

• 1:03:25Speaker 00

  Yeah.

• 1:03:25Speaker 02

  Yeah.

• 1:03:26Speaker 00

  Exactly.

• 1:03:26Speaker 01

  Encoding has gotten to a point where people, the labs will cut you off for competing with them. And this has happened twice.

• 1:03:32Speaker 00

  Yeah.

• 1:03:32Speaker 01

  Do you think that will happen to law?

• 1:03:34Speaker 00

  No, I don't think so. I think.

• 1:03:35Speaker 01

  Because like, you know, they are releasing legal services.

• 1:03:38Speaker 00

  Yeah, yeah, yeah, yeah, they are.

• 1:03:39Speaker 01

  I don't, I mean, we obviously talk to them a lot, but it's also, it's like, hey, are you gonna?

• 1:03:44Speaker 00

  Your sales reps will say no.

• 1:03:46Speaker 01

  Exactly.

• 1:03:46Speaker 00

  They don't make the call.

• 1:03:47Speaker 01

  Exactly. That's not their commitment, right?

• 1:03:49Speaker 00

  And they don't even know like often what's actually going on. I don't, I don't think that's the case. They have so much stuff to capture and knowledge work or in sort of enterprises, knowledge work generally, that like legal has to be part of that, just like data analytics has to and sales and marketing and finance. So like, they have to do things that are good there, but they're never gonna go as deep as we are. And I think if Claude takes a small client, small, you know, corporate clients and they do some of their legal via Claude, like that's, that's great, that's fine. But if you're doing a, you know, $400 million M and A transaction, you're gonna want Legora.

• 1:04:22Speaker 02

  I had kind of an unrelated question, but I'm curious, are you guys going to law schools and kind of like getting them to like teach Legora? Like in classes? Like, how does that work?

• 1:04:33Speaker 00

  Yeah, it's a, it's definitely a program that we are, I think we've started. I actually don't know exactly where we're at, but we do want people in law school to learn to use Legora.

• 1:04:42Speaker 02

  Like, are you seeing that like law schools are changing their curriculums a lot or not really?

• 1:04:46Speaker 00

  I don't know. I, I, I wouldn't know, actually.

• 1:04:49Speaker 02

  Interesting.

• 1:04:50Speaker 01

  I would actually do it a different way. You should do scholarships for law school for CS majors, for engineers. We will cover.

• 1:04:57Speaker 00

  After you've done CS?

• 1:04:58Speaker 01

  Yes.

• 1:04:59Speaker 00

  We'll put you in law school.

• 1:05:00Speaker 01

  CS plus some software experience.

• 1:05:02Speaker 00

  Yeah.

• 1:05:02Speaker 01

  We'll put you in law school.

• 1:05:03Speaker 00

  Yeah.

• 1:05:03Speaker 01

  We'll cover it.

• 1:05:04Speaker 02

  Or you do like the MA, like masters plus JD programs?

• 1:05:09Speaker 01

  Yeah, they don't care about the masters.

• 1:05:11Speaker 02

  Well, meaning like, cuz there's a lot of people who didn't do CS undergrad, so then they do like masters just to kind of like get that.

• 1:05:18Speaker 01

  Yeah, yeah. I, I don't know. I don't see that as often. Yeah.

• 1:05:22Speaker 00

  Yeah.

• 1:05:22Speaker 01

  People do JD MBA, that's a thing.

• 1:05:24Speaker 02

  Yeah.

• 1:05:25Speaker 01

  But JD CS, I haven't seen it. Yeah.

• 1:05:27Speaker 00

  Happens, yeah.

• 1:05:28Speaker 01

  Yeah. Yeah, okay, look, overall, you know, super impressive progress. I mean, congrats on all your success. Like, are you still gonna keep up the pace? Like.

• 1:05:37Speaker 00

  Absolutely.

• 1:05:37Speaker 01

  Yeah, you know, and I think you're hiring in SF, New York.

• 1:05:41Speaker 00

  We're hiring in, yeah, engineering, we're hiring in New York, Stockholm and London.

• 1:05:46Speaker 01

  Yeah.

• 1:05:47Speaker 00

  And all other roles we're hiring everywhere.

• 1:05:50Speaker 02

  How many people do you have in New York right now?

• 1:05:52Speaker 00

  A hundred.

• 1:05:53Speaker 02

  Okay, and you guys are planning on how many in New York?

• 1:05:56Speaker 00

  In New York?

• 1:05:56Speaker 02

  Yeah.

• 1:05:57Speaker 00

  For, just like generally?

• 1:05:58Speaker 02

  Let's just say, yeah, generally and generally.

• 1:06:00Speaker 00

  A lot.

• 1:06:01Speaker 02

  As many as you can.

• 1:06:02Speaker 00

  Yeah, it's, it's aggressive.

• 1:06:05Speaker 01

  Yeah, I mean, that's the whole of corporate law, right? As far as like.

• 1:06:08Speaker 00

  It is, yeah.

• 1:06:09Speaker 01

  America is concerned, so like, yeah, I mean, I'm looking forward to you buying a law firm and like, you know, becoming. Yeah, it's, it's super exciting to, I think like, you know, every industry, especially like the top, like doctors, lawyers, coders, you know, they all have to have like, you know, two or three agent labs that like just dominate the space.

• 1:06:28Speaker 00

  I agree.

• 1:06:29Speaker 01

  So you guys have like a great market, yeah.

• 1:06:30Speaker 00

  Yeah, I think so. And I think it's only gonna get much bigger as like law changes and again, becomes more available to more people.

• 1:06:37Speaker 01

  Yeah. Also, I think like, I mean, we're already like super over, but like, the problems that you work on are very, like, the frontier of knowledge work.

• 1:06:46Speaker 00

  Yes.

• 1:06:46Speaker 01

  Yeah, they're, okay, like, unless you're literally like doing like.

• 1:06:49Speaker 00

  Never stop.

• 1:06:50Speaker 01

  Science, never stops in science. Other than that, like, most work is like, basically converges to legal.

• 1:06:57Speaker 00

  Yeah.

• 1:06:57Speaker 01

  Like.

• 1:07:00Speaker 00

  Yeah.

• 1:07:00Speaker 01

  Uh, yeah.

• 1:07:01Speaker 00

  It's all legal in the end.

• 1:07:02Speaker 01

  Yeah, hiring, finance, everything, like, I just have to consult my lawyer, so.

• 1:07:05Speaker 00

  Yeah, I know, I know. Which is why I think it's a really exciting thing to work on cuz like, modern society runs in some way on legal.

• 1:07:11Speaker 01

  Yeah, yeah.

• 1:07:12Speaker 00

  Cool.

• 1:07:13Speaker 01

  All right, that's it. Thank you.

• 1:07:14Speaker 00

  Thank you.

• 1:07:14Speaker 01

  Thanks.