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

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. 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 next model release solved, it went from 70% to 99%.

We did nothing, and great. But if you're doing a $400 million M&A transaction...

you're going to want Legor. We're just going to be 20 engineers for the rest of the company's history. And like, we're going to beat everyone who's much bigger. 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.

Yes, Jacob Lauritsen, CTO of Legora. Did I get it right, Lauritsen? That's fine. Yeah, that's okay. I'm not too particular on how it's Danish. Yeah, exactly. Does it have a special history? No, Sen is like son, son of. Son of Lauritsen? Just like you have son and yeah. So son of Lauritsen, that's my name. Nice. We've crossed paths here and there.

You spoke at AIU a few times. And obviously, Legora is one of the fastest growing legal tech in history. 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? 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 smallest startup in a basement in Stockholm was going to 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. 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 tell the world how great we are. Because it doesn't come naturally to, I think, some of us. I kind of want to 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. Yeah, absolutely. The way everything started was ChatGVT 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 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.

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 draft a lot of stuff really well. It will edit Word files. It will move your files away, organize everything, run really complex analyses.

And we've added just a bunch more features to it. one of our features called Tabular View, which is now a name that's being used in industry. And we're very happy to see Cloud for Legal using our terminology for what they're building. FRANCESC CAMPOY- Ooh, we got to talk about that. We got to talk about that. MARK MANDELMANN- Which is actually like a way to just bulk extract and book review many, many, many agreements, which you do in due diligence and 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. So we have different sort of, we have a thing called lists, which is sort of like linear for us.

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 10 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. When did you guys start doing or building the agent? So, I mean, we basically had this switch from the assistant to the agent. Yeah. We call it, right? I guess that the agent, I don't know, I want to say a year ago, probably.

Yeah. So, this is a rough timeline for people who are understanding. YC 2023. Yes. And you were a YC founder as well. YC 24. YC 24. Yeah, I was in YC23. The Goro was 24. Okay. And then, so there is, this is like a little bit pre-agents really taking off. Exactly. And then like reasoning models obviously change everything. I mean, you know, 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. Yeah. It's mostly like ChatGPT for lawyers, right? 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. Exactly. That's exactly what it is.

It's co-work or ChatGPT, just like really, really good for legal work. 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. Yeah. What models are you guys using underneath? Can you talk about that? I mean, we're using a bunch of different ones depending on task, right? And then that's not available to the lawyer to see.

You guys pick yourselves. Yeah. Well, we've been back and forth on this. Yeah. 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 tabular review. And 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 going to stay there always, to be honest. So, yeah. Yeah, I mean, so I bring a little bit of context to this because I'm an advisor for cognition. And when I joined, you know, part of my thesis for what an agent lab is, an agent lab is, you know, ideally a domain-specific GPT wrapper, right?

we are the domain experts we will 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 Labs according to our judgment our job is to decide for you because your job is not to exactly we'll always keep keep you on the Pareto frontier and make sure that it's great all the time and you don't have to dive into all the details.

Because one of the things that I've, exactly to this point, if you go to a lawyer and you ask them, oh, you're going to draft this contract based on this precedent, do you think that's a sonnet high or an opus mid task? They won't know. Just give me this model. Just make sure it works. My hourly rate is $1,000 an hour. Exactly. Just make it work.

so yes I originally came in with that I was like oh yeah this is what Devin does differently and now we have five things in the model picker including Fable and Opus and Astra and people want to experiment with the fancy new model is that the same I think so I think it's probably it's definitely way less illegal than it is in coding engineering yeah But there are definitely people that just want table one right away.

And people were asking us about mythos and everything, even though I think, realistically, a lot of legal work does not require mythos-level intelligence. MARK MANDELMANN- Yeah. So exactly, right? I think, basically, you're like, OK, we'll give you the option. You ask for this. But you're going to run down your credits like 10x faster than Yeah, I would have loved, we fought introducing it for a very long time.

And then in the end, we just kind of 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 is no need for them to get better? I think it's a power distribution. So like there's probably like 60% of the work we can do really well right now.

And from now on, it's like a cost and latency thing. Yeah. 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 with Fort Alardu thus probably expands with intelligence.

Yeah. I imagine. Early on, like when you guys first started, I guess, transitioning to the agents or building the agents, like what models were you guys using? I guess it would have been like Opus 4.6 or something. Yeah. That would have been, yeah, sonnet 4.6, output 4.6 is probably right. What were the agents not good at at that point that they're much better at now, even though it's only nine months later? Subagent delegation was one of them that we've gotten working really well now for 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 of those. So we basically have like a big heat map and we're like, and then we can see them move.

And it's like, usually they improve performance most stuff, but there's actually a lot of model releases where they improve some and regress in others. Okay. 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 are those different sub-segments, I guess, that you look at? So, like, there's different just, like, framing stuff.

So we have different, basically, like, worlds, like RL environments, essentially, which is like, here's a, because 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 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 you can kind of like subdivide it a little bit. And that's how we run the evals. Interesting. What does your evals team look like? Like, do you hire lawyers to like do that? 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 want to like help change the industry. Are they IT in big law? No, they're lawyers in big law. They're lawyers in big law. With CS degrees. Yes. Oh my God. It's a Venn diagram. 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's just 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 it's like help us shape the product.

And it's such an advantage. And curious, when did you guys start that team? IVALS grew out of the assistant agent team at some point. I think there was a point up until recently where it was honestly just not really worth it, because 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 want to build, because there was so much to be gained from building a better harness and like just sort of leaning into everything's going to improve and everything kind of just improved.

Yeah, like every two, three months you get a different model. Yeah, exactly. Just pass it through, right? Exactly. I mean, we had one problem where like it wouldn't site properly and so it would be difficult to follow and it was like next model release solved. It went from like 70% to like 99%. It's just like we did nothing and like, Yeah, maybe the real work is, you know, keeping all the data private, making it taggable, sortable, adding new features like the tabular view.

Is that the, you know... You mean over and above ChatGPT? Yes, but obviously now you're also doing evals. I assume 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 evals because it was mostly exposed model capability to lawyers.

Yeah. The huge part of it is just figuring out what does the legal profession look like in five years, 10 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 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 build a 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 AI 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 going to 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. Yeah. Yeah. Yeah. I was going to ask, like, could you go into that in a little more depth? Like, yeah. What is the, like, what profession going to look like in a few years?

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 going to be way more productive than they were before. They're going to be able to do a lot more stuff at a higher quality for lower cost. I think the profession itself, the work itself is going to improve a lot.

It's going to be a lot more I think lawyers are going to 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 all of their judgments, strategic judgment and like working with clients. They're going to do that a lot more and much less of the like trolling 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 going to happen in the partnership model? Like, do you think that stays or like what happens? I actually gave this a lot of thought just like last week, because the partnership model, I don't want to 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 have physical assets or like some sort of intangible assets that you accrue over time 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 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. Yeah. Will that change? Like, I don't... It doesn't have to, but I think what we really want to 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 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 that's something that we want to help empower. And does that change the partnership model then? Because the incentives are different. In the partnership model, you just got to bring more clients and you don't want to take away time from bringing in clients to codify your information, basically.

Because you get rewarded from eat what you kill or make this lockstep, whatever. That needs to change a little. We need to figure out an 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 as soon as they leave the partnership, they don't get any dividends from the assets that they built.

Yeah. So there's like a, yeah, I think the, the, the whole business model is, is, uh, We'll see. Yeah, yeah. It's all in question right now. My actual other take, you know, so on the partnership level, that's like the top end of the industry. Actually, my take is more on the bottom end, right? Yeah, what happened there? Paralegals, gone. Yeah.

Right? Like junior lawyers, gone. I don't need them. That's actually not what we're seeing. I think it's, I don't know, would you say that we're seeing that in engineering? Yeah. Yeah. Junior engineers are kind of cooked. You kind of have to come out of, drop out of university fully baked or else you're not going to make

it. I feel like I'm being a bit dramatic for a comedic purpose. But like, yeah, I know a lot of lawyers, they started as paralegal, they go to law school, all these things, right? And now they're not needed. They're seriously just not needed. 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 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 people lawyers or junior lawyers are worth a lot more.

Yeah. And it's always been the case, right? Yeah. Even more so. It's, yeah, it's polarizing even more so. Yeah. 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, This was actually a fun story.

I was reading Max's YC application and helping him getting into YC, Lea, as it was called back then in YC. And this was my one thing. I was like, dude. And curious, Lea is a Danish thing for something? No, it's Swedish. Swedish. No. Also, it means nothing. There's this really funny story in, I think it was a Spanish newspaper that wrote about us in the early days, Lea.

And then they explained that the abbreviation was Legally Efficient Yoda Assistant. Okay.

Why Yoda? Yeah, I don't know. See, hallucinations are not just from LLS. No, I think journalists hallucinate. But no, it doesn't mean anything. So he wrote the application. Yeah, 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...

Why would they be more efficient? They earn less money. Like, it doesn't make any sense. But I think... The reason that large do want to 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 going to change. 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 hour's 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.

So where is the money being made then? In the strategic work. Yeah, I feel like a lot of what you guys talk about is M&A specifically, like that's where all the money is made. That's just a very easy example. Oh, okay, okay. Litigation is also, the big work still is there and it's very valuable. And so they'll spend, lawyers will spend more of their time there.

Client relationships 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. Yeah. And so now they can do that, but they don't have to lose a lot of money. I thought, I thought I just, I have to pay the lawyer money just to be my friend.

Like, isn't that the retainer thing? Yeah. You told me I can do it for free. Like, yeah, you just have to find the right lawyers. Yeah.

Okay, cool. Or Latin space has to grow much bigger, I don't know. Yeah, yeah, we're trying. You know, so okay, so you're saying, you know, obviously the strategic work and all these high value ad is still there, but our legal fees are not going down. But you also said paralegals are not affected or like they're just shifting. 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 part of it does happen. Other junior engineers embrace it and then become more productive. Exactly like you just said. So I guess like, is there a new term for this role or this job that is having traction with your customers? You mean the super AI-built junior legal? Nothing I've found yet.

Maybe we should coin one. Isn't it legal engineer? That's our, and also now an industry thing. Yeah, CSJDs. Exactly. Yeah, yeah, yeah. Maybe those are the people that are best positioned to do this kind of stuff. I think the derogatory term of meet proxy, where you just 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 I do think a very good meet proxy is just like, well, you know agents very well, and you know Legora very well, and you know how to like, this is my toolkit, and every industry has a toolkit, and I can use my tools to do the thing that you need me to do. But I guess then you're not really a proxy, right? You're actually just doing meaningful work.

Yeah, it's just like I no longer like, you know, well, I'll talk about tabular review because that's the thing that happens a lot. I have hundreds, thousands, millions, thousands. We do up to a million cells, I think. In a single day. That's impressive. We should talk about the table and the windowing. Yeah, I'm working on a big case. I have a million documents.

type it in, usually I'll throw like a team of paralegals, lock them in a room. And they'll sit there until like 4 a.m. Like that doesn't need to happen, right? Because now they can extract it and you can go and reprompt everything. So like, yeah, I think now I don't need a paralegal for that, but like a good like super AI-pilled paralegal would do something else, you know? Yes, yeah, exactly.

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, you know? Yeah. I have a question. So you guys bought a company, Cura. Yes. Is that how you say it? And you guys used your own product to do the M&A? Yes, we do that all the time. So how did that work? Can you talk a little bit about that? Yeah, no, that works great.

We're doing that a lot. Our legal team is, I mean, intake has 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. Yeah, yeah. Right? And it's efficient. So it's like, great, we should look over for that. Yeah. Can you talk a little bit about that? Like, you know, what that process looked like? Yeah, absolutely.

So it's, we do a lot of the due diligence ourselves because we can do it with TabularView and other tools. We do still have counsel coming in to like assess certain risk or like, you know, there's payroll. And so Sakura 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 Loras 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 the, 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? No, I don't think so. I All right. Early on, you said your early customers were Swedish law firms. Have you seen a difference between working with Swedish law versus American law firms, that sort of thing? And you guys are mostly working with big, big law firms, right? Well, we're also smaller law firms also.

We definitely started really, really big law firms, but 50 lawyers also use us and get a lot of value. Yeah, so have you seen differences between working with the Swedish ones versus American ones? Maybe even, I don't know, Asian ones? Yeah, 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 the 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 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 structure in whatever way whereas europeans are much more like we'll just take the off the shelf and what's an example of something they would want to build themselves 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 Salesforce and it goes to this one person for whatever reason and they do something and then it goes into Lagor and then it goes back in and 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.

But that's definitely a thing where like American companies really want 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 say, hey, this sucks. This is great. We want more of this.

And we'll just build a product that does that. Okay. So they don't see like an existential threat here in their business. Whereas the American ones do? 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 it's both extremely important. I think it's just a different way to achieve it. Okay. Another question I think maybe you want to bring this up is product metrics. How do you know that 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? 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 DAO over MAU and our like, you know, hours 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 with a super cheap LMS, 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.

And that's like extremely frustrating to work with because 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 assumed you guys like signed some sort of agreement with the law firm and they're like, oh yeah, 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 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 evalsets. 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 that directly fully says the full trajectory. But obviously 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...

we can't really, I mean, there's always 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. Yeah. It's like we are generally pick the most safe way. It's like 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 figure out how to do in a smart way.

also like on the privacy front, I guess, I'm assuming even two years ago, it must've 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? It must be like a huge thing. All of our infrastructure is on Azure, primarily for this reason. Cause like when we started law firms were like AWS, No.

No way. You don't trust AWS? Yeah, yeah. It's different now. No, but they were like, Amazon, Google, we can't trust them with any of our data. So basically, we had to host everything on Microsoft because they already have 365. Oh, so they're okay with Microsoft? Exactly, because they've already done like, whatever security review, et cetera, for 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 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 just do it in the cloud and it's safe and it's probably safer than what you're doing. So that's changed a lot. And by the way, it's only been three years. So like, it's actually like, yeah, it's a shift. 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.

Yeah. I think we needed the AI kicking the butt for everyone to understand that we need to change our ways a little bit. Okay. Okay. So also then on like open source models now are getting really good. So yeah, how are you thinking about that with the... Yeah, we're just thinking about, to your point, just bring our clients along on like the Pareto frontier.

Yeah. And like the map of all the models and what they're good at and their latency and their cost and their governance and their regional availability. How do we just optimize across all of that? So... Some open weights 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.

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 you want to shout it out as surprisingly good. 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. Oh, so you have a... 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...

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 for the mental text. And so we can do all our analysis on it. No 11 labs. No 11 labs for DPA reasons. Same thing as like the data processing agreement, I should say. So like our data processing agreement has very few vendors on it.

Yeah. Because it's really difficult for us. Exactly. We need to keep it super tight. on where any data goes. And so... I think 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 state-of-the-art.

As long as it's like mostly good enough for all tasks, then who cares? Yeah, absolutely. I should actually shout out also Microsoft's transcription model. They made one recently. MyTranscribe? Yeah. Okay. It's great. okay it's better than the old gemini yeah yeah 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 arena scores and that's good enough yeah exactly it's like you have all the governance and it's super scalable and it's like 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 there if it's off that's no no no no for sure like i've done this a lot 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 describe it as condom.

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

average day-to-day conversation. Yeah. Yeah, absolutely. If there's any sort of jargon in there, it's going to be tough. Yeah, I think Whisper and 11 Labs still transcribe cloud code as cloud code. Yeah, I've actually had that problem. Very, very common. So that's how you know there's a lot more to improve. Yeah, absolutely. 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 name-dropped Tabular Review. We've name-dropped 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 fair to say that they're the big two? Agent and Tabular Review? Yeah. And projects. Yeah, and our Word add-in is also something, because a lot of people work inside of Word, and so our Word add-in is a huge, and Outlook add-in also.

Yeah, so I just want to cover the big ones that everyone must know. So Tableau Review is basically like fan out of a lot across each document. You can ask the same question across all documents, select it on the table, and then work back and forth with it. And then you can, yeah. A million is impressive. What's any other like engineering considerations or performance things or like what's hard about this? Before we do that, can you just like walk through like what is a user experience for a lawyer? And then like actually using tabular review.

Yeah, yeah. 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 the supply contracts, all of whatever. And so employment contracts, you put 10,000 employment contracts in there and then you, um.

Like each 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 going to 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 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 going to 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, 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 it can just do the review and then have, you know, a 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, etc.

And why do you choose that spreadsheet format? Yeah, it's just a lot better to... It's super easy to 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 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... I would say that the spreadsheet form factor 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. No, no. There was V7 that tried to launch. There's Sheets. Even in finance domain, I don't really have a top name that does spreadsheets. I agree. I think it's great 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 understand what's going on. Do you find you must export to Excel or people are happy to live in your spreadsheet? People are happy to live. there. Do you use AG Grid? We do use AG Grid. That seems to be like the leading one. I mean, they've done this for like, I don't know, 15 years. Yeah, they know how to.

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. Engineers maybe are well-equipped to understand the trade-offs of like, Well, OK, before you use fantastic out on a million documents, maybe test it on, like, two. MARK MANDELMANN- Yeah, yeah, yeah. Does that work before you go nuts? Yeah.

FRANCESC CAMPOY- Do they do that? MARK MANDELMANN- Yeah, they will. So our type of review actually will run the first 10 rows. FRANCESC CAMPOY- Yeah, just check, right? MARK MANDELMANN- Always. FRANCESC CAMPOY- Yeah, does this make sense? Did it show us what we thought it was going to show us? MARK MANDELMANN- Yeah. FRANCESC CAMPOY- 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 10 rows until 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, which is your Slack bot. Everyone has a Slack bot. What's different about yours? So ours is just legal specific.

And 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, 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 Legor and 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, hey, here's the ticket. I want this thing reviewed. Okay, now it's not. 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 that 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? 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. Yeah, 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 work really well. And you can have triggers on them, automations on them. And it's like a great glue to glue everything together because 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, adds 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 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 influence. Like, you know, it'd be cool to have like influencers.

Is that worth it? Too overcomplicated? We need 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 like our legal engineers to basically build a lot of products extremely fast. So you can build custom fund management dashboards. You can basically build that on list with your own 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 a bunch of specialized products that we can scale super quickly because all of our legal engineers can just build new ones. If they're out with a client, oh, you want your own? Easy. We'll just fix one for you. So it's like a lovable inside Legor a little bit.

And if we don't want to expose it, that's also how we build our own custom features. So 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 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 what's it called? Disagreement. And that's extremely powerful because then you can also transcribe a court hearing and you'll be like, oh, he said this thing, but actually the email over here says that he was not there.

And if you see it live, it's like so fucking cool. And that we can also build on this primitive. And so 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. So I think a lot about how do we build a core primitive that we can scale to many different end products and create very customizable experiences.

Okay, so what core primitives do you have? Let's just restate for people. Lists is a core one. Yeah, so we're configurable. Yeah, projects, it's basically containers of files, file systems. 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. Okay. Yeah, no, you mean like we called it like Leia or like we gave it a name? Ooh, yeah, Leia. Yeah, Leia would be cool. People used to talk about Leia as like a named entity. But yeah, we stopped that. Maybe I'll bring it back. It might be confusing. So Liz, Agent, 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 ones, yeah.

Yeah, so I actually wanted to talk a little bit about like FTEs because this sounds kind of 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 want to get them value like ASAP so that, you know, they stay on the Gora. Yeah, how has that evolved? Like, when did you guys start that forward deploy team? So we hired our first forward planning engineer.

That was our first time in New York. Also YC founder. Nine months ago, maybe. I'm not actually sure. Are they considered legal engineers or no? No. Okay. True engineers. But we do, it is something that I think about is like, how do we exactly enable that at scale? And I think a really core thing is like, how can we empower our legal engineers? Like how can we empower our power users and our legal engineers to customize the product in a powerful way? And then, of course, we will still have forward deploy engineers like help out, you know, do all the custom integrations and the scoping and figure out what's possible and feed all of that back into core product development.

So that's kind of how I think about it. 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 deploy 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.

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

But if it's a big client and they're super engaged and they like 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 a problem that we'd like to solve. Then we'll basically staff them with legal engineers and a forward-deployed engineer, potentially, depending on what 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 figure out all the workflows that you have right now 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, 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. Yeah, yeah. And a forward-deployed engineer writes code into production, basically. I guess that's the... What kind of background do the forward-deployed engineers normally have? Is that YC founders? Yeah, founders, regular engineers.

You're old. Yeah, D was your... Yeah, exactly. 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. Yeah, first boost on the ground in the US. What are some examples of, I don't know, workflows or things that these people are building for the clients? Do you guys have like, oh, these are like, you know, there's a couple use cases that like all the law firms are like, you know, this is the first thing that RFDs are going to do when they go in.

It's very different. Some core workflows everyone have, and we can just build in the core. And that could be anything from like, this is how we handle these types of NDAs 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 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 yes um yeah so like how did they work on client projects You mean the law firms, how do they work on client projects? Sorry, how do your FTEs work on client projects? So they don't touch the data still. So they'll just build the system. But they will also be onboarded like an employee sometimes.

So they might get a laptop and everything. Like to the law firm? Yeah, if they need to. Oh, wow. Interesting. That doesn't happen very often because usually they'll just build an integration and it kind of works. But yeah, they can if they need to. And you only onboard FTEs into a customer, I'm assuming, if they're a certain size, right? Yeah.

And these two make sense. Because RFDs can also work on core product, right? So it's like a constant prioritization thing. Is there a rule like, I guess, does every, like, you know, so Palantir famously had like, you know, four days you spend on site, one day you come back and contribute back to the products, anything like that? No, we don't.

I mean, to be fully honest with you guys, it's still, it's still, you know, 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 going to be more, maybe not exactly like Palantir, but like I think we will have a larger in constant circulation group of FDs that maybe 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. Yeah. The API business is actually interesting, like you said, because, you know, that's another rule that you can have where you will CTO maintainer of the Logora platform, right? We will offer everything that we have in the Logora web app as an API, and then you guys can use whatever.

Is that a promise they make? That's not something we're promising now. 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? And obviously, you know, some people will love it because I don't have to learn a new tool. I can just use the existing tool I have, right? And then I just like install Agora, for example, with the Word document stuff.

Other than that, you know, I do think like then you have to maintain it. Exactly. So that's been my thing. That's why we've tried not to do it. 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... We move so quickly in the product that I don't want to 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 a cost that we can take on. But like when we're 20 engineers, it's just like... we move so quickly that we can't do this. I have 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 the product.

Yeah, yeah, yeah. You know, like, a very simple one is web app, mobile app, right? Or, like, web app, mobile app, MCP, and then, like, you know, whatever, like, other integrations. Then your FDEs just are one more client to the overall platform anyway. Yes, yeah. And I think even the agent, you can think about it this way. There's like a harness team that runs the agent.

And you can even build a product around it with like skills and automations and whatever else. Yeah, this is like very famously the Amazon web services mandate. Like 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. And then the customers also get it.

Yeah, I think that's also changing a little bit. 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, 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 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. Is that the only holdback? Yeah, and I think deterministic.

Maybe in two out of a hundred times, it's going to do something whack that we didn't want it to do. We're going to go into harness and model fine-tuning in a bit. But I think 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. Are you more on the point of...

Let's 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 just need to hire like 100 people.

I was very strongly the first thing for a very long time. Let's just say no to everything. Like keep the Eng team. I think I've said this before, but like one of our presentations that like after I've been at Liguora for half a year, I pulled up this slide of... you know, the 300 Spartans for the movie. And I was like, we're just going to be 20 engineers for the rest of the company's history.

And like, we're going to beat everyone who's much bigger. We're 100 engineers now. And it feels like we're way too small. I wanted to do that. But I think in the real world, we're in like fierce competition. People want so much stuff. It's like, I could be a Puritan and just be like, no, we have to stay 20 people and we can only build, you know, whatever.

But then we just lose. And like people would go elsewhere. Yeah. 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 customer feels like we've built so much stuff, but we've actually only built a few things. That's how I think about my job right now.

Yeah. I mean, primitives is right, you know? Yeah, exactly. I think that's going to be, that's really powerful. Do testing your products, just seeing if like, hey, there's like any pull here and then you just kind of like, you're like, no, let's just focus on our main thing. We haven't made, I mean, we've made certain strategic bets. Yeah.

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. Yeah. It's like we want all of these things. And so it hasn't really made sense for us to try to be like, hey, maybe this thing could work because like. There's so many people screaming for the other things.

And so we mostly 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? Yeah, exactly. So what are those things? So one of those things

was the agent actually. So like no one was actually asking for like, I want it to be, I want the assistant that I'm using to have more agency and do things without me asking it. Like no one's, no one ever, but we're just like, this is definitely where the industry is going. This is going to empower you to do so much cool stuff. Collaboration was another one where like we think the industry is going to 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 are a few of those. And then, 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 going to take a lot for them to actually learn how to do that. And so that's where you kind of, like, say, hey, FDs, go in there and teach them what they do. Yeah, legal engineers, mostly.

Oh, legal engineers. But they're, like, some people call them forward-deployed legal engineers if you want, but that's essentially what they are. Then they go in, yeah, and help them structure their workflows around the capabilities of the agent. Okay. 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 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 post-trained model can do, legal research is a great example.

It's a fan-out retrieval problem, and you can make a really effective model to those queries super quickly and super cheaply at low latency. So specifically, you're post-training them to be better at searching? Very specific bounded tasks. Yeah, exactly. We're not trying to train our own Fable to be the main agent. We won't win that versus Entropic, most likely.

There's still a lot of, let's say, search and retrieval research or rag research to do that is like maybe less glamorous. It's not actually even model training sometimes. It's just like architecture and pipelines. You did a case study with TurboPuffer, but like, you know, there's also like, do you do late interaction? Yes, absolutely. You do that.

Yeah, we actually don't do that. But it's, you're completely right that this is, so there's one guy on the team, San, who's a, He just really cares about search and he basically comes to me all the time and he's like, we should do these things and like this is new embedding models and like we can do this late and late interaction. He actually talked to Turbo for teams to get them to build multivector so that we could do these types of things.

But no, there's loads of low hanging fruit generally, even before models and even in the harness, honestly, like if you just want to create a better output for our clients, there's like so much stuff that we can do that has immediate impact before training models. What makes a good harness for the law industry, I guess? You guys are making, I'm assuming, your own custom harness.

Yeah, of course. The way that we edit files is important. The way that we do an analysis is important. 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. Yeah, it seems like the search is probably, like, would you say the most important tool that you guys are, like, customizing? Because if you can't pull in the right information. Yeah, and then you're screwed. Yeah, I think it's search and analysis. Yeah, it's search, it's analysis, and it's drafting, probably.

Because, like, drafting huge contracts is actually also not super trivial. Like, what about it is not reviewable? Because you have to, let's say you're drafting a huge contract from scratch, then you have to find precedence of like, how did we do this previously? Do we need this type of clause or not? A specific law firm? How did they do it previously? Yeah.

So I am the law firm and I'm about to draft a huge. NDA is very simple, but there are contracts that are way more complex. And then you need to find the right precedent first. Because lawyers just don't sit and start typing stuff. 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 same industry, same type of company, same whatever. And so you need to identify the right precedent. You might have multiple documents that you then try to figure out which part should I take from what document. And that's actually non-trivial. So it's essentially also a search problem. Which model's best at drafting?

So I'll say, I told that as far as this yesterday, definitely Fable and Office are extremely chatty. I'm sure you guys have known this. They're very verbose. So that's not good. That's generally not good. I've noticed Astra is pretty good at writing. Astra is pretty good at writing. Is it promptable? Are you running like a hundred different prompts to be sure? Yeah, 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 Anthropo is going to be much better at this. Astra is actually very concise. Yeah, yeah. And I assume they all have a Slack channel with you and you're telling them this, right? Yeah, exactly. This is not news to them. No, no, no. They know this. Then the other thing that I really care about is hallucination.

Do they make stuff up? So 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 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 click multiple layers down and find, you know, sort of validate it all the way up. Are you finding that lawyers are verifying that these citations are correct or not? Initially, some of them were, but now it's the same thing.

People shit hallucinated links to Supreme Court. They don't care. That happens, yeah. I think it's like coding. You have engineers that just don't give a shit and just send agents, and you have people that sit and read every comma. There's just so much that how can one human do that, right? Yeah, but I think they probably just like we know in code review what to look for.

What is the system or whatever? I think they also know, okay, this is 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. Okay, interesting. Just like 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.

Any other elements of let's call it legal reasoning or what's the legal frontier that 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. Long, like, million token context. Yeah, exactly. You have a huge contract.

Yeah. And, like, you're making edits across it. It's a difficult thing to do for a model today. And, like, remember that you changed all these things up here and, like, the definitions changed and the ordering changed and whatever else. So the simplest would be one shot. You feed everything in and then one shot output. Yes. You don't do that.

You break it up into chunks and then you orchestrate edits. Yeah, exactly. 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 sizes.

Like we keep changing the scaffolding that we build around as models change. Yes. I would say I do a lot of news reporting, obviously, because of what I do. And I've recently shifted from MapReduce to throw everything into context. And it's better. Yeah, exactly. But it's also 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 in between the chunks, essentially, if you just summarize the individual parts up. And so 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, you need to have reasoning in the different steps there in between. So I'm trying to think of a really good example here. Yeah, 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... And it must be hard, like you said earlier, to actually make the models better at that, because you can't even look at the contracts, right? It's the real contracts. So, do you guys ever ask them for, like, hey, can you make example contracts that similar to your real ones yeah yeah so we have we have feedback and can receive feedback from them and if they're 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 problem whatever and we'll if we can recreate it

then we can fix it yeah i mean so one version of this is you buy a law firm yeah which some people are considering Yes, but 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. Interesting. But it's, yes, it's a way to get a lot of data.

Yeah, people like Google's buying Spirit Airlines. Exactly. Same thing. Yeah, they bought the, yeah, for like 10 million, 7 million or whatever. 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 like buys your failed company. Yes, there is.

Yeah, yeah, yeah. Yeah. Cause like, it's just like, oh, I just want like real people doing work. Exactly. And then, yeah, so it was like, 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 because 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. difficult. We're going to 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 at MTEB and you're taking top model, you're leaving a lot on the table. You should look at Voyage or some of the custom embeddings. So basically, don't take default embeddings. Even OpenAI embeddings, Japanese embeddings, doesn't matter.

Customize your embeddings. You will support that. 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. So that's going to be one of the problems. I mean, Europe is a king of this. Yeah, exactly. Mistral, helpful there? No. Until now, they just raised a ton of money, right? So maybe, let's see.

They also raised a ton of money a year ago. They're going to be Europe champions. I think we need way more model companies out of Europe. Yes. I just wanted to ask you, what predictions do you have maybe over the next year for the wine industry?

We asked a little bit of that earlier. I'll modify it to your second question, which is, in two years, will lawyers do their work inside Legora, or will they use other tools like Cloud or Tragedy and call Legora? Like, you know, the API. Yeah, yeah, yeah. I think both. It really depends. I think if you're a big enterprise, you might have Cloud Cowork, and then you'll...

I think it's similar to, like, how I use Linear through Cloud, but I still go to Linear. I think enterprises will do that. I think law firms will just use Legora because that's simpler and better. Yeah. It kind of reminds me of like open evidence for like medicine. You're basically that for law. Yeah, exactly. Encoding is going to a point where people, the labs will cut you off for competing with them.

And this has happened twice. Do you think that will happen to law? No, I don't think so. Because like, you know, they are releasing legal services. Yeah, they are. I mean, we obviously talk to them a lot, but it's also like, hey, are you going to... Your sales reps will say no. Exactly. They don't make the call. Exactly. That's not their call to make.

Right. And they don't even know like often what's actually going on. I don't think that's the case. They have so much stuff to capture in 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 going to 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 great. That's fine. But if you're doing a, you know, $400 million M&A transaction, you're going to want Legorra. 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 in classes? Like, how does that work? Yeah, it's definitely a program that we are, I think we've started.

I actually don't know exactly where we are, but we do want people in law school to learn to use Legora. Like, are you seeing that like law schools are changing their curriculums a lot or not really? Yeah. I don't know. I wouldn't know, actually. Interesting. I would actually do it a different way. You should do scholarships for law school for CS majors, for engineers.

After you've done CS? Yes. We'll put you in law school? CS plus some software experience, we'll put you in law school. We'll cover it. Or you do like the MA, like master's plus JD programs. Yeah, but they don't care about the masters. Meaning like, because there's a lot of people who didn't do CS undergrad, so then they do like masters just to kind of like get caught up.

Yeah. Yeah. I don't know. I don't see that as often. Yeah. People do JD, MBA. That's a thing. Yeah. But JD, CS, I haven't seen it. Happens. Yeah. Yeah. Yeah. Okay. Look, overall, you know, super impressive progress. I mean, congrats on all your success. Like, are you still going to keep up the pace? Absolutely. Yeah. You know, I think you're hiring in SF, New York.

We're hiring in engineering. We're hiring in New York, Stockholm and London. Yeah. And all other roles we're hiring everywhere. How many people do you have in New York right now? A hundred. Okay. And you guys are planning on how many in New York? In New York? Yeah. Just like generally? Let's just say, yeah, generally and generally. A lot.

As many as you can. Yeah. It's aggressive. Yeah. I mean, that's the home of corporate law, right? As far as like America's concerned. So like, yeah, I'm looking forward to you buying a law firm and like, you know, becoming... Yeah, it's super exciting. I think every industry, especially the top doctors, lawyers, coders, they all have to have two or three agent labs that just dominate the space.

So you guys have a great market. Yeah, I think so. And I think it's only going to get much bigger as law changes and becomes more available to more people. yeah also i think like i mean we're already like super over but like uh the problems that you work on are very like the frontier knowledge work you know yeah they're okay like unless you're literally like doing like science and science other than that like most work is like basically uh converges to legal yeah like

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 because like modern society runs in some way on legal. Yeah. Yeah. Cool. All right. That's it. Thank you. Thank you. Thanks.