# Building Legal Agents When You Can't See the Data — Jacob Lauritzen, CTO of Legora Latent Space · 2026-11-02 · 67 min · https://www.youtube.com/watch?v=bJBEFzlKPoQ ## Transcript swyx 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. Jacob Lauritzen Yeah. swyx Junior lawyers: gone. I don't need them. Jacob Lauritzen That's actually not what we're seeing. We had one problem where it wouldn't cite properly, and we thought, “Next model release, solved.” It went from 70% to 99%. We did nothing, and it was great. swyx But if you're doing a $400 million M&A transaction, you're going to want Legora. Jacob Lauritzen We're just going to be 20 engineers for the rest of the company's history, and we're going to beat everyone who's much bigger. We're 100 engineers now, and it feels like we're way too small. But it's something I'm toying with: how much of our product can just be the agent versus all the other stuff? swyx Okay, we're here in the studio with special guest Jacob Lauritzen, CTO of Legora. Did I get it right, Lauritzen? Jacob Lauritzen That's fine. Yeah. swyx Lauritzen. Jacob Lauritzen That's okay. swyx And that's Danish. Jacob Lauritzen I'm not super particular about it. It's Danish, yeah, exactly. swyx Does it have a special history behind it? Jacob Lauritzen No, “sen” is like “son of.” swyx Son of Laurits. Jacob Lauritzen So it's just like “son of.” So, son of Laurits—that's my name. swyx Nice. We've crossed paths here and there. You spoke at AI a few times, and obviously Legora is one of the fastest-growing legal tech companies in history. Jacob Lauritzen Yep. swyx You said something at the start in our 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? Jacob Lauritzen I think at our core, we're 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 way ahead of us in the US. I think we've always been underdogs, so we've always been very humble. We've always sort of had to fight for our existence. Something we've had to learn as we've entered the US and spent more time there is to be a little bit bolder and tell the world how great we are, because it doesn't come naturally to some of us. swyx I want to start by going over your product, because I feel like with a lot of these legal products, they're kind of under wraps. You're not supposed to show them. Jacob Lauritzen Yeah, sure. swyx If you could just talk about what the product looks like and maybe how you got there—what product iterations got you to where you are today—I think that would be really interesting. Jacob Lauritzen Yeah, absolutely. The way everything started was ChatGPT with a Swedish law search tool in it. That was literally everything. We started with legal research, which is a huge market where lawyers spend a lot of time figuring out what previous cases look like this and what the legal precedent is. What have people done in these situations? That's extremely important. That has always been part of our product. We started with an agent you could ask questions, and it would query laws. That was the very simple beginning. From there, it's expanded in what the agent can do. It will now draft a lot of stuff really well, edit Word files, move your files around, organize everything, and run really complex analyses. We've added a bunch more features to it. One of our features is called Tabular Review, which is now a name that's being used in the industry. We're very happy to see Claude for Legal using our terminology for what they're building. swyx Ooh, we gotta talk about that. We gotta talk about that. Jacob Lauritzen It's essentially a way to bulk extract and bulk review many agreements, which you do in due diligence and when you raise money or whatever. That's part of it. We help lawyers do their work much more efficiently and much better. Outside of just doing the work, we're also helping orchestrate the work a lot more than we were even a year ago. 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 Portal, which is also a way to collaborate: lawyer to lawyer, client to lawyer, lawyer to agent, maybe agent to agent. We're spending a lot of time there because, frankly, the way you worked 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. Those are, I think, the 2 things: doing the work and orchestrating the work. swyx When did you start building the agent? Jacob Lauritzen We basically had to switch from the assistant to the agent, as we call it. I guess the agent came about a year ago, somewhere around then. swyx So this is a rough timeline for people who are trying to understand: YC 2023. Jacob Lauritzen Yes. swyx And you were a YC founder as well. Jacob Lauritzen It was YC 2024. swyx YC 2024. Jacob Lauritzen Yeah, I was in YC 2023. swyx Yeah. Jacob Lauritzen Legora was 2024. swyx Okay. So this is a little bit before agents were really taking off. Jacob Lauritzen Exactly, yeah. swyx And then using models obviously changed everything. Jacob Lauritzen Yes. swyx In one sense, today—we had a preview of the product. Well, we had a private screening. Jacob Lauritzen Private screening, yeah. swyx We'll put up a video on YouTube. It's mostly like ChatGPT for lawyers. Jacob Lauritzen Yep, yep. swyx That's a very fair way to put it. The sidebar has a lot of nice custom tools, like Tabular Review and Intake, which I really liked, and a bunch of other things. Jacob Lauritzen Exactly. That's exactly what it is. It's Cowork or ChatGPT, just really, really good for legal work. swyx And the workflow for in-house corporate lawyers, people looking for upcoming regulations, all these things—we can talk about more of the products there. What models are you guys using underneath? Jacob Lauritzen We're using a bunch of different ones, depending on the task. swyx Okay. And that's not available for the lawyer to see? You guys pick them yourselves? Jacob Lauritzen For the agent, yeah. We've been back and forth on this, just like everyone else, I think. In the agent, there's a model selector for the primary model, but there are certain tools where we use different models. We try different models in Tabular Review. I think we've found it most effective to subdivide the problem and route as we subdivide the task. But right now, we do have a picker in the agent. I'm not sure if that's always going to stay there, to be honest. swyx Yeah. I bring a little bit of context to this because I'm an advisor for Cognition. Part of my thesis for what an agent lab is: an agent lab is ideally a domain-specific GPT wrapper. Jacob Lauritzen Yeah. swyx We're the domain experts. We'll pay attention to you, serve your needs way more than the frontier labs, and give you the best of the frontier labs according to our judgment. Jacob Lauritzen Yeah, we'll abstract away all the— swyx Our job is to decide for you, because your job is not to dive into all the details. Jacob Lauritzen Exactly. We'll always keep you on the Pareto frontier and make sure it's great all the time, and you don't have to dive into all the details. One thing that speaks exactly to this: if you go to a lawyer and ask them, “You're going to draft this contract based on this precedent. Do you think that's a Sonnet High or an Opus Mid task?” swyx They won't know. Jacob Lauritzen “Just give me the smartest model.” swyx Fair. swyx Exactly. Just make sure it works. Jacob Lauritzen My hourly rate is $1,000 an hour. swyx Exactly. Just— Jacob Lauritzen Like, what— swyx Make it work. Jacob Lauritzen So, yes, I originally came in with that. I was like, “Oh, yeah, this is what Devin does differently.” Now we have 5 things in the model picker, including Fable and Opus and Astra. People want to experiment with the fancy new model. swyx Yep. Jacob Lauritzen Is that the same? swyx I think so. It’s definitely way less in legal than it is in— Jacob Lauritzen Coding. swyx —engineering. Jacob Lauritzen Yeah. swyx But there are definitely people who just want Fable 1 right away, and people were asking us about Mythos and everything, even though I think realistically a lot of legal work doesn’t require Mythos-level intelligence. Jacob Lauritzen Yeah. So, exactly, right? I think basically you’re like, “Okay, we’ll give you the option. You ask for this, but you’re going to run down your credits 10 times faster.” swyx 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 were like, “Okay, if you want this level of control, we’ll give it to you.” Basil Chatha So you think the models are already as good as lawyers need? There’s no need for them to get better? Jacob Lauritzen I think it’s a power distribution. There’s probably 60% of the work we can do really well right now, and from now on it’s a cost and latency thing. But for the rest of the work, especially very complex analysis, we still need more intelligence. I think there’s also the work expanse. That’s the work we have right now, but the work available to lawyers probably expands with intelligence, I imagine. Basil Chatha Early on, when you guys first started transitioning to the agents—or building the agents—what models were you using? I guess it would’ve been Opus 4.6 or something. Jacob Lauritzen That would’ve been, yeah. Sonnet 4.6, Opus 4.6 is probably right. Basil Chatha What were the agents not good at then that they’re much better at now, even though it’s only, what, 9 months later? Jacob Lauritzen Subagent delegation was one of them. We’ve gotten it working really well now for fan-out-type retrieval queries. It works extremely well for us now. That was difficult before. ### Evaluating Legal Agents We have a team that’s just doing evals, and we track all of the models’ performance in different practice areas, which are subgroups of legal, and across different tasks in all of those. We have a big heat map, and we can see them move. Usually, they improve at most things, but there are a lot of model releases where they improve at some things and regress at others. That happens a lot more than you’d think. swyx What are some of those tasks? Are you familiar with how you guys are running a lot of the evals? What are the different subsegments you look at? Jacob Lauritzen Yeah. There’s different framing stuff. We have different worlds, like RL environments, essentially. Lawyers work in projects, more or less, so it’s like: “Here’s a 10,000-file data room. You’re doing due diligence. In the end, a great report looks like this. It contains all these red flags, and it doesn’t contain weird stuff. We want it to be concise,” et cetera. That’s how we’ve built it. There are different tasks. Part of it is drafting a report: does the draft look good? Does it contain all the right stuff? Is the wording sound? Is the analysis sound? There’s also finding the red flags, the analysis before that. We can subdivide it a little bit, and that’s how we run the evals. swyx Interesting. What does your evals team look like? Do you hire lawyers to do that? Jacob Lauritzen Yes, it’s a mix. We have engineers and lawyers, and it’s one team. There are 3 engineers and 3 lawyers right now, and then we have a pool of what we call legal engineers. They’re people who have worked in Big Law for 3 or 4 years. Typically, they might have a CS degree, and they’re very tech-forward. They come to us because they want to help change the industry. Basil Chatha Are they IT in Big Law, or are they lawyers? Jacob Lauritzen They’re lawyers. Basil Chatha They’re lawyers in Big Law? Jacob Lauritzen They’re lawyers in Big Law. Basil Chatha With CS degrees? Jacob Lauritzen Yes. Basil Chatha Oh my God. swyx That must be really hard to find. Jacob Lauritzen It’s a Venn diagram. Yeah, exactly. That’s 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 product development. You have a pool of 100 experts who use the product every day and talk to clients every day. They live this and have lived this, and we can pull on them to do evals and help us shape the product. It’s such an advantage. swyx When did you guys start that team? Jacob Lauritzen Evals grew out of the assistant agent team at some point. Until recently, it honestly wasn’t really worth it, because all the models just got better. It was like, do we want to spend a lot of our time doing really complex evals, or do we just want to build a better harness and lean into the fact that everything’s going to improve? Everything kind of just improved. Basil Chatha Yeah, every 2 or 3 months you get a different tier of model. Jacob Lauritzen It just got solved. Basil Chatha Just pass it through, right? Jacob Lauritzen Exactly. Basil Chatha Yeah. Jacob Lauritzen We had one problem where it wouldn’t cite properly, so it was difficult to follow. The next model release solved it. It went from 70% to 99%. We did nothing, and it was great. Basil Chatha Maybe the real work is keeping all the data private, making it taggable and sortable, and adding new features like the tabular view. Is that the— Jacob Lauritzen You mean over and above ChatGPT? Basil Chatha Well, yes. But obviously now you’re also doing evals. I assume your use of open models is increasing. Jacob Lauritzen Yes. Basil Chatha We can talk about that. I don’t know what I’m saying here, apart from: what is the job? The job is maybe not—in the early days, it wasn’t so much about doing evals, because it was mostly exposing model capability to lawyers. Jacob Lauritzen A huge part of it is figuring out what the legal profession looks like in 5 or 10 years with all of this stuff. Coding is maybe a year or 2 ahead, so we can look to that a little bit. But what are the primitives? How do people work? How do you collaborate if it’s not a 200-thread email with V5 Word files going back and forth? What does that look like? That’s not even necessarily purely AI. It’s about building a much better product experience and making sure you do it with audit logs, data retention, and all those really important things in a regulated industry. Then there’s the AI part: make the work faster and better, and build proactive agents that react to things when they come in, so you don’t have to kick everything off yourself. A lot of the work is figuring out what we think it’s going to look like in 5 years. If model capabilities keep increasing and the price keeps coming down, what could we do? Can you log in and have a command center where it’s like, “You need to react to these 5 things the agents have been doing lately,” and review and check and improve the system? Maybe that’s where we’re going—or where we are going. swyx I was going to ask if you could go into that in a little more depth. What is the legal profession going to look like in a few years? Jacob Lauritzen I should preface this by saying I don’t know. swyx Yeah. Jacob Lauritzen 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. Jacob Lauritzen They’re gonna be able to do a lot more stuff at a higher quality for a lower cost. I think the profession itself, the work itself, is gonna improve a lot. Lawyers are gonna spend more of their time doing the stuff they became lawyers to do: figuring out the right risk profile, what’s manageable risk, using their judgment and strategic judgment, and working with clients. They’re gonna do that a lot more, and spend much less time trolling through big documents to find the smoking gun or doing all the menial, super annoying work that a lot of lawyers have been doing. swyx What do you think is gonna happen to the partnership model? Do you think that stays, or what happens? Jacob Lauritzen I actually gave this a lot of thought just last week. swyx Yeah. Jacob Lauritzen The partnership model kind of exists because the only type of capital these companies have is human capital. It’s not like us, or a software engineering firm, or a manufacturer, where you have physical assets or some sort of intangible assets that you accrue over time, and they pay dividends to shareholders. But if you work in an industry like professional services—and it’s the same for consultancies and whatever else—all of your value is in your people, and you can’t really own human capital. You can’t own people; slavery’s abolished. But you can rent them. You can pay them money. So partnerships are essentially a structure where you make the human capital the owners of the company, so that they stay. swyx Yeah. Jacob Lauritzen Will that change? It doesn’t have to. But what we really want is for law firms to be able to build some sort of intangible, durable capital. You can build a system that learns how you work. A lot of firms think about how there’s the X law firm way of doing things, and we can codify that and build a system. Whether that’s a self-improving knowledge graph or whatever it is, and precedent files and documents, there’s a way of working that produces a really good output, and that can be their IP. It’s a way to codify human expertise and judgment into a system. That’s something we want to help empower. swyx Mm. Jacob Lauritzen Does that change the partnership model? The incentives are different in the partnership model. You just have to bring in more clients, and you don’t want to take time away from bringing in clients to codify your information. swyx Mm. Jacob Lauritzen You get rewarded by “eat what you kill” or by a lockstep model, whatever. That needs to change a little. We need to figure out an incentive structure where partners are incentivized to codify things and build an asset for the company. But right now they aren’t, because as soon as they leave the partnership, they don’t get any dividends from the assets they built. swyx Yeah. Jacob Lauritzen I think the whole business model—we’ll see. swyx Yeah, yeah. It’s all in question right now. Basil Chatha My actual other take is more on the bottom end of the industry. The partnership level is the top end. Jacob Lauritzen Yeah. What happened there? Basil Chatha Paralegals are gone. Jacob Lauritzen Yeah. Basil Chatha Right? Junior lawyers are gone. Jacob Lauritzen Mm. Basil Chatha I don’t need them. Jacob Lauritzen Yeah. Basil Chatha That’s actually not what we’re seeing. Jacob Lauritzen Okay. Basil Chatha So, I don’t know. Would you say that we’re seeing that in engineering? Jacob Lauritzen Yeah. Basil Chatha Yeah? Jacob Lauritzen Junior engineers are— Basil Chatha Really kind of cooked. Jacob Lauritzen —kind of cooked. Basil Chatha Yeah. Jacob Lauritzen You kind of have to come out of university fully baked, or else— Basil Chatha Or else you’re not gonna make it. Jacob Lauritzen I feel like I’m being a bit dramatic for comedic purposes. But I know a lot of lawyers who started as paralegals, then went through law school and all these things, right? Basil Chatha Yeah. Jacob Lauritzen And now they’re not needed. Basil Chatha Yeah. Jacob Lauritzen They’re seriously just not needed. Basil Chatha Yeah. Yeah. Jacob Lauritzen It’s interesting what happens to the partnership model, the pyramid. I think generally, you still need the next generation. For engineering, the way I think about it is that a good engineer today is worth a lot more than they were 2 years ago, because they can produce so much more stuff, if they’re good. I think it’s the same thing in legal: they can actually do a lot of really good work if they’re good. So I think it’s more that really good junior lawyers are worth a lot more. Basil Chatha Yeah, it’s— Jacob Lauritzen And— Basil Chatha It’s always been the case, right? Jacob Lauritzen Yeah. Basil Chatha Exactly. Jacob Lauritzen But it’s even more so. It’s polarizing even more. Basil Chatha Yeah. Basil Chatha I’m actually curious about that. The whole law business is basically charging per hour. Jacob Lauritzen Mm. swyx So— Jacob Lauritzen Yeah. swyx If each project can be done— Jacob Lauritzen It’s faster. swyx —a lot faster— Jacob Lauritzen Yeah. swyx —is it gonna be way cheaper? Jacob Lauritzen This was actually a fun story. I was reading Max’s YC application and helping him get into YC, when Leya was called that back in YC. This was my one thing: people have tried this a million times. Legal tech has never been a thing because there’s no incentive for lawyers to be more efficient. Why would they be more efficient? They earn less money. It doesn’t make any sense. But I think lawyers do want to adopt this because they understand the gravity of the situation. They know the business model and everything is under pressure, and they need to change because the competitive pressure is so high. I think the billing model itself is also gonna change. We’re already seeing that, particularly in the US, where a bunch of stuff is being priced on a project fee and not an hours fee, particularly the lower-end stuff on the spectrum, like small reviews and whatever. Some of it is honestly being done for free— Basil Chatha Mm. Jacob Lauritzen —and some of it is just being priced at a flat rate. Basil Chatha So where is the money being made, then? Because I feel like a lot of what you guys talk about is M&A specifically. Is that where all the money is made? Jacob Lauritzen That’s just a very easy example. Basil Chatha Oh, okay, okay. Jacob Lauritzen Litigation, too. The big work is still there, and it’s very valuable, so lawyers will spend more of their time there. Client relationships are also super important. Basil Chatha Like a CRM? Jacob Lauritzen No, just spending more time with the client. Basil Chatha Oh. Jacob Lauritzen A lot of law firms have historically done stuff for free just to have that relationship with the client. Basil Chatha Yeah, yeah. Jacob Lauritzen So now they can do that, but they don’t have to lose a lot of money doing it. Basil Chatha Wait, I thought I just had to pay the lawyer money to be my friend. Isn’t that the retainer thing? Jacob Lauritzen Yeah. Basil Chatha You’re telling me I can do it for free? Jacob Lauritzen Yeah, you just have to find the right lawyers. Basil Chatha Oh, goddammit. Okay, cool. Jacob Lauritzen Or Legora has to grow much bigger. I don’t know. Basil Chatha Yeah, we’re trying. So you’re saying the strategic work and all these high-value-add things are still there, but our legal fees aren’t going down. You also said paralegals aren’t affected, or they’re just shifting. This is something we also worry about with Cognition. Basil Chatha Yeah. swyx People worry about the phrasing, like, “We will replace your junior engineer,” because nobody likes that kind of statement. But in actual fact, yes, some part of it does happen. Other junior engineers embrace it and become more productive. Basil Chatha Exactly. swyx Exactly like you just said. Basil Chatha Yeah. swyx Is there a new term for this role or job that’s gaining traction with your customers? Basil Chatha You mean the super-AI-pilled junior legal? Nothing I’ve found yet. Maybe we should coin one. swyx Isn’t it a legal engineer? Basil Chatha Legal engineer? That’s our term, and it’s also now an industry thing. swyx Yeah. Basil Chatha Yeah. swyx CS JDs. Basil Chatha Exactly. Yeah. And maybe those are the people best positioned to do this kind of stuff. swyx I think the derogatory term is “meat 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. Basil Chatha Yeah. swyx But I do think a very good meat proxy is someone who knows agents very well and knows Legora very well. Basil Chatha Yeah. swyx And you know, “This is my toolkit.” Every industry has a toolkit. Basil Chatha Yeah. swyx And I can use my tools to do the thing that you need me to do. Basil Chatha But I guess then you’re not really a proxy, right? You’re actually just doing meaningful work, I suppose. swyx Yeah. I’ll talk about Tabular Review, because that’s a thing that happens a lot. I have thousands— Basil Chatha We do up to a million cells, I think. swyx In a single— Basil Chatha In a… Yeah. swyx That’s impressive. Basil Chatha Yeah. swyx We should talk about the table and the windowing. Basil Chatha This. Yeah. swyx Yeah, I’m working on a big case. I have a million documents. I type it in. Usually, I’ll throw a team of paralegals into a room. Basil Chatha Yes. swyx Locked in a room. Basil Chatha And they’ll sit there till 4:00 AM. Yeah. swyx That doesn’t need to happen, right? Basil Chatha Exactly. swyx Because now they can extract it, and you can go and reprompt everything. Basil Chatha Mm-hmm. swyx So now I don’t need a paralegal for that. But a good, super-AI-pilled paralegal would do something else, you know? Basil Chatha Yes. Yeah, exactly. swyx Whatever that is. Basil Chatha Yeah. They can do more stuff, or spend more time on the things they didn’t have time for before. swyx Or actually sleep. Who knows? Basil Chatha No. swyx I have a question. You guys bought a company, Kira. Is that how you say it? Basil Chatha Yeah. swyx And you guys used your own product to do the M&A? Basil Chatha Yes, we do that all the time. swyx So how did that work? Basil Chatha Dogfooding. It works great. We’re doing that a lot. Our legal team is—I mean, intake has been built with our legal team. swyx Yeah. Basil Chatha Right now, we have a Slack workflow where everyone floats their stuff in, and they’re like— swyx Yeah. Basil Chatha “This is annoying.” swyx Yeah, yeah. Basil Chatha Right? And inefficient. So it’s like, great, we should use Legora for that. swyx Yeah. Can you talk a little bit about what that process looked like? Basil Chatha Yeah, absolutely. We do a lot of the due diligence ourselves because we can do it with Tabular Review and other tools. We still have counsel come in to assess certain risks. For example, there’s payroll. Kira was simple because that was all in Sweden, but we’ve done one in Canada and one in Australia, and there’s payroll in Australia. Do we want someone to look at this more strategically? We’ll still use lawyers for the strategic part, where they can be sparring partners and help us figure out how to structure this the right way. But a lot of the more menial stuff we can do ourselves. swyx Mm. Basil Chatha A lot of the early things we find—and we’ve had cases where we found something that was a red flag, and then we’ve pulled the brakes. swyx Can you talk a little bit about any of those? Basil Chatha No, I don’t think so. ### How Law Firms Adopt AI swyx All right. Early on, you said your early customers were Swedish law firms. Have you seen a difference between working with Swedish law firms versus American law firms? You guys are mostly working with big law firms, right? Basil Chatha We’re also working with smaller law firms. swyx Oh, okay. Basil Chatha We definitely started with really, really big law firms, but firms with 50 lawyers use this and get a lot of value too. Jacob Lauritzen So have you seen differences between working with the Swedish ones versus American ones? Maybe even Asian ones? Basil Chatha Yeah. I think the European ones have been a bit slower to move. The American ones are very forward and move really quickly. I think it’s also much higher on the agenda for American companies than European ones. It’s a strategic, super-important thing that they need to do a lot of. American companies, both corporates and law firms, also have a much higher appetite to custom-build stuff. They all want to do that. They’ll say, “Hey, we want to build this huge thing with you guys and structure it in whatever way.” Jacob Lauritzen What— Basil Chatha Whereas Europeans are much more like, “We’ll just take the off-the-shelf and figure it out.” Jacob Lauritzen What’s an example of something they would want to build themselves? Basil Chatha Integrations into their own systems. Some of these customers build their own CRM and their own document management system and all sorts of other things, and they want to build that. Then they want to build triggers, like: you do a review in Salesforce, it goes to this one person for whatever reason, they do something, then it goes into Legora, and then it goes back. That’s the simple end. Then there are some that are extremely ambitious, where it’s a whole new product they want to build with us. We can’t really do that. Jacob Lauritzen Yeah, yeah. Basil Chatha That’s definitely something where American companies really want to build their own more than European ones do. Jacob Lauritzen And the European ones are like, “Hey,” and they give you product suggestions? Basil Chatha Yeah, for sure. We have great collaboration with all of them. Jacob Lauritzen Yeah. Basil Chatha They’ll say, “This sucks, this is great. We want more of this.” Jacob Lauritzen Mm-hmm. Basil Chatha And we’ll just build a product that does that. Jacob Lauritzen Okay. So they don’t see an existential threat to their business, whereas the American ones do? Basil Chatha I don’t know if that’s the reason they want a custom build versus not a custom build. I think they both know that this is extremely important and key to their firm’s success and their corporate success. It’s both extremely important. I think it’s just a different way to achieve it. Jacob Lauritzen Okay. Another question I think you might want to bring up is product metrics. How do you know that we’re actually doing something good here? Basil Chatha Yeah. Mm-hmm. Jacob Lauritzen How do you think about that? I’m assuming that’s also related to evals. Basil Chatha 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? Do they come back a lot? We have really good numbers for enterprise software: our DAU over MAU and hours spent per month on the product are extremely high. We also do online evals to generally try to figure out whether we solve the problem. We use a super-cheap LLM judge to have an online metric, and we can use that when we roll out new things. We can compare feature-flag-wise, okay. Basil Chatha Did it improve, or did it catastrophically decline? One thing that might be interesting—and difficult for our business—is that we can’t look at any traces, basically. We can’t look at any data because it’s all super confidential. That’s extremely frustrating to work with because you basically don’t know what people are doing. It’s like, here’s an agent that can do so many amazing things, and I have no idea what people are actually doing with it. Jacob Lauritzen I would’ve assumed you guys signed some sort of agreement with the law firm, and they were like, “Oh, yeah, sure.” Basil Chatha Yeah. Jacob Lauritzen ...with the law firm, and they were like, “Oh, yeah, sure.” Basil Chatha I wish. Yeah, I wish. No, but the thing is, a lot of the data they have isn’t even theirs, right? It’s their clients’— Jacob Lauritzen Oh. Basil Chatha —and it’s super confidential, so we can’t look at it. We have an evals team that’s trying to approximate what we think everyone is doing and build that into eval sets. Jacob Lauritzen Wow. Basil Chatha So that’s just a super annoying kink of the business. swyx Can you paraphrase? For example, ChatGPT has a `/feedback` thing that directly gives you the full trajectory. Basil Chatha Mm. swyx But obviously, that’s not possible for you guys. Basil Chatha Mm. swyx But you could use an LLM to paraphrase the real thing, make a synthetic thing that’s close enough, and change all the names and details, but still— Basil Chatha Yeah. swyx Yeah. Basil Chatha We can’t— There’s always a range, right? If you paraphrase all the way down to three values and pick one of them, then obviously that’s fine. If you just remove the names, then maybe that’s not fine. swyx Yeah. Basil Chatha So we generally pick the safest way. swyx Okay. Basil Chatha We restrict ourselves as much as possible because there should be no risk at all. swyx Yeah, that’s fair enough. Basil Chatha But there are things where we know 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 also classify it into the types of tasks and practice areas, and then we have an idea. It’s something we’re always trying to figure out how to do in a smart way. Jacob Lauritzen Also, on the privacy front, I’m assuming even 2 years ago it must’ve been insanely difficult to get law firms to be okay with this. Basil Chatha Yes. Jacob Lauritzen But— Basil Chatha No. Jacob Lauritzen —how do they think about their data being sent over to Anthropic or, you know? Basil Chatha Yeah. Jacob Lauritzen It must be a huge thing. Basil Chatha All of our infrastructure is on Azure, primarily for this reason. When we started, law firms were like, “AWS? No.” Jacob Lauritzen Yeah. Basil Chatha Like, “No way. We don’t trust AWS.” swyx Law firms don’t trust AWS? Basil Chatha Yeah, yeah. swyx Why? Basil Chatha It’s different now. But they were like, “Amazon, Google—we can’t trust them with any of our data.” So we basically had to host everything on Microsoft because they already have Microsoft 365. Jacob Lauritzen Oh, so they’re okay with Microsoft but not— Basil Chatha Exactly, because they’d already done the security review for all of their documents and Word and everything else. Microsoft is an approved vendor in their mind, so we had to host everything on Azure. That’s changed over the past few years. swyx Mm. Basil Chatha Now people understand that they need to get on the cloud and do all this kind of stuff. There were also a lot more people talking about on-prem back then. That’s disappeared completely. People understand that you should just do it in the cloud, that it’s safe, and that it’s probably safer than what you’re doing. Jacob Lauritzen Yeah. Basil Chatha That’s changed a lot, but I think we can— swyx Yeah, and by the way, it’s only been 3 years, so it’s actually— Basil Chatha Yeah. swyx It’s a huge shift. It’s great. Good for you guys. I don’t expect the legal industry to have somehow ignored this for the last 10 years. Basil Chatha Yeah. I think we needed the AI kick in the butt for everyone to understand that we need to change our ways a little bit. swyx Oh, yeah. Basil Chatha ...our ways a little bit. swyx Okay. Okay. Jacob Lauritzen So, open-source models are getting really good now. How are you thinking about that? Basil Chatha Yeah. We’re thinking about just bringing our clients along on the Pareto frontier. Jacob Lauritzen Yeah. Basil Chatha And the map of all the models—what they’re good at, their latency, their cost, their governance, and their regional availability—how do we optimize across all of that? Some open-weight models are great for certain tasks, and then we’ll use them there. Some we’ll post-train, and some we’ll just use the frontier models. swyx Yeah. You call it model arbitrage. You have different flavors. You did some research on this where you were firmly Anthropic at the start of the year. Grok is improving a lot. Do you want to give an example of a model that wasn’t ranked highly overall, but that you want to shout out as surprisingly good? Basil Chatha Yeah. I don’t think it’s good overall, but one of the early Gemini models is extremely good for certain types of transcription and speaker attribution. We use that for transcription, actually. swyx Oh, so you have a— Jacob Lauritzen Yeah, where are you guys transcribing? swyx Like Granola? Basil Chatha We actually probably will build a meeting thing. swyx Yeah. Basil Chatha But this is just speech-to-speech, speech-to-text, text-to-speech—like any other app that has this. We also transcribe files. If you upload hearings or whatever, we’ll transcribe them, put them into text, and then we can do all of our analysis on them. swyx No ElevenLabs? Basil Chatha No ElevenLabs, for DPA reasons. I mean data processing agreement, I should say. Our data processing agreement has very few vendors on it because we just need to keep it— swyx You just need to keep it fresh. Basil Chatha Exactly. We need to keep it— swyx Tight. Basil Chatha —super tight— swyx Yeah. Basil Chatha —on where any data goes. swyx I think that’s one of the benefits of Gemini and OpenAI, where they’re like, “You come to us; we have most of the things that you need.” That’s actually very valuable. It doesn’t have to be state of the art. As long as it’s mostly good enough for all tasks, then who cares? Basil Chatha Yeah. swyx Like— Basil Chatha Yeah, absolutely. I should also shout out Microsoft’s transcription model. swyx Ah. Basil Chatha They may want— swyx Microsoft Transcribe? Basil Chatha Yeah. swyx Okay. Basil Chatha It’s great. swyx Okay. Basil Chatha It’s better than the old Gemini, from what I’ve seen. swyx Yeah. I think usually all of them are in the top two, top three, top four in terms of the Arena scores, and that’s good enough. Basil Chatha Yeah, exactly. You have all the governance, it’s super scalable, and that’s probably good enough. Jacob Lauritzen At this point, are speech-to-text models pretty much good enough that you’re like, “Oh, one word here or there being off is fine”? Basil Chatha No. swyx It— Jacob Lauritzen No? swyx No, no. Basil Chatha For sure. I’ve done this a lot. swyx Particularly in legal, there are some... We had this thing where, I think it was in Australia, there’s a certain name for a person in court, and it would consistently transcribe it as “condom.” Basil Chatha Oh. swyx Yeah. There are certain things you don’t want there. Basil Chatha I see. Okay. swyx Usually you run an LLM layer on top of it. Then you extract some keywords, and you run the transcription model again with the keywords. That’s kind of my workflow so far. Basil Chatha Interesting. swyx But if you’ve done this at any large scale, you’ll pick up tons and tons of transcription errors on any— Basil Chatha Anything. swyx domain that is not average day-to-day conversation. Jacob Lauritzen Yeah. swyx Yeah, absolutely. If there’s any sort of jargon in there— Jacob Lauritzen Yeah. swyx —it’s gonna be tough. Jacob Lauritzen Yeah. I think Whisper and ElevenLabs still transcribe Claude Code as “cloud clo-code.” swyx Yeah. Jacob Lauritzen And that’s— Basil Chatha Yeah, I’ve actually had that problem. Jacob Lauritzen Very, very common. So that’s how you know there’s a lot more to improve. swyx Yeah. Absolutely. I do want to cover a little bit on the agent product side. We’ve covered a few of the top-level things, right? We’ve already name-dropped Tabular Review, and we’ve name-dropped Intake. 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. Jacob Lauritzen Yeah, yeah, sure. swyx Is that fair to say, though? They’re approximately the big two? Jacob Lauritzen Agent and Tabular Review. swyx Yeah. Jacob Lauritzen And our— swyx And projects. Jacob Lauritzen Probably, yeah. And our Word add-in is also something, because a lot of people work inside of Word, so our Word add-in is huge, and the Outlook add-in too. swyx Yeah. I just want to cover the big ones that everyone must know. Jacob Lauritzen Yeah. swyx So Tabular Review is basically a fan-out across a lot of documents. You can ask the same question across all the documents. Jacob Lauritzen Exactly. swyx It’s collected in a table, and then you work back and forth. Jacob Lauritzen And then you— swyx You can— Jacob Lauritzen Yeah. swyx A million is impressive. What are some other engineering considerations or performance things? What’s hard about this? Jacob Lauritzen Uh— Basil Chatha Really, before we do that, can you walk through the user experience for a lawyer actually using Tabular Review? swyx Okay, so you want us to do a top-level flow? Yeah. Basil Chatha Yeah, like, what are they doing with Tabular Review? Jacob Lauritzen Yeah. Basil Chatha And then we can go into that. Jacob Lauritzen Sure. swyx Yeah. Basil Chatha Yeah. Jacob Lauritzen A good example is due diligence, where it’s like, “We need to review all employment contracts, all supply contracts,” or whatever. So you put 10,000 employment contracts in there, and then— swyx Each cell is one employment contract? Jacob Lauritzen Each row is one employment contract. swyx Okay. Jacob Lauritzen And then for the cells, you ask questions—sorry, per column. The first column might be, “What’s the termination period?” Then it’s going to fill that out for every one: 30 days, or whatever it is. The next question might be, “Is there an IP assignment clause?” The next one might be, “How much do we have to pay them if we fire them?” or “How much are they getting paid?” Then it’s going to fill out the entire thing. You can also just ask the agent to do this. If you drop 10,000 files into the agent and say, “Do due diligence on this,” it will spin up a Tabular Review, run all of them, wait for it to be done, and then analyze the results. It can highlight red flags: the CEO is getting paid an outrageous amount, or there’s a weird bonus structure. Obviously, we need to look at that. The agent can then draft a memo to send to the client, or it can just do the review and have a lawyer—the user—say, “Okay, let’s look at this. Here are the red flags.” It’s also collaborative, so you can comment for other people to look at, et cetera. Basil Chatha And why did you choose that spreadsheet format? Jacob Lauritzen It’s just a lot better to work in. It’s super easy to get an overview of what’s going on and review it. All the stuff we produce also has citations back to source documents, so you can review it easily. If you want to make sure everything’s right, you can highlight cells that have been reviewed or flagged, and you can comment and collaborate. That’s much easier than any other form factor we’ve tried. swyx Yeah. Basil Chatha Mm. swyx I would say that the spreadsheet form factor has a lot of pull in some areas, but somehow hasn’t really spread. Jacob Lauritzen Mm. swyx I find it very weird. Clay is another one on the GTM side that’s very well known for spreadsheets. You guys—I don’t really know if anyone else does a large spreadsheet AI thing. There was V7, which tried to launch. There’s Sheets. Even in the finance domain, I don’t really have a top name that does spreadsheets. Jacob Lauritzen Does this really well. Yeah, no, I agree. If you have fan-out and you do the exact same thing, extracting stuff, it’s such a great form factor to understand what’s going on. swyx Do you find that people must export to Excel, or are they happy to live in your spreadsheet? Jacob Lauritzen People are happy to live there. swyx Do you use AG Grid or your own? Jacob Lauritzen We do use AG Grid. swyx AG Grid. That seems to be the leading one. Jacob Lauritzen Yeah. swyx I mean, they’ve done this for, I don’t know, 15 years. Jacob Lauritzen Yeah, yeah, they know how to. Yeah. swyx Yeah. Jacob Lauritzen It’s a vertical list. swyx Okay, I’m happy on that spreadsheet angle. I think the only other interesting thing for me engineering-wise is the fan-outs. Jacob Lauritzen Yep. swyx Engineers are maybe well-equipped to understand the trade-offs. Before you fan this thing out on a million documents, maybe test it on two. Jacob Lauritzen Mm. swyx Do they do that? Jacob Lauritzen Yeah, they will. Our type of review will actually run the first 10 rows twice. swyx Just check, right? Jacob Lauritzen Yeah. Does this make sense? Did it show us what we thought it was going to show us? That’s really good. It’s also good for people building this to iterate quickly on the first 10 rows until they’re getting the results they want, and then they can go ahead. swyx Yeah. I’m happy to move on to the next thing: Intake, which is your Slack bot. Jacob Lauritzen Yeah, yeah. swyx Everyone has a Slack bot. What’s different about yours? Jacob Lauritzen Ours is just legal-specific. What happens with ours is that it’s not actually— We’ll probably also build one that’s just an interface to the agent, but this one is specifically to kick off an agent that then adds a task to our list. We have this Lists thing, which is like Linear—that’s the closest equivalent. It adds it to a specific intake list. Then lawyers and agents can go into Legora and see the things people are sending to us as a law firm or as a legal team in a big corporation. We can kick off agents for them, collaborate on them, and mark them as done. Then it gets sent back in Slack. It’s not just kicking off an agent. It’s more of a storefront thing: “Hey, here’s the ticket. I want this thing reviewed. Okay, now here it is. It’s back.” No one needs to change anything, and the legal team just sits in Legora and manages the agents there. swyx I think the data structure for this kind of thing is really interesting because it’s basically the inbox for all these kinds of queries that can potentially translate into a thing, into something else. Is it hard to integrate all these with the other features, or do you just not worry about it? Jacob Lauritzen No, it’s not. I think we have some primitives that work really well. Lists is a great primitive because it’s extremely flexible. It’s almost like a Notion database. swyx You could treat it as a Notion database. Jacob Lauritzen It’s like a Notion database, so you can configure it for whatever you want. We invest a lot into making it scalable and work really well. You can have triggers and automations on them, and it’s a great glue to tie everything together. You can kick off an agent run based on a list if something happens, and then it comes back and populates a field, adds new documents, or whatever it is. Jacob Lauritzen And so, just like you might coordinate a bunch of coding agents with Linear or some other task management tool, we can do something similar with Lists. Agents can create lists, and lists can create agents— swyx Wow. Jacob Lauritzen —and agents can read lists, so it’s like the agent swarm comes alive. swyx Yeah. Do people get excited or overwhelmed by that? I feel like this is basically end-user programming. Jacob Lauritzen Yeah. swyx You can let people set up crazy automations. Some people get super obsessed by it, and they become influencers. It’d be cool to have Legora influencers. Jacob Lauritzen Yeah, right. Clay has influencers. swyx Is that worth it? Too overcomplicated? Jacob Lauritzen We need the flexibility, even if we don’t actually expose it to the end user. Even if this were all internal, it’d be a really fast way for us to use people like our legal engineers to build a lot of products extremely quickly. You can build custom fund management dashboards on Lists with your own generative UI, and then you have a new product that some people are going to love. We can have a marketplace of specialized products that we can scale super quickly, because all our legal engineers can build new ones. If they’re out with a client and hear, “Oh, you want your own? Easy. We’ll just build one for you.” It’s a little like having Lovable inside Legora. And if we don’t want to expose it, that’s also how we build our own custom features. We made another acquisition in the UK called Wexler. They’re doing fact intelligence, mostly for litigation: you upload a million documents for a lawsuit or whatever, and then we extract facts with named entities, dates, and so on. Once you have all the facts, you can hold them up against each other and see which ones are corroborated and which ones are in disagreement. swyx Yeah. Jacob Lauritzen That’s extremely powerful, because then you can also transcribe a court hearing and say, “Oh, he said this thing, but actually the email over here says that he wasn’t there.” If you see it live, it’s so cool. swyx Yeah. Jacob Lauritzen We can build that on this primitive, too. We can build a lot of really cool things on this one primitive. That’s how we think about it, because as we scale the company, we have to solve so many things. I think a lot about how we build a core primitive that we can scale across many different end products and use to create customizable— swyx Mm. Jacob Lauritzen —experiences. swyx Okay. So what core primitives do you have? Let’s just restate them for people. Jacob Lauritzen Lists is a core one. swyx Lists. Jacob Lauritzen Yeah. swyx Projects. Jacob Lauritzen Super configurable. Projects are basically containers of files—file systems. swyx Yeah. Jacob Lauritzen The agent, of course, which you can kick off and run in very different configurations. swyx Do you have a name for the agent, by the way? Jacob Lauritzen No, we don’t. swyx Just Intake? Jacob Lauritzen No. swyx Okay. Jacob Lauritzen You mean, like, did we call it Leia or give it a name? No. swyx Ooh. Leia would be cool. Jacob Lauritzen Yeah. swyx People used to talk about Leia as a named entity, but we stopped that. Jacob Lauritzen Okay. Maybe I’ll bring it back. swyx It might be confusing. I don’t know. Jacob Lauritzen So, Lists, Agent, Tabular Review. We’re considering whether that’s actually an instantiation of something. You can take this as far down as you want, right? But those are probably the big ones. Basil Chatha Yeah. I actually wanted to talk a little bit about FTEs, because this sounds kind of like that. I think Max has talked about that a little bit. When you onboard a big customer, you want to get them value ASAP so that they stay on Legora. Jacob Lauritzen Exactly. Yep. Basil Chatha How has that evolved? When did you guys start that forward-deployed team? Jacob Lauritzen We hired our first forward-deployed engineer, our first hire in New York. They were also a YC founder. That was maybe six months ago. I’m not actually sure. Basil Chatha Are they considered legal engineers, or no? Jacob Lauritzen No. Basil Chatha Okay. All right. Jacob Lauritzen They’re true engineers. But I do think about how we enable that at scale. A really core thing is: how can we empower our legal engineers? How can we empower our power users and legal engineers to customize the product in a powerful way? Of course, we’ll still have forward-deployed engineers helping out with custom integrations, scoping and figuring out what’s possible, and feeding all of that back into core product development. That’s how I think about it. It’s almost a first-line, second-line defense— Basil Chatha Yeah. Jacob Lauritzen —where legal engineers should be able to customize a lot of things and build a great experience. Where they can’t, or where we need to make core product changes or custom integrations, we have forward-deployed engineers who cycle in a little behind them. Sometimes they’ll just work on the product, and sometimes they’ll work— Basil Chatha Yeah. Jacob Lauritzen —with clients. Basil Chatha Can you walk through an example? You’ve just got this new client. What’s step number one? Do you say, “Okay, we have a forward-deployed engineer for you. They’re going to build some kind of product for you”? How does that work? Jacob Lauritzen It’s very different from client to client. Basil Chatha Yeah. Jacob Lauritzen If it’s a big client and they’re super engaged, they have all these dreams of things they want to do. Typically, they’ll have already tried to build something and failed, and they’ll say, “This is a problem we’d like to solve.” Then we’ll staff them with legal engineers and potentially a forward-deployed engineer, depending on what they need. We’ll say, “These people will come and make you successful. They’ll sit with your lawyers, teach them how to use it, figure out your current workflows, and build them into Legora.” Some of that will just involve a legal engineer, and some of it will require a forward-deployed engineer. Basil Chatha What’s the separation, if you could talk about that a little bit? Jacob Lauritzen Legal engineers configure the product as a power user would. Basil Chatha Okay. Jacob Lauritzen They don’t write code. Basil Chatha Yeah, yeah. Jacob Lauritzen A forward-deployed engineer writes code into production, basically. I guess that’s the— Basil Chatha Yeah. What kind of background do forward-deployed engineers normally have? Jacob Lauritzen Regular engineers. Basil Chatha You said YC founder. Jacob Lauritzen Yeah. Founders, regular engineers. They’re all— Basil Chatha You have, like— Jacob Lauritzen Yeah. Basil Chatha Dee was your— Jacob Lauritzen Yeah, exactly. Basil Chatha —was the one with two YC companies and worked on search at Meta. Jacob Lauritzen Dee was our first, yeah. Basil Chatha Okay. That’s a high bar. Jacob Lauritzen She’s awesome. She was the first boots on the ground in the US. Basil Chatha What are some examples of workflows or things these people are building for clients? Are there a couple of use cases that all the law firms say, “This is the first thing our FDEs are going to do when they go in”? Jacob Lauritzen It’s very different. Basil Chatha Okay. Jacob Lauritzen There are some core workflows everyone has that we can just build in Legora. That could be anything from how we handle certain types of NDAs. You activate it, and it’s more like skill-building for agents. For most of the FDEs, it’s more that there’s something we can’t do yet: we need more flexibility in some of the primitives, or we have a really complex system we need to integrate with. Then they’ll go out and build the integration against our APIs, and maybe expand our APIs to make it work. Basil Chatha How does the legal structure work there? You said you guys can’t even work on deals. Jacob Lauritzen Mm. Basil Chatha ... yourselves can’t even work on deals. Jacob Lauritzen Yes. Basil Chatha So, how do they work on client projects? Jacob Lauritzen You mean the law firms? How do they work on client projects? Basil Chatha Sorry. How do your FDs— Jacob Lauritzen Yeah. Basil Chatha ... work on client projects if they’re not— Jacob Lauritzen They don’t touch the data, still. Basil Chatha Oh, okay. Jacob Lauritzen They’ll just build the system. Basil Chatha Okay. Jacob Lauritzen But they’ll also be onboarded like an employee sometimes. They might get a laptop and everything, if they need to. Basil Chatha Like, at the law firm? Jacob Lauritzen Yeah, yeah. Basil Chatha Oh, wow. Jacob Lauritzen If they need to. Basil Chatha Interesting. Jacob Lauritzen That doesn’t happen very often, because usually they just build an integration and it kind of works. But they can, if they need to. Basil Chatha And you only onboard FDs into a customer, I’m assuming, if they’re a certain size. Jacob Lauritzen Yeah. Yeah. Basil Chatha Okay. Jacob Lauritzen It needs to make sense. Basil Chatha Yeah. Jacob Lauritzen Because our FDs can also work on the core product, right? So it’s a constant prioritization thing. Basil Chatha Oh. Jacob Lauritzen Is there a rule? I guess, does every—Palantir famously had four days you spend on site. Basil Chatha Mm. Jacob Lauritzen One day you come back and— Basil Chatha Yeah. Jacob Lauritzen ... contribute back to products. Anything like that? Basil Chatha No, we don’t— Jacob Lauritzen Nothing like that? To be fully honest with you guys, it’s still early days in a lot of this. Yeah. Basil Chatha I mean, where do you see it headed over the next year? Jacob Lauritzen I do think it’s going to be more like Palantir, maybe not exactly. I think we’ll have a larger, constantly circulating group of FDs who might sit with a client for two months or whatever to build out one thing, and then they go to the next one, et cetera. I do imagine us rolling in with legal engineers and forward-deployed engineers to work on specific projects. Basil Chatha Hmm. Oh. Jacob Lauritzen Yeah. The API business is actually interesting, like you said. Basil Chatha Mm. Jacob Lauritzen Because that’s another role you can have, where you’re the CTO or maintainer of the Legora platform. Basil Chatha Yeah. Jacob Lauritzen Right? Basil Chatha Yeah. Jacob Lauritzen We’ll offer everything we have in the Legora web app— Basil Chatha Yep. Jacob Lauritzen ... as an API, and then you can use whatever. Is that a promise you make, or— Basil Chatha That’s not something we’re promising now. Jacob Lauritzen Yeah. Basil Chatha Um— Jacob Lauritzen We do have APIs you can build against— Basil Chatha Yeah. Jacob Lauritzen ... but not the entire surface of the product. That’s the curious thing: is that the strategy? Basil Chatha Hmm. Jacob Lauritzen Obviously, some people will love it because— Basil Chatha Yeah. Jacob Lauritzen ... I don’t have to learn a new tool. I can just use the existing tool I have. Basil Chatha Yeah. Jacob Lauritzen Right? And then I just— Basil Chatha Yeah. Jacob Lauritzen ... install Legora, for example, with the Word document stuff. Basil Chatha Hmm. Jacob Lauritzen Other than that, I do think you have to maintain it. Exactly. That’s been my thing, and that’s why we’ve tried not to do it. We haven’t had APIs. I mean, we started our APIs about six months ago. We fought it for a very long time, mostly because we move so quickly in the product, and I don’t want to be slowed down by having to maintain all the API versions for a data model that we’ve changed. Now we’re bigger and things are different, so it’s a cost we can take on. But when we were 20 engineers, we moved so quickly that we couldn’t do this. swyx I’ve toyed with this. It’s generally good for all companies to have a platform team and a product team. You have one product team, but you can easily spin up a second one as long as the platform isn’t too tied to a product. Jacob Lauritzen Yeah. Yeah, yeah. swyx A very simple example is a web app and a mobile app, right? Or a web app, a mobile app, MCP, and other integrations. Then your FDEs are just one more client to the overall platform anyway. Jacob Lauritzen Yes. And I think even the agent, you can think about it this way. There’s a harness team that runs the agent, and then you can build a product around it with skills, automations, and whatever else. swyx Yeah. Jacob Lauritzen Um— swyx This is very famously the Amazon Web Services mandate. Bezos was like— Jacob Lauritzen Everything’s an API. swyx ... “Guys, no more backdoor access. You only offer other teams the same APIs you offer customers.” Jacob Lauritzen Mm. swyx If you don’t have it, you build it. Jacob Lauritzen Yep. swyx And then the customers also get it. Jacob Lauritzen Yeah. I think that’s also changing a little bit. A lot of APIs now—one thing we’re toying with is whether the agent can be the API. I know it sounds weird, but for some of this stuff, what they actually want to do is trigger certain things to happen. For some of it, you could just trigger the agent and ask it to do the thing. I’m not saying we’re doing this, but it’s something I’m toying with: could you just trigger the agent to do this? Obviously, it’s way less efficient than having an API that you always hit. But I’m toying with how much of our product can just be the agent versus all the other stuff. swyx Well, you know, unbounded execution, costs, and latency— Jacob Lauritzen Yeah. That’s the— swyx Is that the only drawback? Jacob Lauritzen Yeah, and then determinism. Maybe one or two times out of a hundred, it’s going to do something whack that we didn’t want it to do. swyx We’re going to get into harnesses and model fine-tuning in a bit, but I think there’s a product question about restraint—about what you don’t do. You could do all that, and obviously there’s a prioritization issue. Are you at the point of saying no to most things and only doing a small number of things, or do you want to do more things and just need to hire 100 people? Jacob Lauritzen I was very strongly in favor of the first thing for a very long time. Let’s just say no to everything and keep the engineering team small. I’ve said this before, but in one of our presentations, after I’d been at Legora for half a year, I put up this slide of the 300 Spartans from the movie, and I was like, “We’re just going to be 20 engineers for the rest of the company’s history, and 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 want to do that, but in the real world, we’re in fierce competition. People want so much stuff. I could be a puritan and say, “No, we have to stay 20 people, and we can only build whatever,” but then we lose, and people go elsewhere. So we have to build more. My job is to figure out how to build a system where we can build a lot, but the customer feels like we’ve built so much stuff when we’ve actually only built a few things. That’s how I think about my job right now. Speaker 0 Yeah. I mean, primitives, right? Basil Chatha No, exactly. I think that’s really powerful. Speaker 2 Do you test new products, just to see if there’s any pull? Then do you decide, “No, let’s just focus on our main thing”? Basil Chatha We haven’t made—I mean, we’ve made certain strategic bets, but we haven’t tried anything we don’t already have a lot of confidence in. Mostly because we have a mountain of demand: “We want all of these things.” It hasn’t really made sense for us to say, “Hey, maybe this thing could work,” because so many people are asking for the other things. So we mostly build those. Sometimes we’ll disagree with clients and say, “Actually, I think this thing over here will make a lot of sense strategically,” and then we’ll try to build that anyway. Speaker 2 Strategically for you? Basil Chatha Yeah, exactly. Speaker 2 So what are those things? Basil Chatha Or the industry. One of those things was the agent, actually. No one was asking for, “I want the assistant I’m using to have more agency and do things without me asking it.” No one ever did, but we were 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. We thought the industry was moving toward collaborating inside the place where you’re working, which is Legora, rather than in emails and text messages. So, yeah, there are a few of those. Speaker 2 And then once you say, “Okay, yeah, we want you guys to use agents,” I’m assuming it’s going to take a lot for people internally at the law firm to actually learn how to do that. Basil Chatha Mm-hmm. Speaker 2 And so that’s— Basil Chatha Yep. Speaker 2 —where you say, “Hey, FDEs, go in there and teach them what they can do”? Basil Chatha Yeah, legal engineers, mostly— Speaker 2 Oh, legal engineers. Basil Chatha Yeah, yeah. Speaker 2 Okay, that makes sense. Basil Chatha Some people call them forward-deployed legal engineers, if you want, but that’s essentially what they are. Then they go in and help structure their workflows around the capabilities of the agent. Speaker 2 You guys said previously—I think Max said this—but that early on, specifically, you weren’t fine-tuning your own models. Is that still the case? Basil Chatha Yeah. We haven’t fine-tuned any models up until now. I think that in the past few months, open-weight models have become extremely capable, so we’ll do it for certain tasks where we think there’s a huge delta between what a frontier model can do in terms of cost and latency and 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 for those queries very quickly and cheaply, with low latency. Speaker 2 So you’re post-training them specifically to be better at searching— Basil Chatha Very specific, bounded tasks. Yeah, exactly. Speaker 2 Okay. Basil Chatha Yeah, yeah. We’re not trying to train our own foundation model to be the main agent. I don’t think that’s something we’ll win at, versus Anthropic, most likely. Speaker 2 Yeah. There’s still a lot of search and retrieval research, or RAG research, to do that’s maybe less glamorous. It’s not even always model training; sometimes it’s just architecture and pipelines. You did a case study with TurboPuffer, but do you do late interaction? Basil Chatha Yes, absolutely. Yeah. Speaker 2 You do that? Basil Chatha We actually don’t do that. Speaker 2 Right. Basil Chatha But you’re completely right. There’s one guy on the team, Song, who really cares about search. He comes to me all the time and says, “We should do these things. There are these new embedding models, and we can do ColBERT and late interaction.” He actually talked to the TurboPuffer team to get them to build multi-vector support so we could do these types of things. But there’s loads of low-hanging fruit, generally, even before models. And even in the harness, if you just want to create a better output for our clients, there’s so much stuff we can do that has an immediate impact before training models. Speaker 0 Yeah. Speaker 2 What makes a good harness for the legal industry, I guess? I’m assuming you guys are making your own custom harness. Basil Chatha Yeah, of course. Speaker 2 So, yeah. Jacob Lauritzen The way we edit files is important. The way we do analysis is important. The way you do legal research is all baked into it. You might have a problem come up, or see something, and then it knows how to do the legal research to figure out what the answer is and what the precedent is. That’s all very important. And then, of course, there’s all the governance stuff around it as well. Speaker 2 Yeah, it seems like search is probably the most important tool you’re customizing, because if you can’t pull down the right information— Basil Chatha Yeah, and then you’re— Speaker 2 Yeah, yeah. Basil Chatha —you’re screwed. Speaker 2 You’re screwed. Basil Chatha Yeah. I think it’s search— Speaker 2 You guys are searching a lot of documents— Basil Chatha —and analysis. Speaker 2 Yeah. Basil Chatha Yeah. It’s search, analysis, and drafting, probably. Drafting huge contracts is actually not super trivial. Speaker 2 What about it isn’t trivial? Basil Chatha If you’re drafting a huge contract from scratch, you have to find precedents. How did we do this previously? Do we need this type of clause or not? Speaker 2 A specific law firm—how did they do it previously? Basil Chatha Yes, yeah. I am the law firm, and I’m about to draft a huge whatever. An NDA is very simple, but there are contracts that are way more complex, and then you need to find the right precedent first. Lawyers don’t just sit and start typing stuff. They figure out which clauses they’ve used in similar deals, and “similar” can mean a lot of different things, as I’m sure you know in search. It could be the same industry, the same type of company, or whatever. You need to identify the right precedent. You might have multiple documents and then try to figure out which part to take from which document. That’s actually nontrivial. So it’s essentially also a search problem. Speaker 0 Which model’s best at drafting? Jacob Lauritzen I was told I was far from this yesterday, but Fable and Opus are definitely extremely chatty. I’m sure you guys have noticed this. They’re very verbose. Speaker 0 So that’s not good. Basil Chatha That’s generally not good, no. Speaker 0 Okay. Jacob Lauritzen Astra is pretty good at writing— Basil Chatha I noticed Astra is pretty good at writing. Jacob Lauritzen Yeah, Astra is pretty good at writing. Speaker 0 And is it promptable? Basil Chatha It’s much more concise. We can do certain things, but I think the chattiness and verbosity are actually a little bit difficult for us to address. Speaker 0 Wow. Jacob Lauritzen Let’s see, but the next model from Anthropic will probably be much better at this. Astra is actually very concise. Speaker 0 Yeah, yeah. Speaker 2 And I assume they all have a Slack channel with you, and you’re telling them this, right? Basil Chatha Yeah, exactly. Speaker 2 Like, this is— Basil Chatha Yeah, we talk about it. Speaker 2 —this is not news to them. Basil Chatha No, no, they know this. Speaker 2 All right. Basil Chatha The other thing I really care about is hallucination. Speaker 0 Mm. Basil Chatha Do they make stuff up? We have a citation system where we basically check that what they’re writing has a link. The user has a link they can click, and it highlights with a bounding box in the PDF where the information was taken from. We can make sure that what it says is always citable somewhere, even multiple layers down. If the agent writes something based on a tabular review, it can cite the cell or the row in the tabular view. You can click multiple layers down and validate it all the way up. Speaker 0 Yeah. Speaker 2 Are you finding that lawyers are verifying that these citations are correct or not? Basil Chatha No. Speaker 0 Initially, some of them were. Speaker 2 It’s kind of like law review, but now are you actually doing it? Basil Chatha Yeah, exactly. It’s the same thing. Speaker 0 People ship hallucinated links to the Supreme Court, and they don’t care. Basil Chatha That happens, yeah. I think it’s like coding. You have engineers who just don’t give a shit and send agents, and you have people who sit and read every comma. It’s the same distribution overall. Speaker 2 There’s just so much. How can one human do that, right? Basil Chatha Yeah, but I think they probably just, like we know in code review, know what to look for. Basil Chatha Like, what is the system or whatever? I think they also know, “Okay, this is the thing that’s important. Let me double-check these things.” Speaker 2 Yeah. Basil Chatha Then these sound reasonable, so it’s probably fine. Speaker 2 Okay. Interesting. Speaker 0 Just like if you receive something from a junior lawyer, it’s the same thing you do, right? You think, “I should double-check this,” and then this probably is fine. Any other elements of legal reasoning—or, what’s the legal frontier that models aren’t good enough at yet, that you want from the next generation of models? Basil Chatha Nothing I can think of specifically right now. Long-document reasoning is still difficult. Speaker 0 Long, like million-token contracts or something? Basil Chatha Yeah, exactly. You have a huge contract, and you’re making edits across it. That’s difficult for a model to do today. You have to remember that you changed all these things up here, and that the definitions changed, the ordering changed, and whatever else. Speaker 0 So the simplest approach would be one-shot: you feed everything in, then get a one-shot output. Basil Chatha Yes. Speaker 0 You don’t do that. You break it up into chunks and orchestrate edits. Basil Chatha Yeah, exactly. Speaker 0 This is one of those fun things about being part of this industry, right? Our Word add-in has gone through MapReduce, and we’ve changed. There was one big one, and there was one big one in multiple sites. We keep changing the scaffolding we build around the models as they change. swyx Yes. I’d say I’ve recently shifted from MapReduce to throwing everything into context. I do a lot of news reporting, obviously, because of what I do. Jacob Lauritzen The entire thing. Yeah. swyx And now it’s— Jacob Lauritzen Because now they’re— swyx —it’s better. Jacob Lauritzen They’re good at it now. swyx Yeah, exactly. But it’s also different. We had this problem with search, where you’re searching for certain things in huge contracts. You can use MapReduce, but if you’re summarizing something, it might lose important nuance between the chunks, essentially if you just summarize the individual parts. We’ve been dealing with this problem. We can do 2 types of search. We can also do the other kind, where you need to have reasoning in the different steps in between. I’m trying to think of a really good example. There are some documents where they talk about something at length over, let’s say, 2 pages, and each individual chunk isn’t necessarily relevant to the search term or what they’re trying to figure out. But together, it’s extremely relevant. These are some of the non-trivial problems. Basil Chatha 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? These are real contracts. swyx Exactly. Basil Chatha So do you ever ask them, “Can you make example contracts that are similar to your real ones?” swyx We do, yeah. We can receive feedback from them, if they’re willing to engage. Jacob Lauritzen Get the company— swyx Yeah, exactly. Or they’ll say, “This is super important to us, and it’s not working well.” Then we’ll say, “Okay, great. Can you anonymize the documents?” And then, whatever the problem is, if we can recreate it, we can fix it. Jacob Lauritzen One version of this is that you buy a law firm, which some people are considering. swyx Yes, but there’s some stuff around whether their data is actually their data or the client’s data. So if the clients are all gone, then maybe it’s fine. I actually don’t know. Jacob Lauritzen Interesting. swyx But, yes, it’s a way to get a lot of data. Jacob Lauritzen Yeah. People like Google are buying Spirit Airlines. swyx Google, exactly. Yeah. Jacob Lauritzen Right? And, like— Basil Chatha Say what? Jacob Lauritzen Yeah, they bought— swyx Yeah, they bought the—yeah, for like $10 million or whatever. Jacob Lauritzen Oh, the data. swyx Yeah. Jacob Lauritzen If you have a failed company, you still have your Slack. You can sell your Slack. I think there’s a YC company that buys your failed company. swyx Yes, there is. Jacob Lauritzen Yeah, because it’s just like, “Oh, I just want real—” swyx Yeah, people— Jacob Lauritzen “—people doing work.” swyx Exactly. Jacob Lauritzen And then just pull stuff out. swyx Exactly. The problem with buying a law firm’s data is that you get all the inputs, the real inputs, which is great. The outputs are a little more difficult, because you just get their end result, and it’s difficult to figure out how they got there. You basically have to reverse-engineer it. In our product, when we get real traces from real use cases, it’s extremely high-value. But if we just get an output and don’t know if it’s good or bad, or how it was created, it’s a little difficult. Jacob Lauritzen We’re going to wrap up soon. The last thing I’ll point people to is that there’s also a lot of alpha left on embeddings. If you’re doing a RAG-heavy workload and you’re just looking at MTEB and taking the top model, you’re leaving a lot on the table. You should look at Voyage or some of the custom embeddings. You’ve looked into this. swyx Yeah, absolutely. Jacob Lauritzen Basically, don’t take default embeddings. Even if they’re OpenAI embeddings or Gemini embeddings, customize your embeddings. swyx Yeah. Jacob Lauritzen Right? You support that? swyx Yes. I think that’s right. The only thing is you need to make sure they’re multilingual. We serve so many languages, so that’s going to be one of the problems. Jacob Lauritzen I mean, Europe is king of this. swyx Yeah, exactly. Jacob Lauritzen Is Mistral helpful there? swyx No. Jacob Lauritzen Ooh. Basil Chatha Not yet. They just raised a ton of money, right? So maybe. Jacob Lauritzen Yeah. swyx Let’s see. Jacob Lauritzen You guys better be Europe’s champions. swyx They also raised a ton of money a year ago. I don’t know. I think we need way more model companies out of Europe. Jacob Lauritzen Yes. ### The Next Two Years Of Law Basil Chatha I just wanted to ask what predictions you have for the law industry over the next year. Jacob Lauritzen We asked a little bit about that earlier. I’ll modify it to your second question: In 2 years, will lawyers do their work inside Legora, or will they use other tools like Claude or ChatGPT and call Legora, like through an API function? swyx Yeah, yeah. I think both. It really depends. If you’re a big enterprise, you might have Claude or Copilot, and then you’ll… I think it’s similar to 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 because it’s simpler and better. Basil Chatha It kind of reminds me of OpenEvidence for medicine. You’re basically that for law. swyx Exactly. Jacob Lauritzen In coding, it’s gotten to a point where the labs will cut you off for competing with them. This has happened twice. swyx Yeah. Jacob Lauritzen Do you think that will happen in law? swyx No, I don’t think so. Jacob Lauritzen Yeah. swyx I think— Jacob Lauritzen Because they’re releasing legal-services products. swyx Yeah, they are. We obviously talk to them a lot, but it’s also like, “Hey, are you going to…” What’s— Jacob Lauritzen Your sales reps will say no. They don’t make the call. swyx Exactly. That’s not their call to make. Jacob Lauritzen Right? And they often don’t even know 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 enterprise knowledge work generally, that legal has to be part of that, just like data analytics has to—yeah. swyx —and sales and marketing and finance. They have to do things that are good there, but they’re never going to go as deep as we are. If Claude takes small corporate clients and they do some of their legal work via Claude, that’s great. That’s fine. But if you’re doing a $400 million M&A transaction, you’re going to want Legora. Basil Chatha I had kind of an unrelated question. I’m curious: are you guys going to law schools and getting them to teach Legora in classes? swyx Mm-hmm. Basil Chatha How does that work? Are you guys doing that? swyx Mm. Basil Chatha Like, are you seeing law schools changing their curriculums a lot, or not really? Jacob Lauritzen I don’t know. I wouldn’t know, actually. Basil Chatha Yeah. Interesting. Jacob Lauritzen I would actually do it— Basil Chatha I have to— Jacob Lauritzen —a different way. You should do scholarships for law school for CS majors, for engineers. We’ll cover your— swyx After you’ve done CS— Jacob Lauritzen Yes. CS plus some software experience, and we’ll put you in law school. swyx Yeah. Jacob Lauritzen We’ll cover it. Basil Chatha Or you could do the master’s-plus-JD programs. Jacob Lauritzen Yeah. Basil Chatha I mean, a lot of people didn’t do CS as undergrads, so then they do a master’s just to get caught up. Jacob Lauritzen Yes. swyx Mm. Jacob Lauritzen Yeah. I don’t see that as often. swyx I don’t— Jacob Lauritzen Yeah. swyx Yeah. Jacob Lauritzen People do JD/MBA. That’s a thing. swyx Yeah. Jacob Lauritzen But JD/CS, I haven’t seen it. swyx Yeah, it happens. Jacob Lauritzen Yeah. Overall, super impressive progress. Congrats on all your success. Are you still going to keep up the pace? swyx Absolutely. Jacob Lauritzen Yeah. And I think you’re hiring in San Francisco, New York— swyx We’re hiring in New York, Stockholm, and London for engineering. Jacob Lauritzen Yeah. swyx For all other roles, we’re hiring everywhere. Jacob Lauritzen How many people do you have in New York right now? swyx About 100. Jacob Lauritzen Okay. And how many are you planning to have in New York? swyx In New York? Jacob Lauritzen Yeah. swyx Generally? Jacob Lauritzen Let’s just say generally for engineering. swyx A lot. Jacob Lauritzen As many as you can? swyx I know. It’s aggressive, yeah. Jacob Lauritzen Cool. swyx I mean, that’s the home of corporate law, as far as— Jacob Lauritzen It is, yeah. swyx —as M&A is concerned. Jacob Lauritzen New York is— swyx So, yeah, I’m looking forward to you buying a law firm and becoming— Jacob Lauritzen Yes. swyx Yeah. It’s super exciting. I think every industry, especially the top doctors, lawyers, and coders, they all have to have two or three agent labs that just— Jacob Lauritzen Yes, I agree. swyx —and sort of dominate the space. Jacob Lauritzen Yeah. swyx So you guys have a great market. Good. Jacob Lauritzen Yeah, I think so. swyx And I think it’s only going to get much bigger as law changes and becomes more available to more people. Jacob Lauritzen Yeah. We’re already way over, but the problems you work on are very much frontier knowledge work. swyx Yes. Jacob Lauritzen You know? swyx Yeah. Jacob Lauritzen Unless you’re literally doing science—Navier–Stokes and science—most work basically converges to legal. swyx Yeah. Jacob Lauritzen Yeah. It’s all legal in the end. swyx Yeah. Hiring, finance, everything—I just have to consult my lawyer. Jacob Lauritzen Yeah, I know. Which is why I think it’s a really exciting thing to work on, because modern society runs, in some way, on legal. swyx Yeah. Yeah. Jacob Lauritzen Cool. swyx All right. That’s it. Jacob Lauritzen All right. swyx Thank you. Jacob Lauritzen Cool. Thank you. swyx Thanks.