Building Legal Agents When You Can't See the Data - Jacob Lauritzen, CTO of Legora
Latent Space: The AI Engineer Podcast · 2 Nov 2026
Source: https://lspace.beehiiv.com/podcast/s/latent_space_the_ai_engineer_podcast/building_legal_agents_when_you_can_t_see_the_data_-_jacob_lauritzen_cto_of_legora
Transcript: https://podcasts.opennash.com/shows/latent-space/building-legal-agents-when-you-cant-see-the-data-jacob-lauritzen-cto-of-legora-6cb707/ (via OpenNash Podcasts, machine-generated)

People were asking us about mythos and everything, even though I think realistically, a lot of legal work does not require mythos level intelligence. Paralegal's gone, Yep,

Junior lawyer's gone, I don't need them.

um, that's actually not what we're seeing. And we had one problem where, like, it wouldn't cite properly, and so it would be like, next model release solved. It went from like, 7% to like ninety nine. It's just like we did nothing and like, great. But if you're doing a, you know, 400 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 be everyone's much bigger.

Uh, and we're a 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 versus all the other stuff?

Okay, we're here in the studio with special guest, uh, Jacob Lauritzen, the CTO of Legora. Did I get it right? Lordsen? Lordsen?

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

does it have a special history?

It just no. Any Sen is like son, son of

son of Lawrence?

so just like you have son, and yeah, so son of Lawrence, that's my name. Nice,

Uh, we've crossed paths here and there. You, you, you spoke at, uh, AI, a few times. And obviously, Legora is one of the fastest growing legal tech in history. And, uh, y- you said something at the start in a pre-show that I thought was really interesting. You said that your origin is very European, uh, even though obviously you're expanding in New York and SF. What feels different about your culture?

I think we are just at the core, probably very, uh, 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, you know, outcompete this huge behemoth that was, like, way ahead of us in the US. So I think we've always been underdogs, and so we've always been very humble. Um, we've always sort of had to fight for our, uh, existence.

Um, I think something we've had to learn as we've also become more and more. Um, as we've entered the US and been in the US a lot more, is to be a little bit more, uh uh, bold and like t s tell the world how great we are. Cause it's it doesn't come naturally to, I think, some of us.

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

I think that would be really interesting.

yeah, absolutely. The way everything started was ChatGPT with, uh, Swedish laws 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, um, lawyers spend a lot of time figuring out what are previous cases that look like this. What's the legal precedent like? Is this, you know, what have previous people done in these situations? That's extremely important.

Um, and so that has always been part of our product. Basically, we started from like an an agent you could ask questions, and it would query laws. That was the very simple beginning. Um, and then from that it's expanded, and so it's expanded in like, what can the agent do? It it will now, you know, draft a lot of stuff really well, it will edit word files, it will, you know, move your files away, organize everything, um, run really complex analyses, um.

And we've added just a bunch more features to it. So one of our features is called tabular view, which is, um, now a name that's being used in the industry. And we're very happy to see Claude for legal using our terminology for ooh, 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, um, agreements, which you do in due diligence or 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, um, helping orchestrate the work a lot more than we were just even a year ago. So we have different sort of we have a a thing called lists, which is sort sort of like linear for us, and um, we have intake, which is a way to collaborate with, um, clients.

And we have um, 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 we're spending a lot of time there. Cause, um, there's just frankly, the way that you work with a lawyer ten years ago, or maybe even today, is 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 it's doing the work, and it's also like orchestrating the work.

When did you guys start doing or building the agent?

So, I mean, we've all we basically had this switch from the assistant to the agent, if we recall it, right. Um, I guess that the agent, I don't know, I wanna say a year ago, probably,

Yeah, so this is a um, from rough timeline for people who are understanding. YC 2023, uh, and then you were, you were a YC founder YC as well. YC 24.

Yeah, I was in YC 23, Legora was 24.

okay, and then, uh, so so there is. This is like a little bit pre pre, like agents really taking off. And then, like, reasoning models, obviously change everything. I mean, you know, in one, in one sense today, uh, you know, we had a preview of the products, uh, it does look well preview. We had a private, uh, thing, but we will put up private a video on the on team. the YouTube. It's mostly like ChatGPT for lawyers, right?

Like a very like, very fair to say that. But then, like, uh, the sidebar has a lot of nice custom tools, like the tabular view, uh, like the in intake, which I really liked, uh, and, uh, you know, a bunch of other things.

exactly. yeah, that's, that's exactly what it is. It's it's cowork or chatGPT, just like, really, really good for legal work.

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

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

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

okay. And then that's not available to the lawyer to see you guys for pick

the agent. yourselves. Yeah, well, we've been back and forth on this. Yeah, it's 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, we try. I think we found it most effective to subdivide the problem and and and route on, like as we subdivide the task. But we do right now have a a picker in the agent.

I'm not sure if that's gonna stay there always, to be honest. Um, so, yeah,

yeah, I mean, so I bring a little bit of context to this because I'm advisor for cognition. Uh, and when I joined, you know, part of my my thesis for what an agent lab is, an agent lab is, you know, uh, ideally a domain specific GPT wrapper, right? Like, we, we, we run the uh, we are the domain experts. We'll pay attention to you, we'll serve your needs way, way more than the frontier labs, and we'll give you the best of the frontier yeah, we left labs.

According straight away all to our judgment, the yeah, say, our job is to decide for you because your not your job is not to decide exactly. We'll for us.

always keep you on the Pareto frontier and make sure that it just it's great all the time, and you don't have to dive into all the details. Cause, 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, uh, draft this contract based on this precedent, do you think that's a Sonnet high or an Opus mid task? Like, you know, they they won't know.

just give me the I barely know what smartest model, it's like. It's just like, make sure it works

right? Our hourly rate is $1,000 an hour, exactly. Just like right? Like, what?

make it work.

Um, 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 and Astra. And, uh, people wanna experiment with the fancy new model. Uh, do you is that's the that the same

I I think so, I think it's prob- it's. It's definitely way less in legal than it is in, um, coding? engineering. Yeah, But there are definitely people that just want table one right away. And, you know, people were asking us about mythos and everything. Um, even though I think realistically, a lot of legal work does not require mythos level intelligence. There's

so ex- so exactly right. Like, I think, basically, y- you're like, Okay, we'll give you the option you you ask for this, but you're gonna run down your credits, like 10x faster than

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

So you think the models are already, like, as good as lawyers need, like, there's no need for them to get better.

It's, uh, I think it's a power distribution. So, like, there's probably like 60 of the work we can do really, uh, 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 the thing where, especially for like, very complex analysis, we s 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 will further so probably expands with intelligence.

I imagine,

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 46 or something.

that would have been, yeah, Sonnet 46, Opus 46 is probably right.

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

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. Um, 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 of legal and different tasks across all of those. So we basically have like a big cheat map, 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 and regress in others, and that actually happens a lot more than you'd think.

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

so like, there's, um, there's different, just like framing stuff. So we have different, basically like worlds, or like our environments, essentially, which is like, here's a cause, cause. Lawyers work in projects, always, more or less. So it's like, here's 10,000 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, uh, stuff, and like we want it to be concise, etcetera, etcetera.

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 which you can s kind of like, subdivide it a little bit. And that, and that's how we run the evals.

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

So, yes, it's a mix. We have, uh, 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, um, 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, uh, the industry.

are they IT in big law, or No, they are they they're are lawyers, lawyers in big law

they are lawyers in big law.

with CS degrees? Oh my but Mostly really it's a Venn

hard problems.

diagram. That's, yeah, exactly, that's like the hottest person to hire for. But they're also such a force multiplier, cause we can pull on them for the eval stuff and for the product development. Which is like, you have a pool of 100 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 just like, help us shape the product, and it's such a such an advantage.

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

Evals, um, grew out of the assistant agent team at some point. I think there was a point up until recently where it was like, honestly, just not really worth it. Cause, like, all models just got better. So it was like, do we wanna spend a lot of our time doing really complex evals, or do we just like, wanna build? Cause 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.

But

yeah, like every two, three months, you it just get a new frontier like, solved. I'm, yeah, model, just exactly, I mean, we pass it through, right?

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, 7% to like ninety nine. It's just like we did nothing and like, great, yeah,

maybe the the the real work is, uh, you know, keeping all the data private, making it taggable, sortable, add adding new features like the the tabular view. Maybe is that there, you know, may you mean, over like, well,

and above ChatGPT?

I mean, like, 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. Uh, so, yeah, I I don't know what I'm saying here, apart from like, you know, what is the job? The job is, uh, maybe not. Uh, in the early days, it was not so much to do do evals, because it was mostly exposed model capability to lawyers.

yeah. The huge part of it is just, um, 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, like, we can kinda 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 200 thread email with like, V5 word files back and forth, like, what does that look like?

And that's like, not even necessarily purely AI. That's just like, but like, much better product experience 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 AI part, which is like, make the work faster and better, and and proactive agents that react to stuff when it comes in. So you don't have to, you know, uh, 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, um, 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, I guess.

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

I should preface this by saying, I don't know. I mean, who knows, really? But um, I think we can look to coding a lot. I think, um, all lawyers are gonna be way more, uh, productive than they were before. They're gonna be able to do a lot more stuff at a higher quality, uh, for, uh, 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.

Uh, 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. Trawling through big documents to, like, find the smoking gun, or like, do all this menial, super annoying work that a lot of lawyers have been doing.

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

I gave this, I actually gave this a lot of thought, just like last week, cause 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 manufacturer, whatever. You ha- 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, uh, consultancies and 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. And so partnerships, essentially, is a structure where you make the human capital the owners of the company so that they stay.

Will that change? Like, I don't, it doesn't have to, but I think what we really wanna do with Legor is we actually want lawyers to be able, and law firms to be able to build some sort of intangible capital, some durable capital. In 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 X 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 out output. And that can be their IP. So it's like a way to codify the human expertise and judgment into a system that I think is now. I'm just rambling completely, but like, um, that's something that we want to help empower. And does that change the partnership model then?

Cause 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. Cause, like, you get rewarded from, you know, eat what you kill, or make this large step, whatever. Um, that needs to change a little bit. We need to figure out an incentive structure where partnerships, uh, partners are incentivized to codify things for to build an asset for the company.

But right now they aren't, cause as soon as they leave the partnership, they don't, um, get any dividends from the assets that they built. So there's like, a, yeah, I think the the the whole business model is is, uh, we'll, we'll see.

yeah, yeah, it's all it's all in question right now.

My 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?

yeah, what happened there? Paralegal's gone, yeah,

right? Like, junior lawyer's gone, I don't need them. Like, it's

um, that's actually not what we're seeing. So yeah, there's a I think it's, I don't know, would you, would you say that we're seeing that in engineering? Uh, yeah, so, Yeah,

uh, junior engineers are really just kind of called cooks, right? Like, you kind of have to come out of, uh, drop out of university, fully baked, or else you're

yeah, yeah, you're not gonna make it.

um, I feel like I'm not. I'm being a bit dramatic for for, uh, comedic purpose, but like, uh, 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.

yeah, yeah, yeah, it is. It's interesting what happens to the partnership model, like the pyramid. I think generally a lot of lawyers, um, 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, cause they can produce so much more stuff. Like if they're good, and I think it's the same thing in legal where, like, 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.

Yeah, it's, it's always been And the case, right? Yeah, is it like, even more but it's like, so?

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

I'm actually curious about that. So, like, the whole, like law business is basically like, um, charging per hour. So, you know, if each project now can

it's faster.

be done a lot faster, is it going to be, like, way cheaper? Like, this was cause, yeah,

actually so, um, fun story. I was I was reading Max's YC application, uh, and like, helping him getting into YC, get Leia, as it was called back then, into YC. And this was my one thing. I was like, and dude,

and curious, Leia is a Danish thing for something no, Swedish, um, Swedish.

no. Also, it means nothing. There's this, there's this really funny story in, Um, 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, and we're like, why Yoda?

why Yoda?

Yeah, I don't know. So I was like, why, why is See, this?

hallucinations are not just from LLMs.

No, I think journalists hallucinate. Um, but no, it, it doesn't mean anything. uh, so Um, he wrote the application, he, he wrote, Yeah. And my feedback to him was, um, you know, people have tried this a million times. Legal tech has never been a thing. Cause, 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, cause the competitive pressure is so high. The billing model itself, I think, is also gonna change. We've we're already seeing that, particularly in the US. That a bunch of stuff is actually being priced on like a project fee and not on an hours fee. Um, particularly there's 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

So where is the money being made then? Is it cause? and the strategic Uh, I, work. yeah, I feel like a l- lot of what you guys talk about is M and A specifically, like, that's where all the money It's just is made.

a a very easy example. Yeah, yeah, like, litigations 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's also super important.

like a CRM.

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 that relationship with the client. Uh, and so now they can do that, but they don't have to lose a lot of money on wait, doing it.

I I thought I thought I just I have to pay s the lawyer money just to be my friend. Like, in this, like, isn't that the retainer thing? yeah, the that's, that's You, you tell you

the stuff.

tell me I can do it for free, like,

Yeah, yeah, you just have to find the right oh, gotcha, lawyers. Yeah, that's right. Or latency based has to grow much bigger. I don't know.

Yeah, yeah, we're trying, we're trying. Uh, you know, yeah, so okay, so so, uh, uh, so you're saying, um, you know, obviously the 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, uh, they're, they're just shifting. And and this is something that, uh, we also did with, uh, worry about with cognition. Like, uh, people worry about the phrasing of like, we will replace your junior engineer, cause nobody likes that kind of statement.

But i, uh, in actual fact, yes, like some, some part of it, uh, does happen. The junior engineers embrace it and they become more productive,

for sure.

exactly like you just said. So I guess, like, I is, is there a new term for this role or this, this job that is taking, that is having traction with your customers?

you mean, the the super AI pilled junior legal? Nothing I've found yet. Maybe we should coin one isn't it legal, legal legal engineer,

issue?

that's our and and also now an industry thing. CSJD's Exactly, yeah yeah. And maybe that's the they're those other people that are, uh, best positioned to do this kind of stuff.

I think the the the derogatory term meat proxy, where you just like, sit in front of the machine and type in something that, uh, 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, is you know agents very well, and you, you know Legora very well, and you know how to like, like, th- 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.

But I I guess then you're not really a proxy, right? You're actually just doing meaningful work, Yeah, it's as opposed to

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

we do up to a million cells, I think,

in a in a single thing. and then, yeah, That's impressive. Uh, we should talk about the the table and the windowing. Yeah, these, you know, like, I've, like, I'm working on a big case. I have a million documents. I type it in. Usually, I'll throw a par, throw, like a team of paralegals yes. And locked in a they'll sit there until room. like, four am. Yeah, Uh, like that, that doesn't need to happen, right?

Cause now you can extract it and you can go and re-prompt everything. So like, yeah, and 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, whatever that is.

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? No,

I have a question. So you guys bought a company, Kira, I is that how you say it? And you, you guys used your own product to do the M and A.

yes, we do that all the time. So how did that Yeah,

work? Like, can you talk a little bit ooh, dogfooding, about that? Yeah,

yeah, no, that works great. We're doing that a lot. Our legal team is is, I mean, in-take has been built with our legal team. Cause right now we have a Slack workflow where everyone throws their stuff in there. Like, this is annoying, right? And it efficient. So it's like, great, we should use Legor for that.

yeah, yeah, uh, can you talk a little bit about that? Like, you know, what that process looked like?

Yeah, absolutely, so it's it's, um, we, uh, do a lot of the due diligence ourselves because we can do it, uh, with tabular view and other tools. We do still have counsel coming in, um, to, like, assess certain risk. Or like, you know, there's payroll and so. The cure was simple, cause that 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 lawyers for the strategic part, where they could 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, uh, yeah, a lot of the early things we would find, and we have had cases where we found something, uh, that's been like a red flag, and then we've, we've pulled the brakes.

can you talk a little bit about any of the other

I don't think so.

use cases? 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?

Well, we're also go smaller law firms also. No, we st. We definitely started really, really big law firms, but 50 lawyers also will use us and and get a lot of value.

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?

yeah, yeah. I think the European ones, um, have been a bit slower to move, the American ones are very forward. Um, move really quickly. I think, uh, it's also very high on the agenda of the American companies, more so than the, uh, 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 wanna build this like huge thing with you guys and like, structure it in whatever way. Where What's at European, it's a lot more like, we'll just take the off the shelf and what's an and figure it out.

example of something they would wanna build themselves?

Integrations into their own, like some of these customers, build their own CRM and their own, uh, document management system and their own all sorts of stuff. And they wanna build that, and then they wanna build triggers that, like, you do a review in in in Salesforce and it 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 wanna build with us.

And I, you know, we can't really do that, um, but but that's definitely a thing where, like, American companies really want, um, to build their own, more than European ones do.

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

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

okay. So they don't see like an existential threat here in their business, I mean, there's, whereas the American ones do. Or

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

m'kay. Another question, I think maybe y- you wanna 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.

so we have the regular product metrics that we care a lot about. Are people spending a lot of time in our product? Uh, 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, uh, software of like our DAO of our amount and our like, uh, you know, hour spent 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, did we solve the problem here?

Just wai- with a super cheap LLM that suggests 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, cause it's all super confidential.

And that's like, extremely frustrating to work with, cause 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 I would have with it.

assumed you guys, like, signed some so sort of agreement with the law firm, and they're like, oh, yeah, I wish, sure,

yeah, I wish. No. But the thing is like, a lot of the data that they have is not even even theirs, right? It's their clients, 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. Um, so that's just like a super annoying kink of the business.

can you do paraphrase? So, for example, ChatGPT has like a slash feedback thing, uh, that directly fully says the full trajectory. But obviously that that is not possible for you guys, uh, 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, yeah,

we can't re. There's, I mean, there's always 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. And so, like, we are, um, generally pick the the most safe way. So, like we, we restrict ourselves as most possible, cause we, you know, there yeah, that's should be no

fair enough.

risk at at all. Um, but there are things where it's like, okay, we know that the failure modes are probably these ten or twenty, so we can, uh, classify it into one of those, and that's a helpful signal. Uh, we can classify it into the TAT 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.

also, like, on the privacy front, I guess, um, 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 Gemini? It must be like a huge this thing.

all of our infrastructure's on Azure, um, primarily for this reason. Cause, like, when we started, law firms were like AWS, no, like, no way, we law don't trust it firms don't trust all. Yeah,

AWS. Why?

yeah, it's different now. No, but it there was like Amazon, Google, we can't trust them with any of our data. So we basically we had to host everything on Microsoft, cause they already have three sixty five.

oh, so they're okay with Microsoft, but not, cause they've already oh 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. Um, there's 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. Um, so that's changed a yeah, but lot. But it was really and by the way, painful.

it's only been three years, so like, it's actually like, Yeah, it's a very chilled.

yeah, yeah, it's a huge shift. It's, it's, it's, it's great.

I mean, good for you guys, but yeah, I mean, I don't expect the the like, you know, the legal firm, ha- legal industry has somehow ignored this for the last, like ten years. Like, yeah,

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

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

yeah, the we're just thinking about, uh, to to your point, um, just bring our clients along on, like the Pareto frontier. And like the of the the map of all the models and what they're good at, and their latency and their cost, and their, uh, governance and and and their, um, regional availability. How do we just optimize across all of that? So some open weight models are great for certain tasks, and then we'll use them there.

Um, some we'll post train, and and some we'll just use the frontier models.

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

yeah, I think not overall good. Gemini, one of the early Geminis, is, uh, yeah, extremely good for certain types of, um, uh, transcription and speaker attribution. So we use that for transl- um, transcription oh, so you have actually. a, uh,

yeah, why are you guys transcribing? 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 an an, um, any more, any other app that has this. And we do actually also transcribe files. If you upload hearings or whatever, we'll we'll then like, transcribe them, put them into text, and so we can do all of our analysis on it. no, eleven labs, No eleven, lab for GPA reasons.

Same thing. It's like a data processing agreement, I should say, so, like our data processing agreement has very few vendors on it, yeah, you cause it's just need to really difficult keep it to exactly. We need to keep it super tight. tight, uh, on where any data goes. And so, um,

I think no that that is one of the benefits of like, a Gemini and OpenAI, where they're like, you, you come to us. We have most of the things that you need. And that is actually va- very valuable, even if it's like, it doesn't have to be like state of the art, it's just like mostly good enough for all tasks. Then who cares, like,

yeah, no, absolutely. I should actually shout out also Microsoft's transcription model. They made one recently. my, my transcribe? Okay, it's great, it's better than the old Gemini. Uh, in a lot of yeah, yeah, they, some respects.

they, 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 the arena scores, and that's good enough. yeah, exactly. And it's Yeah,

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

yeah, I was gonna say, like, at this point, are pretty much the, uh, speech to text models like good enough to where you're like, uh, one word here or there, if it's off, it's off. for sure. Like, I've done this a and a lot,

lot, really.

and particularly in legal, there's like, some we we had this thing where I think it's I, I forget if it's like in Australia, where there's like a certain name for like a p, a person in court. And it would consistently transcribe it as condom. And so, yeah, so there, yeah, there's, there's certain things that you don't want there.

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

Yeah,

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

yeah, y- like, I think, um, Whisper and Eleven Labs still transcribe, uh, Claude Code as cloud clo- code, and like, it's

yeah, I've, I've actually had very, very, that a little

very common. Uh, so so, like, that's, that's how, you know, there's like a lot more to improve. I do want to cover a little bit on the the agent product side, uh, so we've covered a few, like the of the top level stuff, right? We've already named job tabular review, uh, we named jobs intake. And you've, you've got some other, uh, stuff that we haven't even, uh, touched on yet. But I just wanna cover the the big two, let's call it like, is it, is that is, is that fair to say, that they're the big two approximately?

Agent and tabular review, Yeah, uh, and our and projects, yeah,

probably yeah, and our word add-in, um, is also something, cause that's p. A lot of people work work inside of Word, and so our word add-in is is a huge and an Outlook add-in. Also.

yeah. So I just wanna cover, like the the big ones that everyone must know. Uh, so Table review is basically like fan out of like, uh, a lot. Across each document, you can ask the same question across all documents, drag it in on the table, uh, and then work back and forth and they did, between a million is impressive. Uh, what's any other like engineering considerations or performance things, or like, what? What's hard about this?

wait, like, before we do that, can you just like, walk through? Like, what is the user experience for a lawyer? And then, like, okay, so you wanna, actually using

you wanna think of top

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

um, 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 supply contracts, all of whatever, and so employment contracts. You put 10,000 employment contracts in there, and then you, um, like, each ha-

cell is one employment contract,

each row is one employment contract. And then for cells, you ask questions, basically, so like the first question, the first, uh, no, sorry, per column. So the first column might be, what's the termination, uh, 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, uh, is there an IP assignment clause? or whatever? Next one is like, uh, 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 view 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. And then the agent from that can draft a memo to send to the client. Or, uh, it can just do the review and then have, you know, a lawyer, the use, or just be like, Okay, let's let's look at this. Here are the red flags. There's also collaborative, so like, you can comment on it, um, for other people to look at, et cetera.

and why Yeah,

do you choose that, like, uh, spreadsheet format?

yeah, it's just a lot better to. It's it's super easy to work with, work in, uh, it's really easy to get an overview super quickly of what's going on, uh, 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 wanna 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. yeah, I would Hm,

say that the spreadsheet form factor has s ha- has a lot of pull in some areas, but somehow hasn't really spread. I, uh, it fi- I find it very weird. Like, Clay is another one on the GTM side that, uh, you know, very known for the spreadsheets. You guys, uh, I don't really know if anyone else does, uh, a large spreadsheet AI thing. The there was like, V7 that like, tried to launch the like, there's like sheets, there's, uh, even in finance domain, I don't really have like a a top name that, like, does spreadsheets.

So it's just really, yeah, no, I I agree. I think it's like a great. If you've, if you have fan out and you do the exact same thing and you're you're extracting stuff, it's it's such a great form factor to, like, understand what's going on.

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

People are happy to live there. Um,

Uh, do you use AG Grid or your we do use AG own AG Grid? grid. Yeah, That seems to be like the leading one. I mean, they've done this for, like, I don't know, 15 years.

yeah, yeah, they know how to. Yeah, Uh, yeah, so so work with us.

okay, yeah, I mean, I'm I'm happy on this that spreadsheet angle. Um, I mean, I think the the only other interesting thing for me, engineering wise, is the fan-outs. Engineers maybe can a are well equipped to understand the trade-offs of like, well, okay, before you use fan, it's sticking out on a million documents, maybe test it on like two, uh, and

yeah, yeah, yeah. Does that work before you're gonna do launch? Yeah,

do they do that?

yeah, they will. So our tab of the view actually will run the first ten rows

Yeah, just check, right?

always. Yeah, does this make sense? Did it, did it show us what we thought it was gonna show us? That's a that's really good, oh, but also for people when people build this, it's just really good for them to iterate quickly on the first ten rows. Until, like, they have a, uh, they're getting the results that they want, and then they can go ham.

yeah, I am happy to move on to the next thing. Intake, uh, which is your Slack bot, um, everyone has a Slack bot. Uh, what's

of course.

different about yours?

So ours is just legal specific, uh, 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, uh, kick off an agent that then adds a task to our list. So we have this lists thing, which is like linear for sh- for, you know, that's the closest, uh, equivalent. And so it will add it to a specific intake list.

And then lawyers and agents can go into Lagori and just be like, Okay, these are the things that, you know, people are sending to us as our law firm or as our, um, 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, um, I don't know.

Storefront thing where it's like, here, here's the ticket. I want this thing reviewed. Okay, now it's now, it's here, it is, it's back. No one needs to change anything. And the legal team just sits in Legora and, like, manages the agents and everything there.

I think the the data structure for this kind of thing is really interesting. Cause 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. Uh, and like, I, I don't know. Is it hard to integrate all these with all the other features, or do you just not worry about it?

it's a no, it's not. I think we have some primitives that work really well, so, like, lists is a great primitive, cause it's essentially it's like extremely flexible. It's Like a also like a notion to-do list? Yeah, database, a Notion database, 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 it 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 populates a field or whatever, asks 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.

yeah. Do people get excited or overwhelmed by that? You know, like, I I feel like, uh, this is basically end user programming. Uh, your, you know, you can let people set up crazy automations. Some people get super obsessed by it, and they become like, influen- like, you know, it'd be cool to have, like, a world where influencers

play has influencers. Yeah, yeah,

um, is that worth it? Too overcomplicated?

we need the the flexibility, even if we don't actually expose it through the end user. Let's say this was just all internal, then it's a really fast way for us to utilize people like 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 lists with, like, your own, a generative UI. And then you basically have a new product that some people are gonna love.

And we can have a markets ba- place of just like a bunch of s 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, oh, 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 wanna expose it, that's also how we build our own custom features. We we made another acquisition in the UK called Wexler, and they're doing fact intelligence, which is for litigation mostly.

Which is like you upload a million documents, uh, 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 it? Disagreement, they, uh, you know. And that's extremely powerful, cause 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. 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, cause 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.

okay, so you have, uh, what? What core primitives do you have? Let's just restate for for people

S lists is a core one. lists, projects, Yeah, super configurable one, yeah, projects, is basically containers of files, file systems. Um, the agent, of course, you can kick that off and run that in very different configurations.

do you have a name for the agent, by the way? No, we don't. No, just okay, just Okay, intake. okay,

yeah, no, you mean, like, we called it, like, uh, Leia, or it's like, we gave it a name. No, Ooh, yeah, Leia, yeah, yeah, Leia would be cool. Yeah, um, people used to talk about Leia as like an a named entity, um, but yeah, we s we stopped that. We we might well bring it back,

it might be confusing. yeah. So I don't know. list agent probably, uh, tabular review,

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,

Yeah. So I actually wanted to talk a little bit about, like, FTEs, cause this sounds kinda like that. And I think Max has talked about that a little bit. That like, okay, when you onboard a new, like, big customer, you wanna get them value, like asap, so that you know they stay on, stay on Legora. Yeah, how has that evolved? Like, when did you guys start that forward deployed team?

So we hired our first forward deployed engineer, that was our first hire in New York, also YC, uh, founder, nine months ago. Maybe I'm not actually sure. Um, Are they considered it's hard to think about.

legal engineers or no? Okay, okay,

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 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 will still have forward deployed engineers. Like, help out, do you know, do all the custom integrations and the 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. Is like almost a first line, second line of defense, where 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 deployed 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.

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 gonna go build, you know, some kind of product for you, like, they, how does that work?

uh, 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, want, they have all these dreams 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 s. We'll basically staff them with legal engineers and a forward deployed engineer, potentially depending on what, you know, the 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 Legora. And some of that will just be a legal engineer, and some of that will require a forward deployed engineer.

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

Legal engineers configure the product as a power user would. They don't write code, and a forward deployed engineer writes code into production. Basically, I guess that's the that's the

What kind of background do the forward deployed engineers normally have? regular You said, YC founder

engineers, yeah, founders, regular engineers, you're old. like, yeah, D Yeah, was your yeah, exactly, was the guy D was our first. Yeah,

two YC companies? And worked on search at Meta?

yeah, she's awesome. Yeah, yeah,

Okay, that's a high bar. she's great. Yeah, yeah, Yeah,

yeah, yeah, she's, yeah. First, first boost on the ground in the US. Yeah, sorry,

So what are some examples of, of, I don't know, workflows or things that these people are building for the clients? Or do you guys have like, oh, these all sorts are like,

of things.

you know, there's a couple use cases that, like, all the law firms are like, you know, this is the first thing that our FDs are gonna do when they when they go in. It's very different. Um, Okay,

some core workflows everyone have, and we can just build in Legora. And that could be anything from like, um, this is how we handle these types of NDAs or whatever. And then it's just like, and you activate it, and it's more like skill building, really, for at least, and most of the FDS. 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.

and how does the like legal structure work there? Because you said you guys yourselves can't even work on deals. Um, so, like, how, how do they work on client projects?

you mean, the law firms, how do they work on client projects, Sorry, or how are they h- how do your working? FDs work Yeah,

on client projects? If they're so they don't touch not

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. Um, like to the if they need to,

law firm?

yeah, yeah, if they need to. That doesn't happen very often, cause like, usually they'll just build an integration and like, kinda works, but they, yeah, they can if they need to.

And you only onboard FDs into a customer, I'm assuming if they're a certain size, okay,

it needs to make sense, cause we our FDs can also work on core product, right? So it's like it's c- a constant prioritization thing.

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 on site, one day you come back and, uh, contribute back to products, anything like that. no, we, Uh, that that

we don't.

makes sense.

Uh, I I mean, to be fully honest with you guys, it's still, it's still, uh, you know, like, still early days in a lot of this. I mean, where

do you see it headed, maybe over the next year?

I do think that it's gonna be more, maybe not exactly like Palantir, but like we, I think we will have a larger in constant circulation group of FDs. 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, I do imagine us rolling in with legal engineers and forward deployed engineers to, like, work on specific projects.

yeah, the API business is actually, uh, interesting. Like, like you said, um, because, uh, uh, you know, that's another role that you can have, where you are CTO maintainer of the Legora platform, right? Like, we will offer everything that we have in the Legora web app as an API, and then you guys can use whatever is. Is that is that a a promise that you make? Or,

that's not something we're promising now. Um, we do have APIs that you can build against, but not the entire surface of the product.

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 the existing tool I have, right? And then I just, like, Uh, install Legora, if, for example, with the the Word document stuff, other than that, you know, I, I do think, like, then you have to maintain it.

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've fought it for a very long time, mostly because, yeah, I just don't wanna. Uh, we. We move so quickly in in the product that I don't wanna be like slowed down by having to maintain old 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 were 20 engineers, it's just like we, we move so quickly that we can't do this.

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 tight to the product. Uh, you know, like a a very simple one is web app, mobile app, right? or like, web app, mobile app, uh, MCP, and and then, like, you know, whatever, like o- other other integrations, uh, then your FDs just are one more client to the overall platform anyway.

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

is like, very famously, the Amazon, uh, web services mandate, right? Like, uh, Bezos was like, kind of things in you guys, the AI. Yeah, 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, and then the customers also get it.

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 wanna 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 there's like a thing that I'm toying with in my head is, could that just be like, okay, you trigger 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 versus all the other stuff?

Well, you know, unbounded execution and cost and latency, Yeah, that's the uh, that's is that the only hold back?

that's, yeah, and then I think, uh, deterministic, like, in, maybe in, you know, 100 out of, or in two out of 100 times. It's gonna do something whack that we didn't want it to do.

we're gonna go into like, harness and 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 because you could do all that. And obviously there's a prioritization issue. Like it, are are you at, uh, 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 wanna do more things and we n just need to hire like 100 people.

I was, I was very strongly the first thing for a very long time. Let's just say no to everything, and like, keep the eng team. I I think, um, I've said this before, but like, one of our presentations that I 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 in 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 be everyone's much bigger.

Uh, and we're a hundred 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, 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.

yeah, I mean, primitives is right, you know?

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

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. And Ooh,

We haven't made, I mean, we've made certain strategic bets, 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 that's like, we want all of these things, and so it's does. It 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.

like, strategically for you. So what are those that one the industry, things?

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 were just like, this is def definitely where the industry is going. This is gonna empower you to do so much cool stuff. Um, collaboration was another one, where, 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.

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

legal engineers, it w mostly Oh, legal engineers, will be, yeah, yeah. okay, that makes But they're like sense. 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.

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?

yeah, so we haven't fine-tuned any models up until now. I think now, in the past few months, open weight 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 the those queries super quickly and super cheaply, at low latency.

so specifically, you're post-training them to be better at Very specific, bounded searching? tasks. Yeah, exactly, yeah, Okay,

yeah. We're not trying to, like, train our own fable 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.

yeah. There's still a lot of, uh s, let's say, search and retrieval research, or RAG research to do. 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, Turbo Perf, but like, you know, there's also like, uh, do you do late interaction of like, you, you, you do that

yeah, uh, we actually don't do that, but it's, uh, you're completely right that this is. So there's one guy on the team, Simon, who's, uh, he just really cares about search, and he ca- he basically comes to me all the time, and he's like, Yeah, 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 the TurboPerf team to get them to build Multivector 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.

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.

Yeah, yeah, of course. So, yeah, Yeah. 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 you see something, then it knows how to go and do the legal research to figure out what the answer is, or What the precedent is. That's all very important, and then, of course, there's all the governance stuff around it as well.

Yeah, it seems like the search is probably, like, would you say, the most important tool that you guys are, like, customizing? Cause i It's If you can't pull in The right information, Yeah, and then then Then Yeah, You're, it's Yeah, you're screwed.

Screwed. It's, uh, yeah, I think it's it's it's, um,

You guys are searching, like, Search A lot of documents. And analysis. Yeah, it's Yeah.

Search, it's analysis, and it's drafting, probably. Cause, like, drafting words drafting huge contracts is actually also not super trivial.

Like, what about it is not Cause you have Trivial?

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 A specific Or not?

Law firm, how did they do it previously?

Yes, yeah, so I'm I am So 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, and you might have, like, multiple documents that you then try to figure out, wait, which part

should I take from what document? And that's actually non-trivial. So, It it's essentially also a search problem.

Which model's best at drafting? You know?

So, I'll say, I told I was perfecting this yesterday, uh, definitely, Fable and OFA are extremely chatty. I'm sure you guys have known this, uh, they're very, very So, that's not Verbose. Good. That's generally not good. No. So, this I noticed Is super interesting. Astra's been like, pretty Yeah.

Good at writing. Astra is, uh, yeah, Yeah. And Pretty good at writing,

Is it promptable?

Much more more concise. Um, Yeah, are you running, For for

Like, 100 different prompts to, like, Yeah, we Be sure?

We can yeah, we can we can Do we can do certain things, but I think the chattiness, verbosity, 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's gonna be much better at this. Astra is actually very concise. Yeah, yeah. And I

S I assume they they all have a Slack channel with you, and you're telling Them, like, Sorry, like, This is like, this Yeah, we don't Is not news to

Talk about this. Them. No, no, no, they know this.

Then the other thing that I really care about is hallucination. Do they make stuff up?

So, uh, we have a system of, uh, 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 view or the row in the tabular view, so you can actually, like, click multiple layers down and find, you know, sort of validate it all the way up.

Are you finding that lawyers are, like, verifying that these citations are The it in Correct or Not? In in. Initially, That's that's kinda like It's somewhat The art, isn't it? Working, but now, Like, are Yeah, exactly, it's the You actually

Same thing. Are you actually It's the same Some people should

Checking it? Thing.

Like, hallucinate links to Supreme Court. They don't care.

That happens, yeah. Exactly, that happens. I 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 distinction There's just, like, In law.

So much that, like, how can one human do that, right?

Yeah, but I think they probably just, like, we know in code review, what to look for, Like, 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, And, like, these sound reasonable, so it's probably fine. Just like, if you if you receive something from a junior lawyer, it's the same thing you do, right?

It's like, Ah, I should double check this, and, like, this probably is fine.

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?

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

Long, like, million token token contexts? Like,

You have a huge contract, 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. Hm. So, Um,

The simplest would be 1 shot. You put feed everything in and then 1 shot output. You don't do that. You break it up into chunks, and then You orchestrate edits. Yes.

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 at it, and it was, like, we've we've done, you know, we've done MapReduce, and we've changed them. 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.

Yes, I I I would say I I, um, I've recently I do a lot of, like, news reporting, uh, Obviously, cause of what I do, and I've recently shifted from MapReduce to throwing

In context. Everything into context, Yeah, yeah, And it's, like, Cause now they're both

Actually, it's better.

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 huge contracts, 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 in between the chunks, essentially, if you just summarize the individual parts up. And so, we've this has been a problem where it's like, we can do 2 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 2 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, uh, And it must And and Be hard, So

Like you said earlier, to actually make the models better at that, cause you can't even look at the contracts, right? Like, the real contracts. So, do you guys ever ask them for, like, Hey, can you Make example contracts That are similar to the

We do.

Real ones?

Yeah, yeah, so we have We have feedback, and can receive feedback from them, and if they're Things that the company Willing to engage, Yeah, exactly, 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 prompt, and whatever, and we'll re we if we can recreate it, then we can fix it.

I mean, so, one version of this is you buy a law firm, Which some people are considering.

Yes, but, uh, there's some we there's some stuff there on whether, uh, 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. Yeah, but it's, uh, yes, it's it's a way to get a lot of data.

Yeah, yeah. People like, Google's buying startup Google, exactly, AIs, right? Yeah, so you're I I Like, what? Saying Yeah, they bought

Yeah, they bought the yeah, yeah, for, like, Oh, the 10 million, ten Data. Oh, Million or whatever.

Okay, okay, yeah, yeah, yeah.

Like, you know, if you have a failed company, you still have your Slack, you can Sell the Slack. Like, I Think there's, like There's, like, a YC company that, like, buys your failed company.

Yes, there is, yeah, yeah, yeah.

Yeah, cause, like, it's just like, Oh, I just want, like, real Yeah, people People doing Are Work. And then, yeah, just, uh, like, Pull stuff up.

Exactly. The problem with buying, uh, law firm data is, do well, you get all the inputs, the real inputs, which is great. Uh, the outputs are a little bit more difficult cause you just get what their end result was, and it's difficult, uh, to figure out if, like, the way you have to basically, like, uh, 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, like, 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.

We're gonna wrap up soon. Uh, the last thing I'll point people to is also, there's a lot of alpha left on embeddings. If you're If you're a RAG-heavy work workload, uh, you're you're just looking, like, MTB and you're t taking, like, top model, uh, you're leaving a lot on the table. You should look at, like, uh, Voyage or, like, some of the Embed uh, custom embeddings. You you've Been looking into this.

We've yeah, yeah, yeah.

Yeah, so basically, don't take default embeddings, even, like, OpenAI embeddings, Gemini embeddings, doesn't matter. Customize your embeddings, Right? You you will you will Support that.

Yes, I th- I think that's right. I think that's right. We the only thing is, uh, need to make sure that you're m multi- uh, language. So, for us, we we serve so many languages, so that's I mean, Gonna be more You're the Of a problem.

Vis- like, king of this. Uh, Mistral, helpful there? Uh All right. Ooh.

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

Yeah, let's see.

I mean, you guys been

They also raised a ton of money, You're They're gonna be The you're You know, The champions, I think Like We need way more model companies out of the out of Europe.

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

Uh, ex- uh, we we asked a little bit of that earlier. I'll modify it to your second question, which is, uh, in 2 years, will lawyers do their work inside LeGora, will they use, uh, other tools like Claude or ChatGPT and Call LeGora, like, you know, the API?

Yeah Yeah. I think both. It really depends. I think if you're an an big enterprise, you might have Claude CoWork, 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, um, Because th- that's simpler and better. Um,

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

Encoding is well into the point where people the labs will cut you off for competing with them. And this has happened twice. Do you th- do you think that'll happen to law?

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

Like, you know, they are le- releasing legal services Too, right? And

Yeah. They are. I don't I mean, we obviously talk to them a lot, but it's also it's like, Hey, are you gonna what? Yeah, your sales team The

The sales team will say No, but they don't Make the call.

Exactly. That's not their job, Right? And they don't even know, o- like, often, what's actually going on. I don't think I don't think that's the case. They have so much stuff to capture in knowledge work, or in in 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, uh, they're never gonna go as deep as we are.

And I think if if Claude takes, uh, small client small, uh, 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, $400,000, 000 M&A transaction, you're gonna want LeGOR.

I had kind of an unrelated question, but I'm curious, are you guys going to law schools and kinda, like, getting them To, like, teach LeGOR, Like, in classes, like, how Does that work? And are Yeah, it's it's, You guys teaching them?

Uh, it's definitely a program that we are, uh, I think we've started. I actually Don't know exactly where we are, but we we do want people in law school to Learn to use LeGOR. Um,

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

I don't know. I I Wouldn't know, actually. I would actually do I don't It a different Know.

Way. Uh, you should do scholarships for law for law school for CS majors, for engineers. We will cover After you've Your Done CS, we'll we'll Yes, we'll cover

Put you in law school.

CS plus some software experience. We'll put you in law school. We'll cover it.

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

Yeah, but they they don't Care about the masters.

Well, I mean, I'm meaning, like, Cause there's a lot of people who didn't do CS undergrad, so then they do, like, masters just to kinda, like, get get that Cut off. Yeah.

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

Know. Yeah.

People do JD-MBA, that's a thing, but JD-CS, uh, I haven't seen it. Yeah.

Happens, yeah.

Yeah. Yeah, uh, okay, look, uh, overall, uh, you know, super impressive progress. I mean, congrats on all your success. Like, uh, are you still gonna keep up the pace? Like, Uh, I lo- Yeah, you know, uh, I and I think you're hiring in SF, New York, We're hiring Sweden.

In yeah, engineering, we're hiring in New York, um, Stockholm, and London, Uh, and all other roles, we're hiring in everywhere,

How many people do you have Honestly. In New York right now? 100. About 100, Okay, and you guys are Planning on how many in New York?

In New York? For for just, like, generally.

Let's just say, yeah, generally engineering.

Um, a lot. As many I don't know.

As you can.

Yeah, I mean, it's it's it's aggressive.

Yeah, I mean, uh, that So That's the home of corporate law, right, as far as, It is, yeah, Like, uh, American It is New York, Business concerns, So, So, like, yeah, I mean, k- I'm looking forward to you buying a law firm and, like, You know, becoming Yeah, it, uh, I it Is it's super exciting to to I think, like, you know, every industry, uh, especially, like, the top, like, doctors, lawyers, coders, you know, th- they all have to have, like, you Know, 2

I agree.

Or 3 agent labs that, like, just Yeah, so I Completely dominate Mean, I The space. So, Agree. You guys have, like, a Great market, yeah, good to hear.

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

Yeah. Also, I I think, like, I I mean, we're already, like, super over, but, like, uh, the problems that you work on are very, like, the frontier of knowledge work, You know? They're Okay, like, u- unless you're literally, like, doing, Never Like, science science Stops. Never Stokes and science. Other than that, like, most work is, like, basically, c- uh, converges to legal. Like, uh, yeah.

Yeah. It's all legal in the end.

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

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

Right, that's it.

All right.

Thank you.

Cool. Thanks.

Thank you.