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

1. 0:00 – 0:40

   Cold open

   1. SWswyx0:00

      People were asking us about Mythos and everything, even though I think realistically a lot of legal work does not require Mythos-level intelligence. Paralegals, gone.

   2. JLJacob Lauritzen0:08

      Yeah.

   3. SWswyx0:08

      Junior lawyers, gone. I don't need them. [laughs]

   4. JLJacob Lauritzen0:10

      Um, that's actually not what we're seeing. And we had one problem where, like, it wouldn't cite properly, and so we were like, "Next model release solved." It went from like [laughs] 70% to 99%. It's just like we did nothing, and, like, great.

   5. SWswyx0:20

      But if you're doing a, you know, $400 million M&A transaction, you're gonna want Legora.

   6. JLJacob Lauritzen0:24

      We're just gonna be 20 engineers for the rest of the company's history, and, like, we're gonna beat everyone who's much bigger. And we're 100 engineers now, and it feels like we're way too small. 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.

   7. SWswyx0:36

      [ on-hold music]

2. 0:40 – 1:05

   Meet Jacob Lauritzen, CTO of Legora

   1. SWswyx0:40

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

   2. JLJacob Lauritzen0:45

      That's fine. Yeah.

   3. SWswyx0:46

      Lauritzen.

   4. JLJacob Lauritzen0:46

      That's okay.

   5. SWswyx0:46

      I'm not super sure that how-

   6. JLJacob Lauritzen0:48

      And it's Danish. It's Danish, yeah, exactly.

   7. SWswyx0:49

      Does it have a special history meaning?

   8. JLJacob Lauritzen0:50

      It just... No. Sen is like sun, son of.

   9. SWswyx0:53

      Son of Laurits.

   10. JLJacob Lauritzen0:53

       So it's like you have son, and yeah.

   11. SWswyx0:54

       [laughs]

   12. JLJacob Lauritzen0:55

       So son of Laurits. That's my name. [laughs]

   13. SWswyx0:56

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

3. 1:05 – 1:54

   Starting out as underdogs in a Stockholm basement

   1. JLJacob Lauritzen1:05

      Yep.

   2. SWswyx1:06

      And, uh, y- you said something at the start in our pre-show that I thought was really interesting. You said that your origin is very European-

   3. JLJacob Lauritzen1:12

      Mm-hmm

   4. SWswyx1:12

      ... uh, even though obviously you're expanding in New York and SF. What feels different about your culture?

   5. JLJacob Lauritzen1:17

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

4. 1:54 – 4:12

   How Legora grew from ChatGPT with Swedish law into a legal agent

   1. SWswyx1:54

      I kinda wanna start by going over your guys' product 'cause I feel like with a lot of these, like, legal products, you know, they're kinda like under wraps. Like, you know-

   2. JLJacob Lauritzen2:02

      Yeah, sure

   3. SWswyx2:02

      ... you're not supposed to, like, show it. But, um, yeah, if you could just talk about, like, what does the product look like and maybe, like, how did you guys get there? Like, like, what have been the product iterations that got you-

   4. JLJacob Lauritzen2:11

      Hmm

   5. SWswyx2:11

      ... to where you are today? I think that would be really interesting.

   6. JLJacob Lauritzen2:13

      Yeah, absolutely. The way everything started was ChatGPT with a Swedish loss-

   7. SWswyx2:19

      Okay

   8. JLJacob Lauritzen2:19

      ... search tool in it. That was literally the entire everything. And so that's where we started. We started with legal research, which is, like, a huge market basically in the world where, um, lawyers spend a lot of time figuring out what are previous cases that look like this. What's the legal precedent? Like, is this, you know-- what have previous people done in these situations? That's extremely important. Um, and so that has always been part of our product. Basically, we started from, like, an, an agent you could ask questions, then it would query loss. That was the very simple beginning. Um, and then from that it's expanded, and so it's expanded in, like, what can the agent do? It, it will now, uh, you know, draft a lot of stuff really well. It will edit Word files. It will, you know, move your files away, organize everything, um, run really complex analyses. Um, and we've added just a bunch more features to it. So one of our features is called Tabular Review, which is, um, now a name that's being used in industry, [laughs] and we're very happy to see Claude for legal using-

   9. SWswyx3:11

      [laughs]

   10. JLJacob Lauritzen3:11

       ... our terminology for what they're building. [laughs]

   11. SWswyx3:12

       Ooh, we gotta talk about that. We gotta talk about that.

   12. JLJacob Lauritzen3:15

       Which is essentially, like, a way to just bulk extract and bulk review many, many, many, um, 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, um, helping orchestrate the work a lot more than we were just even a year ago. So we have different sort of-- We have a, a thing called Lists, which is s-sort of like Linear for us. And, um, we have Intake, which is a way to collaborate with, um, clients. And we have, um, Portal, which is also sort of a way to collaborate, you know, lawyer to lawyer, client to lawyer, lawyer to agent, agent to agent maybe. [laughs] We're, we're spending a lot of time there 'cause, um, there's just frankly the way that you work with a lawyer ten years ago or maybe even today is, is really painful, and there's loads of room to do that-

   13. SWswyx4:06

       [laughs]

   14. JLJacob Lauritzen4:06

       ... in a much better way, to be honest. And so those are, like, I think the two things. It's, it's doing the work, and it's also, like, orchestrating the work.

5. 4:12 – 5:23

   The switch from assistant to agent

   1. SWswyx4:12

      When did you guys start doing or building the agent?

   2. JLJacob Lauritzen4:15

      So I mean, we've al-- We basically had this switch from the assistant to the agent-

   3. SWswyx4:18

      Yeah

   4. JLJacob Lauritzen4:18

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

   5. SWswyx4:25

      Yeah.

   6. JLJacob Lauritzen4:26

      Um, somewhere.

   7. SWswyx4:26

      So this is a rough timeline for people who are understanding. YC 2023.

   8. JLJacob Lauritzen4:30

      Yes.

   9. SWswyx4:30

      Uh, and then you were, you were a YC founder as well.

   10. JLJacob Lauritzen4:32

       It was YC '24.

   11. SWswyx4:33

       YC '24.

   12. JLJacob Lauritzen4:33

       Yeah, I was in YC '23.

   13. SWswyx4:35

       Yeah.

   14. JLJacob Lauritzen4:35

       Legora was '24.

   15. SWswyx4:36

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

   16. JLJacob Lauritzen4:41

       Exactly, yeah.

   17. SWswyx4:42

       And then, like, using models obviously changed everything.

   18. JLJacob Lauritzen4:44

       Yes.

   19. SWswyx4:44

       I mean, you know, in one, in one sense today, uh, you know, we had a preview of the products. Uh, it does look... Well, preview. We had a private, uh-

   20. JLJacob Lauritzen4:51

       [laughs]

   21. SWswyx4:52

       ... thing. Well, we will put up a video on the-

   22. JLJacob Lauritzen4:53

       Private screening, yeah

   23. SWswyx4:53

       ... on the YouTube. It's mostly like ChatGPT for lawyers.

   24. JLJacob Lauritzen4:56

       Yeah.

   25. SWswyx4:56

       Right? Like a very-

   26. JLJacob Lauritzen4:57

       Yeah

   27. SWswyx4:57

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

   28. JLJacob Lauritzen5:07

       Yeah

   29. SWswyx5:07

       ... things.

   30. JLJacob Lauritzen5:07

       Exactly. That, that's, that's exactly what it is. It's, it's CoWork or ChatGPT-
6. 5:23 – 7:48

   Which models Legora uses and why it added a model picker

   1. SWswyx5:23

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

   2. JLJacob Lauritzen5:27

      I mean, we're using a, a bunch of different ones depending-

   3. SWswyx5:29

      Yeah

   4. JLJacob Lauritzen5:29

      ... on task, right? That's, um-

   5. SWswyx5:31

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

   6. JLJacob Lauritzen5:35

      For the agent... Yeah. Well, we've been back and forth on this.

   7. SWswyx5:38

      Yeah, yeah. [laughs]

   8. JLJacob Lauritzen5:39

      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, like, Tabular View, and, like, we, we try. I think we found it most effective to subdivide the problem and, and, and route on, like, as we subdivide the task. But we do right now have a, a picker- In the agent.

   9. SWswyx5:59

      Mm-hmm.

   10. JLJacob Lauritzen6:00

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

   11. SWswyx6:01

       Ah.

   12. JLJacob Lauritzen6:02

       Um, so yeah.

   13. SWswyx6:03

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

   14. JLJacob Lauritzen6:07

       Yeah.

   15. SWswyx6:07

       Uh, and when I joined, you know, part of my, my thesis for what an agent lab is, an agent lab is a, you know, uh, ideally a domain-specific GPT wrapper.

   16. JLJacob Lauritzen6:17

       Yeah.

   17. SWswyx6:17

       Right? Like we-

   18. JLJacob Lauritzen6:18

       Yeah

   19. SWswyx6:18

       ... we, we run the, uh... We are the domain experts. We'll pay attention to you. We'll, we'll serve your needs way, way more than the frontier labs, and we'll give you the best of the frontier labs-

   20. JLJacob Lauritzen6:26

       Yeah, we'll abstract away all the-

   21. SWswyx6:26

       ... according to our judgment.

   22. JLJacob Lauritzen6:28

       Yeah.

   23. SWswyx6:28

       See, our job is to decide for you because your not, your job is not to-

   24. JLJacob Lauritzen6:31

       Exactly

   25. SWswyx6:32

       ... use models.

   26. JLJacob Lauritzen6:32

       We'll always keep you on the Pareto frontier-

   27. SWswyx6:33

       Yes

   28. JLJacob Lauritzen6:34

       ... and make sure that it just is great all the time, and you don't have to dive into all the details. 'Cause like, one of the things that I've... Exactly to this point, if you go to a lawyer and you ask them, "Oh, you're gonna, you know, uh, draft this contract based on this precedent, do you think that's a Sonnet high or an Opus mid task?" [laughs]

   29. SWswyx6:48

       Like, you know, they, they won't know.

   30. JLJacob Lauritzen6:50

       Just give me the smartest model.
7. 7:48 – 8:20

   Are today’s models good enough for lawyers?

   1. JLJacob Lauritzen7:48

      Yeah.

   2. BCBasil Chatha7:48

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

   3. JLJacob Lauritzen7:53

      It's a... I think it's a power distribution. So like, there's probably like 60% of the work-

   4. BCBasil Chatha7:58

      Yeah

   5. JLJacob Lauritzen7:58

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

8. 8:20 – 9:18

   What agents couldn’t do nine months ago

   1. BCBasil Chatha8:20

      Yeah

   2. JLJacob Lauritzen8:20

      ... I imagine.

   3. BCBasil Chatha8:21

      Early on, like, when you guys first started, I guess, transitioning to the agents-

   4. JLJacob Lauritzen8:25

      Mm

   5. BCBasil Chatha8:25

      ... or building the agents, like, what were... like, what models were you guys using? I guess it would've been, like, Opus 46 or something.

   6. JLJacob Lauritzen8:32

      That would've been, yeah, Sonnet 46, Opus 46 is probably right.

   7. BCBasil Chatha8:37

      What were the agents, like, not good at at that point-

   8. JLJacob Lauritzen8:40

      Mm

   9. BCBasil Chatha8:40

      ... that they're much better at now, even though it's only what, like-

   10. JLJacob Lauritzen8:43

       Yeah

   11. BCBasil Chatha8:43

       ... nine, nine months later?

   12. JLJacob Lauritzen8:44

       Sub agent delegation was one of them that we've gotten working really well now for, like, fan out type retrieval queries.

   13. BCBasil Chatha8:51

       Yeah.

   14. JLJacob Lauritzen8:51

       Works extremely well for us now. Um, that was difficult before. We basically track... So we have a team that's just doing evals, and so we track all of the models' performance in different practice areas, which is like subgroups of, of legal, and different tasks across all of those. So we basically have, like, a big heat map, and we're like-

   15. BCBasil Chatha9:05

       Hmm.

   16. JLJacob Lauritzen9:06

       And then we can see them move, and it's like usually they improve most stuff, but there's actually a lot of model releases where they improve some and, and regress in others.

   17. BCBasil Chatha9:16

       Okay.

   18. JLJacob Lauritzen9:16

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

9. 9:18 – 10:07

   Testing the agent in simulated worlds and a 10,000-file data room

   1. BCBasil Chatha9:18

      Like, what are some of those tasks? Like, are you familiar with how you guys are running a lot of the evals?

   2. JLJacob Lauritzen9:22

      Mm. Yeah.

   3. BCBasil Chatha9:22

      Like, what, like, what are those different subsegments, I guess, that you look at?

   4. JLJacob Lauritzen9:25

      Yeah. So, like, there's, um, there's different just, like, framing stuff. So we have different basically, like, worlds, like RL environments essentially, which is like, "Here's a..." 'Cause, 'cause lawyers work in projects always, more or less. So it's like, "Here's 10,000-file data room. You're doing a due diligence. In the end, a great report looks like this. Like, it contains all these ri- red flags, and, like, it doesn't contain whatever weird, uh, stuff, and, like, we want it to be concise," et cetera, et cetera. That's kind of how we've built it. So there's different tasks, which is like part of it is drafting a report. Like, does the draft look good? Does it contain all the right stuff? Is the wording sound, the analysis sound? There's also the part of finding the red flags, like the analysis before that. So we can kind of like subdivide it a little bit, and then, and that's how we run the evals.

10. 10:07 – 11:03

    The evals team and Legora’s 100 legal engineers

    1. BCBasil Chatha10:07

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

    2. JLJacob Lauritzen10:12

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

    3. SWswyx10:34

       Are they IT in Big Law, or-

    4. JLJacob Lauritzen10:37

       No

    5. SWswyx10:37

       ... they're lawyers?

    6. JLJacob Lauritzen10:37

       They're lawyers in Big Law.

    7. SWswyx10:38

       They're lawyers in Big Law.

    8. JLJacob Lauritzen10:39

       Yeah.

    9. SWswyx10:39

       With CS degrees.

    10. JLJacob Lauritzen10:40

        Yes. [laughs]

    11. SWswyx10:40

        Oh my God.

    12. BCBasil Chatha10:41

        Must be really hard to find those.

    13. JLJacob Lauritzen10:41

        It's a Venn diagram that... Yeah, exactly.

    14. SWswyx10:43

        [laughs]

    15. JLJacob Lauritzen10:43

        That's like our hardest person to hire for. [laughs]

    16. SWswyx10:45

        [laughs]

    17. JLJacob Lauritzen10:45

        But they're also such a force multiplier 'cause 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 to, like, help us shape the product, and it is such a, such an advantage.

11. 11:03 – 12:18

    When evals didn’t seem worth it and one release took citations from 70% to 99%

    1. BCBasil Chatha11:03

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

    2. JLJacob Lauritzen11:05

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

    3. BCBasil Chatha11:30

       Hmm.

    4. JLJacob Lauritzen11:30

       But-

    5. SWswyx11:30

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

    6. JLJacob Lauritzen11:33

       ... it just like solved. I'm-- Yeah, exactly. I mean-

    7. SWswyx11:33

       Just pass it through, right?

    8. JLJacob Lauritzen11:34

       Exactly.

    9. SWswyx11:35

       Yeah.

    10. JLJacob Lauritzen11:35

        I mean, we had one problem where, like, it wouldn't cite properly, and so it would be difficult to follow, and it was like next model release solved. It went from like [laughs] 70% to 99% [laughs] . It's just like we did nothing and, like, great.

    11. SWswyx11:44

        Yeah. Maybe the, the, the real work is, uh, you know, keeping all the data private, making it-

    12. JLJacob Lauritzen11:50

        Yeah

    13. SWswyx11:50

        ... taggable, sortable, ad- adding new features like the, the tabular view.

    14. JLJacob Lauritzen11:53

        Yep. Yep.

    15. SWswyx11:53

        Maybe is that the... You know, may- like-

    16. JLJacob Lauritzen11:55

        You mean over and above ChatGPT?

    17. SWswyx11:56

        Well, I mean, like, yes. But obviously now you're also doing evals.

    18. JLJacob Lauritzen12:00

        Sure.

    19. SWswyx12:00

        I assume your, your use of open models is also increasing.

    20. JLJacob Lauritzen12:02

        Yes. Yeah.

    21. SWswyx12:02

        We can talk about that. Uh, so yeah. I, I don't know what I'm saying here apart from like, you know, what is the job?

    22. JLJacob Lauritzen12:09

        The job is- Yeah ... uh, maybe not... Uh, in the early days, it was not so much to do, do evals- Mm ... because it was mostly exposed model capability-

12. 12:18 – 14:18

    What legal practice could look like in five to ten years

    1. JLJacob Lauritzen12:18

       Yeah ... to lawyers. Yeah. The huge part of it is just, um, 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, like, we can kinda look to that a little bit, but, like, what are the primitives? How do people work? How do you collaborate if it's not a 200-thread email with, like, V5 Word files back and forth? Like, what does that look like? And that's, like, not even necessarily purely AI. That's just, like, build [laughs] a much better product experience- Yeah ... and make sure you do it with, like, audit logs and data retention and all of those sort of really important things in regulated industry. And then there's the, the AI part, which is, like, make the work faster and better, and, and proactive agents that react to stuff when it comes in, so you don't have to, you know, uh, kick off everything. So I think a lot of the work is just figuring out what do we think it's gonna look like in five years. If, you know, model, um, capabilities keep increasing, if price keeps coming down, what could we do? Can you log in, and it's, like, command center, where it's just like, "You need to react to these five things that the agents have been doing lately, and, like, review and check and improve the system"? Maybe that's where we're going, or is where we're going. Yeah, yeah.

    2. BCBasil Chatha13:21

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

    3. JLJacob Lauritzen13:28

       [laughs] I should preface this by saying I don't know.

    4. BCBasil Chatha13:34

       Yeah.

    5. JLJacob Lauritzen13:34

       I mean, who knows really? But, um, I think we can look to coding a lot. I think, um, all lawyers are gonna be way more, uh, productive than they were before. They're gonna be able to do a lot more stuff at a higher quality, uh, for, uh, lower cost. I think the profession itself, the work itself, is gonna improve a lot. It's gonna be a lot more... I think lawyers are gonna spend more of their time doing the stuff that they became lawyers to do, uh, you know, figuring out what's the right risk profile, which manageable risk, what's, like, the... all of their judgment, strategic judgment, and, like, working with clients. They're gonna do that a lot more, and much less of the, like, trawling through big documents to, like, find the smoking gun or, like, do all this menial, super annoying work that a lot of lawyers have been doing.

13. 14:18 – 16:40

    Will the law firm partnership model survive?

    1. BCBasil Chatha14:18

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

    2. JLJacob Lauritzen14:22

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

    3. BCBasil Chatha14:25

       Yeah.

    4. JLJacob Lauritzen14:25

       Yeah. 'Cause the, the partnership model, I don't wanna get, uh, 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 or whatever. You h- you have physical assets or, like, some sort of intangible assets that, that you accrue over time, and, and they pay dividends to the shareholders. But if you work in an industry like professional services, and it's the same for, like, uh, consultancies and, and whatever else, all of your value is in your people, and you can't really own human capital. You know, you, you can't [laughs] you know, slavery's 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.

    5. BCBasil Chatha15:12

       Yeah.

    6. JLJacob Lauritzen15:13

       Will that change? Like, I don't... It doesn't have to, but I think what we really wanna do with 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 X law firm way of doing things, and we can codify that, I think. And we can build a system. And whether that's, like, a self-improving knowledge graph or whatever it is, and, like, precedent files and documents, where there's, like, a way of working that produces a really good out- output, and that can be their IP. So it's, like, a way to codify the human expertise and judgment into a system. That, I think, is... Now I'm just rambling completely, but, like, um, that's something that we want to help empower. Mm. And does that change the partnership model then? 'Cause the incentives are different in the partnership model. You just gotta bring more clients, and you don't wanna take away time from bringing in clients to codify your information, basically. Mm. 'Cause, like, you get rewarded from, you know, eat what you kill or- Yeah ... make this lockstep, whatever. Um, that needs to change a little. We need to figure out an incentive structure where partnerships, uh, partners are incentivized to codify things for, to build an asset for the company. But right now they aren't, 'cause as soon as they leave the partnership, they don't, um, get any dividends from the assets that they built. Yeah. So there's, like, a... Yeah. I think the, the, the whole business model is, is, uh... We'll, we'll see. [laughs]

    7. BCBasil Chatha16:38

       Yeah, yeah. It's all, it's all in question

14. 16:40 – 18:00

    What happens to paralegals and junior lawyers?

    1. BCBasil Chatha16:40

       right now.

    2. JLJacob Lauritzen16:40

       Yeah. My, my actual other take, y- you know, so n- on the partnership level, that's, like, the top end of the- Mm ... the industry. Actually, my take is more on the bottom end, right? Yeah. What happened there? Uh, paralegals, gone. Yeah. Right? Like, junior lawyers, gone. Mm. I don't need them. Yeah. Like, it's, um- [laughs] That's actually not what we're seeing. Okay. So, yeah, there's a... I think it's... I don't know. Would you, would you say that we're seeing that in engineering? Uh, yeah. Yeah? So, uh, junior engineers are- Really kind of cooked ... kind of cooked. Yeah. Like, you kinda have to come out of, uh, drop out of university fully baked, or else you're [laughs] Or else you're not gonna make it. [laughs] Yeah. Um, I feel like I'm, I'm being a bit dramatic- Yeah ... for, for, uh, comedic purpose, but, like, uh, yeah, I know a lot of lawyers, they started as paralegal. They go through law school, all these things, right? Yeah. And now they don't, they're not needed. Yeah. They're seriously just not needed. Yeah, yeah. Yeah, it, it's interesting what happens to the partnership model, like, the pyramid. I think generally a lot of lawyers, um, you still need ju- you need the next generation. And at least for engineering, the way I think about it is you have a good engineer today, they're worth a lot more even than they were two years ago 'cause they can produce so much more stuff, like, if they're good. And I think it's the same thing in legal, where, like, they can actually do a lot of really good work if they're good. So I think it's more that, like, really good lawyers or junior lawyers are worth a lot more. Yeah. It's- And- It's always been the case, right? Yeah. Yeah. Exactly. But it's even more so. But it's like, it's, yeah, it's polarizing even more so.

15. 18:00 – 19:39

    The billable hour and why earlier legal tech fell short

    1. JLJacob Lauritzen18:00

       Yeah.

    2. BCBasil Chatha18:00

       I'm actually curious about that. So, like, the whole, like, law business is basically, like, um, charging per hour.

    3. JLJacob Lauritzen18:07

       Mm.

    4. BCBasil Chatha18:07

       So-

    5. JLJacob Lauritzen18:07

       Yeah

    6. BCBasil Chatha18:07

       ... you know, if each project now can be done-

    7. JLJacob Lauritzen18:10

       Is faster

    8. BCBasil Chatha18:11

       ... a lot faster-

    9. JLJacob Lauritzen18:12

       Yeah

    10. BCBasil Chatha18:12

        ... is it going to be, like, way cheaper? Like-

    11. JLJacob Lauritzen18:14

        This was actually-

    12. BCBasil Chatha18:14

        Yeah

    13. JLJacob Lauritzen18:14

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

    14. SWswyx18:24

        And, and curious, Leia is a Danish thing for something?

    15. JLJacob Lauritzen18:26

        No, a Swedish.

    16. SWswyx18:27

        Swedish.

    17. JLJacob Lauritzen18:28

        Um, no. Also, it means nothing. [laughs]

    18. SWswyx18:30

        [laughs] Okay, okay.

    19. JLJacob Lauritzen18:31

        There's this really funny story in, um, I think it was a Spanish newspaper that wrote about us in the early days, Leia, and then they, they explained that the abbreviation was Legally Efficient Yoda Assistant. [laughs]

    20. SWswyx18:42

        [laughs] Why Yoda?

    21. JLJacob Lauritzen18:44

        Yeah, I don't know. [laughs] I'm just like, "Why, why is it-"

    22. SWswyx18:47

        See, hallucinations are not just from LLMs.

    23. JLJacob Lauritzen18:48

        No, I think journalists hallucinate. [laughs]

    24. SWswyx18:50

        [laughs]

    25. JLJacob Lauritzen18:52

        Um, but no, it, it doesn't mean anything.

    26. SWswyx18:53

        Mm-hmm.

    27. JLJacob Lauritzen18:53

        Uh, so he wrote the application. He, he wr- And my feedback to him was, um, you know, "People have tried this a million times. Legal tech has never been a thing 'cause, like, there's no incentive for lawyers to, to... Why would they be more efficient? They earn less money. Like, it doesn't make any sense." But I think the reason that lawyers do wanna adopt this is that they understand the gravity of the situation. They know that, like, the business model and everything is under pressure, and it's like they need to change 'cause the competitive pressure's so high. The billing model itself I think is also gonna change. We've, we're already seeing that, particularly in the US, that a bunch of stuff is actually being priced on, like, a project fee and not on an hours fee. Um, particularly the, 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.

    28. SWswyx19:36

        Mm.

    29. JLJacob Lauritzen19:36

        And some of it is just being priced on a flat rate.

16. 19:39 – 22:44

    Where the money goes now

    1. SWswyx19:39

       So where is the money being made then? Is it... 'Cause I, I-

    2. JLJacob Lauritzen19:41

       In the strategic work.

    3. SWswyx19:43

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

    4. JLJacob Lauritzen19:47

       That's just a, a very easy example.

    5. SWswyx19:48

       Oh, okay, okay.

    6. JLJacob Lauritzen19:49

       Yeah, yeah. Litigation's also. The big work still is there, and it's very valuable, and so they'll, they'll spend-- lawyers will spend more of their time there. Client relationship's also super important.

    7. SWswyx19:59

       Like a CRM?

    8. JLJacob Lauritzen20:00

       No, just like spending more time with the client.

    9. SWswyx20:02

       Oh.

    10. JLJacob Lauritzen20:02

        Like, a lot of law firms will or historically have basically done stuff for free just to have that relationship with the client.

    11. SWswyx20:08

        Yeah, yeah.

    12. JLJacob Lauritzen20:08

        Uh, and so now they can do that, but they don't have to lose a lot of money on doing it. [laughs]

    13. SWswyx20:11

        Wait, I thought, I thought I just-- I have to pay s- the lawyer money just to be my friend. Like, this, like-

    14. JLJacob Lauritzen20:16

        Yeah. [laughs]

    15. SWswyx20:16

        ... isn't that the retainer thing?

    16. JLJacob Lauritzen20:17

        Yeah. [laughs] Yeah. Yeah, that, that, that's, that's-

    17. SWswyx20:19

        You, you, you tell me I can do it for free? Like...

    18. JLJacob Lauritzen20:20

        Yeah, you just have to find the right lawyers, yeah.

    19. SWswyx20:22

        Oh, goddammit. [laughs]

    20. JLJacob Lauritzen20:23

        [laughs]

    21. SWswyx20:25

        Uh, okay, cool.

    22. JLJacob Lauritzen20:26

        Or Latent Space has to grow much bigger. I don't know.

    23. SWswyx20:28

        Yeah, yeah, we're trying. We're trying. [laughs]

    24. JLJacob Lauritzen20:29

        [laughs]

    25. SWswyx20:29

        Uh, you know. Yeah, so okay, so, so, uh, uh, so you're saying, um, you know, obviously the, the strategic work and all this high-value add is still there.

    26. JLJacob Lauritzen20:37

        Mm.

    27. SWswyx20:37

        But our legal fees are not going down. But you also said paralegals are not affected-

    28. JLJacob Lauritzen20:41

        Mm

    29. SWswyx20:41

        ... or, like, they're, they're just shifting. And, and this is something that, uh, we also did, we, uh, worry about with Cognition.

    30. JLJacob Lauritzen20:47

        Yeah.
17. 22:44 – 23:59

    How Legora used its own product for acquisition diligence

    1. JLJacob Lauritzen22:44

       No. [laughs]

    2. SWswyx22:44

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

    3. JLJacob Lauritzen22:47

       Yes.

    4. SWswyx22:48

       Is, is that how you say it?

    5. JLJacob Lauritzen22:48

       Yeah. Yeah.

    6. SWswyx22:49

       And you, you guys used your own product to do the M&A?

    7. JLJacob Lauritzen22:52

       Yes, we do that all the time.

    8. SWswyx22:52

       So how did that work?

    9. JLJacob Lauritzen22:53

       Yeah.

    10. SWswyx22:53

        Like, can you talk a little bit about that?

    11. JLJacob Lauritzen22:54

        Ooh, dogfooding.

    12. SWswyx22:55

        Yeah.

    13. JLJacob Lauritzen22:55

        No, that works great. We're doing that a lot. Our legal team is, is... I mean, intake has been built with our legal team.

    14. SWswyx23:01

        Yeah.

    15. JLJacob Lauritzen23:01

        'Cause right now we have a Slack workflow where everyone floats their stuff in, and they're like-

    16. SWswyx23:04

        Yeah

    17. JLJacob Lauritzen23:04

        ... "This is annoying".

    18. SWswyx23:04

        Yeah, yeah.

    19. JLJacob Lauritzen23:05

        Right? And inefficient. So it's like, great. We should use Legora for that.

    20. SWswyx23:08

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

    21. JLJacob Lauritzen23:12

        Yeah, absolutely. So it's, it's, um, we, uh, do a lot of the due diligence ourselves because we can do it, uh, with Tabular Review and other tools. We do still have counsel coming in-

    22. SWswyx23:21

        Mm

    23. JLJacob Lauritzen23:21

        ... um, to, like, assess certain risk or, like, you know, there's payroll. And so Kira was simple 'cause that was all in Sweden, but, you know, we've done one in Canada and one in Australia, and so there's, like, payroll in Australia. Okay, do we want someone to look at this, like, a bit more strategically? So there we will still use lawyers for the strategic part, where they can actually be sparring partners and help us a lot on, like, how to figure out how to structure this the right way. But a lot of the more menial stuff we could actually just do ourselves.

    24. SWswyx23:46

        Mm.

    25. JLJacob Lauritzen23:46

        So, like, a lot of, uh, yeah, a lot of the early things we would find, and we have had cases where we found something, uh, [laughs] that's been, like, a red flag, and then we've, we've pulled the brakes.

    26. SWswyx23:55

        Can you talk a little bit about any of those?

    27. JLJacob Lauritzen23:56

        No, I don't think so. [laughs]

    28. SWswyx23:57

        [laughs]

    29. JLJacob Lauritzen23:58

        Yeah.

18. 23:59 – 26:12

    How Swedish and American law firms differ

    1. SWswyx23:59

       All right. Early on, you said you, your early customers were Swedish-

    2. JLJacob Lauritzen24:03

       Mm

    3. SWswyx24:03

       ... like Swedish law firms.

    4. JLJacob Lauritzen24:04

       Yeah.

    5. SWswyx24:05

       Have you seen a difference between working with, like, Swedish law versus, like-

    6. JLJacob Lauritzen24:08

       Yeah

    7. SWswyx24:08

       ... American law firms-

    8. JLJacob Lauritzen24:09

       Mm

    9. SWswyx24:09

       ... that sort of thing? And you guys are mostly working with, like, big, big law firms, right?

    10. JLJacob Lauritzen24:14

        Well, we're also g- smaller law firms also.

    11. SWswyx24:17

        Oh, okay.

    12. JLJacob Lauritzen24:17

        No, we st- we definitely started really, really big law firms, but 50 lawyers also. Use us and, and get a lot of value.

    13. BCBasil Chatha24:23

        Yeah. So have you seen differences between working with, like, the Swedish ones-

    14. JLJacob Lauritzen24:26

        Yeah

    15. BCBasil Chatha24:26

        ... versus American ones? Maybe, like, even-

    16. JLJacob Lauritzen24:28

        Mm

    17. BCBasil Chatha24:28

        ... I don't know, Asian ones? [chuckles]

    18. JLJacob Lauritzen24:29

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

    19. BCBasil Chatha25:02

        What-

    20. JLJacob Lauritzen25:02

        ... are much more like, "We'll just take the off-the-shelf and figure it out"

    21. BCBasil Chatha25:04

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

    22. JLJacob Lauritzen25:06

        Integrations into their own. Like, some of these customers build their own CRM and their own-

    23. BCBasil Chatha25:11

        Ah

    24. JLJacob Lauritzen25:11

        ... uh, document management system, and their own all sorts of stuff, and they want to build that, and then they want to build triggers that, like, you do a review in, in, in Salesforce and it goes to this one person for whatever reason, and they do something, and then it goes into Legora, and then it goes back in. And there's-- so that's, like, the simple end, and then 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. [chuckles]

    25. BCBasil Chatha25:32

        Yeah, yeah.

    26. JLJacob Lauritzen25:32

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

    27. BCBasil Chatha25:39

        And the European ones are like, "Hey," like, you know, they give you product suggestions or-

    28. JLJacob Lauritzen25:43

        Yeah, for sure. I mean, we have-

    29. BCBasil Chatha25:44

        Yeah

    30. JLJacob Lauritzen25:44

        ... great collaboration with all of them.
19. 26:12 – 27:41

    Product metrics when you can’t read the traces

    1. JLJacob Lauritzen26:12

       to achieve it.

    2. BCBasil Chatha26:12

       Okay. Another question I think maybe y-you wanna bring this up is, like, product metrics. Like, how do you know-

    3. JLJacob Lauritzen26:19

       Mm

    4. BCBasil Chatha26:19

       ... that, like, you know, we're actually doing-

    5. JLJacob Lauritzen26:20

       Yeah

    6. BCBasil Chatha26:21

       ... something good here?

    7. JLJacob Lauritzen26:21

       Yeah. Yeah. Mm-hmm.

    8. BCBasil Chatha26:22

       How do you think about that? I'm assuming that's also related to evals.

    9. JLJacob Lauritzen26:25

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

    10. BCBasil Chatha27:20

        I would've assumed you guys, like, signed some sort, sort of agreement with the-

    11. JLJacob Lauritzen27:23

        Yeah

    12. BCBasil Chatha27:23

        ... law firm, and they were like, "Oh, yeah, sure."

    13. JLJacob Lauritzen27:24

        I wish. Yeah, I wish. No, but the thing is, like, a lot of the data that they have is not even, even theirs, right? It's their clients.

    14. BCBasil Chatha27:29

        Oh.

    15. JLJacob Lauritzen27:30

        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-

    16. BCBasil Chatha27:35

        [chuckles]

    17. JLJacob Lauritzen27:35

        ... what we think everyone is doing and, like, build that into eval sets. Um-

    18. BCBasil Chatha27:38

        Wow

    19. JLJacob Lauritzen27:38

        ... so that's just, like, a super annoying kink of

20. 27:41 – 28:42

    Paraphrasing traces and narrowing failures down to 10 or 20 types

    1. JLJacob Lauritzen27:41

       the business.

    2. SWswyx27:41

       Can you do paraphrase? So for example, ChatGPT has, like, a slash feedback thing-

    3. JLJacob Lauritzen27:46

       Mm

    4. SWswyx27:46

       ... uh, that directly fully says the full trajectory.

    5. JLJacob Lauritzen27:49

       Mm.

    6. SWswyx27:50

       But obviously that would-- that is not possible-

    7. JLJacob Lauritzen27:52

       Yeah

    8. SWswyx27:52

       ... for you guys.

    9. JLJacob Lauritzen27:53

       Mm.

    10. SWswyx27:53

        Uh, but you can use an LLM to paraphrase, like, from this real thing-

    11. JLJacob Lauritzen27:56

        Yeah

    12. SWswyx27:57

        ... make a synthetic thing that is, like, close enough, but change all the names, change all the details-

    13. JLJacob Lauritzen28:02

        Yeah

    14. SWswyx28:02

        ... but, like, still-

    15. JLJacob Lauritzen28:03

        Yeah.

    16. SWswyx28:03

        Yeah.

    17. JLJacob Lauritzen28:04

        We can't re-- There's, I mean, there's always a, a, a, a range, right, of, like, if you, if you paraphrase all the way down to, like, three values and you pick one of them, then obviously that's fine. If you, if you just remove the names, then that's may-maybe not fine.

    18. SWswyx28:16

        Yeah.

    19. JLJacob Lauritzen28:16

        And so, like, we are, um, generally pick the, the most safe way.

    20. SWswyx28:21

        Okay.

    21. JLJacob Lauritzen28:21

        So, like, we, we restrict ourselves as most possible 'cause we, you know, there should be-

    22. SWswyx28:24

        Yeah, that's fair enough

    23. JLJacob Lauritzen28:25

        ... no risk at, at all.

    24. SWswyx28:26

        Yeah.

    25. JLJacob Lauritzen28:26

        Um, but there are things where it's like, okay, we know that the failure modes are probably these ten or twenty, so we can, uh, classify it into one of those, and that's-

    26. SWswyx28:33

        Yeah

    27. JLJacob Lauritzen28:33

        ... a helpful signal. Uh, we can classify it into the ta-types of tasks and the practice areas also, and then, like, we have an idea. It's something that we're always trying to, to figure out how to do in a smart way.

21. 28:42 – 30:04

    Why data privacy led Legora to run everything on Azure

    1. BCBasil Chatha28:42

       Also, like, on the privacy front, I guess, um, I'm assuming even two years ago it must have been, like, insanely difficult to get the law firms to be okay with this.

    2. JLJacob Lauritzen28:49

       Yes.

    3. BCBasil Chatha28:49

       But, like-

    4. JLJacob Lauritzen28:49

       Yeah

    5. BCBasil Chatha28:50

       ... how do they think about their data being sent over to Anthropic or-

    6. JLJacob Lauritzen28:53

       Yeah. Yeah, yeah

    7. BCBasil Chatha28:53

       ... you know?

    8. JLJacob Lauritzen28:54

       Yeah.

    9. BCBasil Chatha28:54

       It must be, like, a huge thing.

    10. JLJacob Lauritzen28:56

        This-- All of our infrastructure is on Azure-

    11. BCBasil Chatha28:58

        Yeah

    12. JLJacob Lauritzen28:58

        ... um, primarily for this reason. 'Cause, like, when we started, law firms were like, "AWS? No."

    13. BCBasil Chatha29:03

        Yeah. [chuckles]

    14. JLJacob Lauritzen29:04

        Like, "No way. We don't trust AWS."

    15. SWswyx29:05

        Law firms don't trust AWS?

    16. JLJacob Lauritzen29:07

        Yeah, yeah.

    17. SWswyx29:07

        Why?

    18. JLJacob Lauritzen29:07

        It's different now. No, but it-- they were like, "Amazon, Google-

    19. SWswyx29:10

        [chuckles]

    20. JLJacob Lauritzen29:11

        ... we can't trust them with any of our data." So we basically, we had to host everything on Microsoft 'cause they already have 365.

    21. BCBasil Chatha29:16

        Oh, so they're okay with Microsoft but not-

    22. JLJacob Lauritzen29:17

        Exactly, 'cause they've already done, like, whatever security review-

    23. BCBasil Chatha29:20

        Oh, oh

    24. JLJacob Lauritzen29:20

        ... 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, on Azure, and that's changed over the past few years.

    25. BCBasil Chatha29:29

        Mm.

    26. JLJacob Lauritzen29:29

        So, like, now people understand, okay, we need to get on cloud, we need to do all this kind of stuff. Um, there was also a lot more people talking about on-prem back then. That's also disappeared completely. People understand that, like, you should just do it in the cloud and it's, and it's safe, and it's probably safer than what you're doing.

    27. BCBasil Chatha29:41

        Yeah.

    28. JLJacob Lauritzen29:42

        Um, so that's changed a lot, but I think we can-

    29. SWswyx29:44

        Yeah, and by the way, it's only been three years, so, like, it's actually like-

    30. JLJacob Lauritzen29:46

        Yeah. [laughs]
22. 30:04 – 30:55

    Open-weight models and model arbitrage

    1. BCBasil Chatha30:04

       So also then on, like, open source models now are getting really good.

    2. JLJacob Lauritzen30:07

       Mm.

    3. BCBasil Chatha30:08

       So yeah, how are you thinking about that with the-

    4. JLJacob Lauritzen30:10

       Yeah. The-- We're just thinking about, to, to your point, um, just bring our clients along on, like, the Pareto frontier.

    5. BCBasil Chatha30:17

       Yeah.

    6. JLJacob Lauritzen30:17

       And, like, the, on the, the map of all the models and what they're good at and their latency and their cost and their, their Governance and, and, and their, uh, 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. Um, some we'll post-train, and, and some we'll just use the frontier models.

    7. SWswyx30:36

       Yeah. You call, uh- call it model arbitrage.

    8. JLJacob Lauritzen30:39

       Yeah.

    9. SWswyx30:39

       Uh, you have different, uh, favors. You did some research on this where you were firmly anthropic at the start of the year. Uh-

    10. JLJacob Lauritzen30:46

        Yeah

    11. SWswyx30:46

        ... Grok is improving a lot. Um, yeah, you wanna give an example of a model that wasn't ranked highly overall, but, like, you wanna shout it out as, uh, surprisingly good?

23. 30:55 – 33:33

    Transcription models and why Legora doesn’t use ElevenLabs

    1. JLJacob Lauritzen30:55

       Yeah, I think not overall good. Gemini, one of the early Geminis is-

    2. SWswyx31:00

       Ooh

    3. JLJacob Lauritzen31:00

       ... uh, yeah, extremely good for certain types of, um, uh, transcription-

    4. SWswyx31:04

       Yeah

    5. JLJacob Lauritzen31:04

       ... and speaker attribution. So we use that for transla- um, transcription actually.

    6. SWswyx31:07

       Oh, so you have a, a-

    7. BCBasil Chatha31:08

       Yeah, were you guys transcribing?

    8. SWswyx31:09

       Like a Granola?

    9. JLJacob Lauritzen31:10

       We don't have... We actually probably will build, like, a meeting thing.

    10. SWswyx31:13

        Yeah.

    11. JLJacob Lauritzen31:13

        But this is just like talk-to-spe- speech-to-text-

    12. SWswyx31:15

        Ah

    13. JLJacob Lauritzen31:15

        ... text-to-speech, just like an- an, um, any wor- any other app [chuckles] that has this. And we do actually also transcribe files. If you upload hearings or whatever-

    14. SWswyx31:23

        Oh

    15. JLJacob Lauritzen31:23

        ... we'll, we'll then, like, transcribe them, put them into text, and so we can do all of our analysis on it.

    16. SWswyx31:28

        No ElevenLabs. [laughs]

    17. JLJacob Lauritzen31:29

        No ElevenLab for DPA reasons. Same thing as, like, yeah, data processing agreement, I should say. So, like, our data processing agreement has very few vendors on it-

    18. SWswyx31:37

        Yeah

    19. JLJacob Lauritzen31:37

        ... 'cause we just need to keep it-

    20. SWswyx31:38

        You just need to keep it for-

    21. JLJacob Lauritzen31:39

        Exactly. We need to keep it-

    22. SWswyx31:39

        Tight

    23. JLJacob Lauritzen31:40

        ... super tight-

    24. SWswyx31:40

        Yeah

    25. JLJacob Lauritzen31:40

        ... on where any data goes. And so, um-

    26. SWswyx31:43

        I think, no, that, that is one of the benefits of, like, a Gemini and OpenAI where they're like, you, you come to us, we have most of the things that you need.

    27. JLJacob Lauritzen31:50

        Yeah.

    28. SWswyx31:50

        And that is actually va- 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-

    29. JLJacob Lauritzen31:58

        Yeah

    30. SWswyx31:58

        ... then who cares?
24. 33:33 – 34:24

    The agent, Tabular Review, projects, and the Word add-in

    1. SWswyx33:33

       I do want to cover a little bit on the, the agent product side. Uh, so we've covered a few, like, of, of the top-level stuff, right? Uh, we've already name-dropped Tabular Review.

    2. JLJacob Lauritzen33:41

       Mm.

    3. SWswyx33:41

       Uh, we've name-dropped Intake.

    4. JLJacob Lauritzen33:43

       Yeah.

    5. SWswyx33:43

       And you've, you've got some other, uh, stuff that we haven't even, uh, touched on yet. But I just wanna cover the, the big two, let's call it.

    6. JLJacob Lauritzen33:48

       Yeah. Yeah. Sure.

    7. SWswyx33:49

       Is it- is that- is, is that fair to say that they're the big two, approximately?

    8. JLJacob Lauritzen33:52

       Agent and Tabular Review.

    9. SWswyx33:53

       Yeah.

    10. JLJacob Lauritzen33:53

        Uh, and our-

    11. SWswyx33:54

        And projects

    12. JLJacob Lauritzen33:54

        ... probably-

    13. SWswyx33:55

        Yeah

    14. JLJacob Lauritzen33:55

        ... yeah, and our Word add-in, um-

    15. SWswyx33:57

        Okay

    16. JLJacob Lauritzen33:57

        ... is also something 'cause that's p- a lot of people work, work inside of Word, and so our Word add-in-

    17. SWswyx34:01

        Yeah

    18. JLJacob Lauritzen34:01

        ... is, is a huge... And an Outlook add-in also.

    19. SWswyx34:03

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

    20. JLJacob Lauritzen34:06

        Yeah.

    21. SWswyx34:07

        Uh, so Tabular Review is basically like fan-out of, like, uh, a lot across each document. You can ask the same question across all, all documents.

    22. JLJacob Lauritzen34:13

        Exactly.

    23. SWswyx34:14

        It's collected in a table-

    24. JLJacob Lauritzen34:15

        Yeah

    25. SWswyx34:15

        ... uh, and then work back and forth.

    26. JLJacob Lauritzen34:16

        And then you-

    27. SWswyx34:17

        You can-

    28. JLJacob Lauritzen34:17

        Yeah.

    29. SWswyx34:17

        A million is impressive. Uh, what's any other, like, engineering considerations or performance things? Like, what, what's hard about this?

25. 34:24 – 35:51

    How a lawyer uses Tabular Review

    1. JLJacob Lauritzen34:24

       Uh-

    2. BCBasil Chatha34:24

       Wait, like, before we do that-

    3. JLJacob Lauritzen34:25

       Yeah

    4. BCBasil Chatha34:25

       ... can you just, like, walk through, like, what is a user experience for a lawyer and then, like, actually using-

    5. SWswyx34:29

       Okay. So you want, you want us to do a top-level flow?

    6. BCBasil Chatha34:31

       ... Tabular Review.

    7. SWswyx34:31

       Yeah.

    8. BCBasil Chatha34:31

       Yeah, yeah. Like-

    9. SWswyx34:31

       Okay

    10. BCBasil Chatha34:32

        ... so, like, what are they doing-

    11. SWswyx34:33

        Mm

    12. BCBasil Chatha34:33

        ... like, with Tabular Review?

    13. JLJacob Lauritzen34:34

        Yeah.

    14. BCBasil Chatha34:34

        And then we can go into that.

    15. JLJacob Lauritzen34:35

        Sure.

    16. SWswyx34:35

        Yeah.

    17. BCBasil Chatha34:36

        Yeah.

    18. JLJacob Lauritzen34:36

        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-

    19. SWswyx34:49

        Like, each cell is one employment contract.

    20. JLJacob Lauritzen34:51

        Each row-

    21. SWswyx34:52

        Okay

    22. JLJacob Lauritzen34:52

        ... is one employment contract. And then for cells, you ask questions, basically. So, like, the first question, the first, uh, no, sorry, per column. So the first column might be what's the termination, uh, period. And then it's gonna q- like, fill out for everyone. It's 30 days or whatever it is. And the next question is like, uh, is there an IP assignment clause or whatever. Next one is like, uh, how much, you know, how much do we have to pay them if we fire them or whatever it is. Like, how much are they getting paid? And then it's gonna fill out the entire thing. You can also just ask the agent to do this. Like, if you just drop 10,000 files into the agent and say, like, "Do a due diligence on this," it will spin up a Tabular Review and run all of them and wait for it to be done and then analyze the results, and it can then highlight, like, red flags. Okay, this, the CEO is getting paid an outrageous amount, or there's, like, this weird bonus structure. Okay, then, like, obviously we need to look at that. And then the agent from that can draft a memo to send to the client, or, uh, it can just do the review and then have, you know, a lawyer they use will just be like, "Okay, let's, let's look at this. Here are the red flags." It's also collaborative so that you can comment on it, um, for other people to look at, et cetera.

26. 35:51 – 37:53

    Why a spreadsheet works and what you learn from the first 10 rows

    1. BCBasil Chatha35:51

       And why'd you choose that, like, uh, spreadsheet format?

    2. JLJacob Lauritzen35:54

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

    3. SWswyx36:20

       Yeah.

    4. BCBasil Chatha36:21

       Mm.

    5. SWswyx36:21

       I would say that the spreadsheet form factor has S- has a lot of pull in some areas, but somehow hasn't really spread.

    6. JLJacob Lauritzen36:29

       Mm.

    7. SWswyx36:29

       I, uh, I fi- I find it very weird. Like Clay-

    8. JLJacob Lauritzen36:31

       Yeah

    9. SWswyx36:31

       ... is another one on the GTM side-

    10. JLJacob Lauritzen36:33

        Yeah

    11. SWswyx36:33

        ... that, uh, you know, very known for the spreadsheets.

    12. JLJacob Lauritzen36:34

        Yeah.

    13. SWswyx36:35

        You guys. Uh, I don't really know if anyone else does a, a large spreadsheet AI thing.

    14. JLJacob Lauritzen36:40

        No, no.

    15. SWswyx36:42

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

    16. JLJacob Lauritzen36:50

        Mm

    17. SWswyx36:50

        ... does spreadsheets.

    18. JLJacob Lauritzen36:51

        Does this really well. Yeah.

    19. SWswyx36:52

        [laughs]

    20. JLJacob Lauritzen36:53

        No, I, I agree. I think it's like a great... If you, if you have fan-out and you do the exact same thing, and you- you're extracting stuff, it's, it's such a great-

    21. SWswyx36:58

        Yeah

    22. JLJacob Lauritzen36:58

        ... form factor to like understand-

    23. SWswyx37:00

        Yeah

    24. JLJacob Lauritzen37:00

        ... what's going on.

    25. SWswyx37:01

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

    26. JLJacob Lauritzen37:05

        People are happy to live there. Uh-

    27. SWswyx37:07

        Do you use ag-Grid or your own?

    28. JLJacob Lauritzen37:08

        We do use ag-Grid.

    29. SWswyx37:09

        ag-Grid.

    30. JLJacob Lauritzen37:10

        Yeah.
27. 37:53 – 39:11

    How the legal intake bot works in Slack

    1. SWswyx37:53

       Yeah. I am happy to move on to the next thing.

    2. JLJacob Lauritzen37:54

       Mm.

    3. SWswyx37:54

       Intake, uh, which is your Slack bot.

    4. JLJacob Lauritzen37:57

       Yeah, yeah.

    5. SWswyx37:57

       Um, everyone has a Slack bot. Uh-

    6. JLJacob Lauritzen37:59

       Of course

    7. SWswyx37:59

       ... what's different about yours?

    8. JLJacob Lauritzen38:00

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

    9. SWswyx38:52

       I think the, the data structure for this kind of thing is really interesting 'cause it's like basically the inbox, right-

    10. JLJacob Lauritzen38:57

        Yeah

    11. SWswyx38:57

        ... for all these kinds of queries that can potentially translate into a thing, into something else-

    12. JLJacob Lauritzen39:02

        Yeah

    13. SWswyx39:02

        ... into something else. Um, and like, I, I don't know. Is it hard to integrate all these with all the other features, or do you just not worry

28. 39:11 – 40:15

    How agents create lists and lists start agents

    1. SWswyx39:11

       about it? [laughs]

    2. JLJacob Lauritzen39:12

       It's... No, it's not. I think we have some primitives that work really well. So like Lists is a great primitive 'cause it's essentially... It's like extremely flexible. It's almost like a Notion database.

    3. SWswyx39:21

       You could treat it as, yeah, a Notion database.

    4. JLJacob Lauritzen39:22

       It's like a Notion database, and so you can basically configure it for whatever you want, and we, of course, invest a lot into making this super scalable and work really well, and you can have triggers on them, automations on them, and it's like a great glue to glue everything together 'cause then you can kick off an agent run based on a list if something happens, and then that comes back and 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-

    5. SWswyx39:50

       Wow

    6. JLJacob Lauritzen39:50

       ... agents can read lists, and so it's like the agent swarm comes alive. [laughs]

    7. SWswyx39:54

       Yeah. Do people get excited or overwhelmed by that? You know, like I, I feel like, uh-

    8. JLJacob Lauritzen39:58

       Yeah

    9. SWswyx39:58

       ... this is basically end user programming.

    10. JLJacob Lauritzen40:01

        Yeah.

    11. SWswyx40:01

        Uh, you're, you know, you can let people set up crazy automations. Some people get super obsessed by it-

    12. JLJacob Lauritzen40:07

        Mm

    13. SWswyx40:07

        ... and they become like influ- like, you know-

    14. JLJacob Lauritzen40:08

        Yeah

    15. SWswyx40:08

        ... it'd be cool to have like Legora influencer.

    16. JLJacob Lauritzen40:09

        Yeah, right, Legora has influencers. Yeah, yeah.

    17. SWswyx40:11

        Um, is that worth it?

    18. JLJacob Lauritzen40:13

        Um-

    19. SWswyx40:13

        Too overcomplicated?

29. 40:15 – 42:37

    Building products on those same pieces and acquiring Wexler

    1. JLJacob Lauritzen40:15

       We need the, the flexibility, even if we don't actually expose it to the end user. Let's say this was just all internal. Then it's a really fast way for us to utilize people like, people like our legal engineers to basically build a lot of products extremely fast. So like you can build custom like fund management dashboards. You can basically build that on List with like your own, uh, generative UI, and then you basically have a new product that some people are gonna love, and we can have a marketplace of just like a bunch of sp- specialized products that we can scale super quickly 'cause all of our legal engineers can just build new ones. If they're out with a client, "Oh, you want your own? Easy. Like we'll just fix one for you." So it's like a lovable inside Legora a little bit, and if we don't wanna expose it, that's also how we build our own custom features. So we, we made another acquisition in the UK called Wexler, and they're doing fact intelligence, which is for litigation mostly, which is like you upload a million documents, uh, for a lawsuit or whatever, and then we extract facts from those with like named entities and dates and whatever. And then when you have all the facts, you can basically hold them up against each other and see which ones are corroborated and which ones are, um, what do you call? Disagreement. They-

    2. SWswyx41:20

       Yeah

    3. JLJacob Lauritzen41:20

       ... you know. And that's extremely powerful 'cause then you can also transcribe a court hearing, and you'd be like, "Oh, he said this thing, but actually the email over here says that he was not there." Uh, and it's like if you see it live, it's like so fucking cool.

    4. SWswyx41:33

       Yeah.

    5. JLJacob Lauritzen41:33

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

    6. SWswyx41:51

       Mm

    7. JLJacob Lauritzen41:51

       ... experiences.

    8. SWswyx41:52

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

    9. JLJacob Lauritzen41:57

       Lists is a core one.

    10. SWswyx41:58

        Lists.

    11. JLJacob Lauritzen41:58

        Yeah.

    12. SWswyx41:58

        Projects.

    13. JLJacob Lauritzen41:58

        It's a core one. Yeah, projects.

    14. SWswyx42:00

        Yeah.

    15. JLJacob Lauritzen42:00

        It's basically containers of files, file systems.

    16. SWswyx42:02

        Yeah.

    17. JLJacob Lauritzen42:03

        Um, the agent, of course. You can kick that off and run that in very different configurations.

    18. SWswyx42:07

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

    19. JLJacob Lauritzen42:09

        No, we don't. No.

    20. SWswyx42:10

        Okay. Just intake.

    21. JLJacob Lauritzen42:11

        No.

    22. SWswyx42:11

        Okay.

    23. JLJacob Lauritzen42:11

        Yeah. No, you mean-

    24. SWswyx42:12

        That's okay

    25. JLJacob Lauritzen42:12

        ... like we called it-

    26. SWswyx42:13

        Yeah

    27. JLJacob Lauritzen42:13

        ... like, uh, Leia or-

    28. SWswyx42:14

        Yeah

    29. JLJacob Lauritzen42:14

        ... like we gave it a name?

    30. SWswyx42:15

        [laughs]
30. 42:37 – 43:52

    What forward-deployed engineers do at Legora

    1. BCBasil Chatha42:37

       Yeah. So I actually wanted to talk a little bit about, like, FTEs, 'cause this sounds-

    2. JLJacob Lauritzen42:41

       Yeah

    3. BCBasil Chatha42:41

       ... kinda like that. And I think Max has talked about that a little bit. That, like, okay, when you onboard a new, like, big customer-

    4. JLJacob Lauritzen42:48

       Yeah

    5. BCBasil Chatha42:48

       ... you wanna get them value, like, ASAP-

    6. JLJacob Lauritzen42:50

       Yeah

    7. BCBasil Chatha42:50

       ... so that, you know, they stay on-

    8. JLJacob Lauritzen42:51

       Exactly

    9. BCBasil Chatha42:51

       ... stay on Legora.

    10. JLJacob Lauritzen42:52

        Yep.

    11. BCBasil Chatha42:52

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

    12. JLJacob Lauritzen42:56

        So we hired our first forward deployed engineer, that was our first hire in New York, also YC, uh, founder, nine months ago maybe. I'm not actually sure. Um-

    13. BCBasil Chatha43:04

        Are they considered-

    14. JLJacob Lauritzen43:05

        Just talking about

    15. BCBasil Chatha43:05

        ... legal engineers, or no?

    16. JLJacob Lauritzen43:06

        No, no.

    17. BCBasil Chatha43:07

        Okay. All right.

    18. JLJacob Lauritzen43:07

        True engineers. But we do... It, it is something that I think about, is like how do we exactly enable that at scale? Um, and I think a, a really core thing is, like, how can we empower our legal engineers? Like, how can we empower our power users and our legal engineers to customize the product in a powerful way? And then of course, we, we will still have forward deployed engineers, like, help out, you know, do all the custom integrations and the, the, the scoping and figuring out what's possible, and feed all of that back into core product development. So that's kind of how I think about it, is like almost a first-line, second-line defense. [laughs]

    19. BCBasil Chatha43:36

        Yeah.

    20. JLJacob Lauritzen43:36

        Where it's like legal engineers should be able to customize a lot of stuff and build a great experience, and then where they can't or we need to make core product changes or custom integrations or whatever, we have forward deployed engineers who also then cycle in a little bit behind, like, sometimes they'll just work on the product and sometimes they'll work-

    21. BCBasil Chatha43:51

        Yeah

    22. JLJacob Lauritzen43:51

        ... with clients.

31. 43:52 – 46:43

    How legal engineers and forward-deployed engineers onboard a big client

    1. BCBasil Chatha43:52

       Can you walk through, like, an example? Like, okay, so you-

    2. JLJacob Lauritzen43:54

       Mm

    3. BCBasil Chatha43:54

       ... just got, you just got this new client. Like, what's step number one? Like, are you guys like, "Okay, hey, we have a forward deployed engineer for you guys. They're gonna go build-"

    4. JLJacob Lauritzen44:03

       Yeah

    5. BCBasil Chatha44:03

       ... you know, some kind of product for you." Like, how does that work?

    6. JLJacob Lauritzen44:05

       Yeah. So it's very different client to client, right?

    7. BCBasil Chatha44:06

       Yeah.

    8. JLJacob Lauritzen44:06

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

    9. BCBasil Chatha44:39

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

    10. JLJacob Lauritzen44:43

        Legal engineers configure the product as a power user would.

    11. BCBasil Chatha44:47

        Okay.

    12. JLJacob Lauritzen44:47

        They don't write code.

    13. BCBasil Chatha44:48

        Yeah, yeah.

    14. JLJacob Lauritzen44:49

        And a forward deployed engineer writes code into production-

    15. BCBasil Chatha44:51

        Mm

    16. JLJacob Lauritzen44:51

        ... basically. I guess that's the, that's the, the-

    17. BCBasil Chatha44:52

        Yeah. What kind of background do the forward deployed engineers normally have?

    18. JLJacob Lauritzen44:56

        Regular engineers.

    19. BCBasil Chatha44:56

        You said YC founder.

    20. JLJacob Lauritzen44:57

        Yeah. Founders, regular engineers. They're all-

    21. BCBasil Chatha45:00

        Your, like-

    22. JLJacob Lauritzen45:00

        Yeah

    23. BCBasil Chatha45:00

        ... yeah, Dee was your-

    24. JLJacob Lauritzen45:01

        Yeah, exactly.

    25. BCBasil Chatha45:02

        Was the guy-

    26. JLJacob Lauritzen45:02

        Dee was our first, yeah

    27. BCBasil Chatha45:03

        ... two YC companies and worked on Search at Meta.

    28. JLJacob Lauritzen45:05

        Yeah. She's awesome. Yeah.

    29. BCBasil Chatha45:07

        [laughs]

    30. JLJacob Lauritzen45:07

        Yeah.
32. 46:43 – 47:24

    What’s next for the forward-deployed team over the coming year

    1. BCBasil Chatha46:43

       Oh.

    2. JLJacob Lauritzen46:43

       Is there a rule, like, uh, I guess, does, uh, every, like... You know, so Palantir famously had, like, you know, four days you spend on site.

    3. BCBasil Chatha46:50

       Mm.

    4. JLJacob Lauritzen46:50

       One day you come back and, uh-

    5. BCBasil Chatha46:51

       Yeah

    6. JLJacob Lauritzen46:51

       ... contribute back to products. Anything like that?

    7. BCBasil Chatha46:54

       No. We, we don't-

    8. JLJacob Lauritzen46:54

       Uh, nothing like that?

    9. BCBasil Chatha46:55

       Uh, [laughs] I, um, to be fully honest with you guys, it's still, it's still, uh, you know, still early days in a lot of this. Yeah.

    10. JLJacob Lauritzen47:00

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

    11. BCBasil Chatha47:03

        I do think that it's gonna be more, maybe not exactly like Palantir, but, like, we... I think we will have a larger in-constant circulation group of FDs that 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.

    12. JLJacob Lauritzen47:18

        Yeah.

    13. BCBasil Chatha47:18

        But I, I do imagine us rolling in with legal engineers and forward deployed engineers to, like, work on specific projects.

33. 47:24 – 49:26

    Why Legora resisted building APIs

    1. JLJacob Lauritzen47:24

       Mm. Okay.

    2. BCBasil Chatha47:24

       Yeah. The API business is actually, uh, interesting, like, like you said.

    3. JLJacob Lauritzen47:27

       Mm.

    4. BCBasil Chatha47:27

       Um, because, uh, you know, that's another rule that you can have, where you are the CTO maintainer of the Legora platform.

    5. JLJacob Lauritzen47:34

       Yeah.

    6. BCBasil Chatha47:34

       Right?

    7. JLJacob Lauritzen47:35

       Yeah.

    8. BCBasil Chatha47:35

       Like, we will offer everything that we have in the Legora web app-

    9. JLJacob Lauritzen47:38

       Yep

    10. BCBasil Chatha47:38

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

    11. JLJacob Lauritzen47:43

        That's not something we're promising now.

    12. BCBasil Chatha47:44

        Yeah.

    13. JLJacob Lauritzen47:44

        Um, we do have APIs that you can build against-

    14. BCBasil Chatha47:47

        Yeah

    15. JLJacob Lauritzen47:47

        ... but not the entire surface of the product.

    16. BCBasil Chatha47:49

        That's the curious thing, like, is that the strategy?

    17. JLJacob Lauritzen47:52

        Mm.

    18. BCBasil Chatha47:52

        Or... And obviously, you know, some people will love it because-

    19. JLJacob Lauritzen47:55

        Yeah

    20. BCBasil Chatha47:55

        ... uh, I don't have to learn a new tool. I can just use the, the existing tool I have.

    21. JLJacob Lauritzen47:58

        Yeah.

    22. BCBasil Chatha47:59

        Right? And then I just like-

    23. JLJacob Lauritzen48:00

        Yeah

    24. BCBasil Chatha48:00

        ... uh, install Legora, the-

    25. JLJacob Lauritzen48:02

        Yeah

    26. BCBasil Chatha48:02

        ... for example, with the, the Word document stuff.

    27. JLJacob Lauritzen48:04

        Mm.

    28. BCBasil Chatha48:04

        Other than that, you know, I, I do think, like, then you have to maintain it.

    29. JLJacob Lauritzen48:07

        Exactly. That, that's, so that's been my thing. That's why we've tried not to do it. Uh-

    30. BCBasil Chatha48:11

        Okay
34. 49:26 – 50:12

    Can the agent be the API?

    1. SWswyx49:26

       get it."

    2. JLJacob Lauritzen49:26

       Yeah. I think, I think that's also changing a little bit. A lot of, um, a lot of APIs now, like one thing that we're toying with is like can the agent be the API? I know it sounds weird, but like for some of this stuff, what they actually want to do is they wanna trigger certain things to happen. For some part of this, it could-- you could just be... I'm not saying that we're doing this, but 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?

    3. SWswyx49:58

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

    4. JLJacob Lauritzen50:01

       Yeah. That's the-

    5. SWswyx50:02

       That's-- Is that the only holdbacks?

    6. JLJacob Lauritzen50:04

       That's... Yeah, and then I think, uh, deterministic, like im-

    7. SWswyx50:07

       Yeah

    8. JLJacob Lauritzen50:07

       ... maybe, you know, 100 out of-- or in, in two out of 100 times, it's gonna do something whack that we

35. 50:12 – 51:32

    The 300 Spartans slide and the plan to stay at 20 engineers

    1. JLJacob Lauritzen50:12

       didn't want it to do.

    2. SWswyx50:13

       We're gonna go into, like harness and, and model, uh, fine-tuning in a bit, but I think there's a, there's a product question about restraint-

    3. JLJacob Lauritzen50:19

       Mm

    4. SWswyx50:19

       ... about what you don't do.

    5. JLJacob Lauritzen50:20

       Yep.

    6. SWswyx50:20

       Because you could do all that, and obviously there's a prioritization issue.

    7. JLJacob Lauritzen50:24

       Mm.

    8. SWswyx50:24

       Like it-

    9. JLJacob Lauritzen50:24

       Mm.

    10. SWswyx50:24

        Are, are you at, uh, more at a point of let's, uh, say no to most things-

    11. JLJacob Lauritzen50:28

        Mm

    12. SWswyx50:28

        ... and then only do a short number of stuff? Or no, actually we wanna do more things, and we need... just need to hire like 100 people? [laughing]

    13. JLJacob Lauritzen50:35

        [laughing] I was, I was very strongly the first thing for a very long time.

    14. SWswyx50:39

        Yeah.

    15. JLJacob Lauritzen50:39

        Let's just say no to everything, like keep the eng team. I, I think, um, I've said this before, but like one of our presentations that I... like after I've been at Legora for half a year, I, I put up this slide of, um, you know, the 300 Spartans and, and, and-

    16. SWswyx50:52

        Yeah, yeah

    17. JLJacob Lauritzen50:52

        ... for the movie, and I was like, "We're just gonna be 20 engineers for the rest of the company's history, and like we're gonna beat everyone who's much bigger." And we're 100 engineers now, and it feels like we're way too small. I wanted to do that, but I think the... in the real world, we're in like fierce competition. People want so much stuff. It's like, uh, I could be a puritan and just be like, "No, we have to stay 20 people, and we can only build, you know, whatever," uh, but then we just lose, uh, and like people would go elsewhere. So we have to build more, and so I think my job is to figure out how do I build a system where we can build a lot, but actually only... like where we can... the, the customer feels like we've built so much stuff, but we've actually only built a few things. That's, that's how I think about my job right now.

    18. SWswyx51:27

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

    19. JLJacob Lauritzen51:29

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

36. 51:32 – 53:05

    The bets nobody asked Legora to make

    1. BCBasil Chatha51:32

       Do testing new products, just seeing if like, hey, there's like any pull here, and then you just kinda like, you're like, "No, let's just focus on our main thing," or...

    2. JLJacob Lauritzen51:39

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

    3. BCBasil Chatha51:43

       Yeah

    4. JLJacob Lauritzen51:43

       ... 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-

    5. BCBasil Chatha51:50

       Yeah

    6. JLJacob Lauritzen51:50

       ... that's like, "We want all of these things," and so it's does- hasn't really made sense for us to try to be like, "Hey, what... maybe this thing could work," 'cause like, there's so many people screaming for the other things.

    7. BCBasil Chatha51:57

       Yeah.

    8. JLJacob Lauritzen51:57

       And so we mostly, uh, build those, and then sometimes we'll disagree with clients, and we'll be like, "Actually, I think this thing over here will make a lot of sense strategically," and then we'll try to build that anyway.

    9. BCBasil Chatha52:07

       Like strategically for you?

    10. JLJacob Lauritzen52:08

        Yeah, exactly.

    11. BCBasil Chatha52:08

        So what are those things?

    12. JLJacob Lauritzen52:09

        Or the industry. So one of those things, um, was, uh, the agent actually. So like no one was actually asking for like, "I want us to be, uh... I want the assistant that I'm using to have more agency and do things without me asking it."

    13. BCBasil Chatha52:22

        Yeah.

    14. JLJacob Lauritzen52:22

        Like no one, no one ever... but we're just like, "This def-definitely where the industry is going. This is gonna empower you to do so much cool stuff." Um, collaboration was another one where we're like, we think the industry is going in a place where you can collaborate inside of where you're working, which is Legora, and not in like emails and text messages. So yeah, there, there are, there are a few of those.

    15. BCBasil Chatha52:39

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

    16. JLJacob Lauritzen52:47

        Mm

    17. BCBasil Chatha52:47

        ... learn how to do that.

    18. JLJacob Lauritzen52:48

        Yep.

    19. BCBasil Chatha52:48

        And so that's-

    20. JLJacob Lauritzen52:48

        Yeah

    21. BCBasil Chatha52:48

        ... where you kinda like say, "Hey, FDEs, go in there and teach them what they can do."

    22. JLJacob Lauritzen52:52

        Yeah, legal engineers w- mostly-

    23. BCBasil Chatha52:53

        Oh, legal engineers

    24. JLJacob Lauritzen52:54

        ... they'll be, yeah. Yeah.

    25. BCBasil Chatha52:54

        Okay, that makes sense.

    26. JLJacob Lauritzen52:55

        But they're like some people call them forward-deployed legal engineers-

    27. BCBasil Chatha52:57

        Yeah, yeah

    28. JLJacob Lauritzen52:57

        ... if you want, but that's essentially what they are. [laughing] Um, then they go in, yeah, and help, and help them structure their workflows around, uh, the capabilities of the agent.

37. 53:05 – 54:05

    Post-training open-weight models for legal research

    1. BCBasil Chatha53:05

       You guys said previously, I think Max said this-

    2. JLJacob Lauritzen53:08

       Mm

    3. BCBasil Chatha53:08

       ... but that early on specifically, you guys weren't fine-tuning your own models. Is that still the case?

    4. JLJacob Lauritzen53:14

       Yeah. So we haven't fine-tuned any models up until now.

    5. BCBasil Chatha53:17

       Yeah.

    6. JLJacob Lauritzen53:17

       I think now in the past few months, open-weight models have become extremely capable, and so we will do it for certain tasks where we think there's a huge delta between what a frontier model can do at the cost and latency versus what we think a, a, a post-trained model can do. Legal research is a great example. It's like, uh, you have to make... it's a, it's a fan-out retrieval problem, and you can make a really effective, uh, model to tho-those queries super quickly and super cheaply at low latency.

    7. BCBasil Chatha53:43

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

    8. JLJacob Lauritzen53:47

       Very specific bounded tasks

    9. BCBasil Chatha53:49

       ... searching.

    10. JLJacob Lauritzen53:49

        Yeah, exactly.

    11. BCBasil Chatha53:50

        Okay.

    12. JLJacob Lauritzen53:50

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

    13. BCBasil Chatha53:54

        Yeah

    14. JLJacob Lauritzen53:54

        ... to like be the main agent. I, I don't think that's like a... We won't win that, you know-

    15. BCBasil Chatha53:59

        Yeah, yeah

    16. JLJacob Lauritzen53:59

        ... versus Anthropic most likely.

    17. BCBasil Chatha54:00

        Yeah. There's still a lot of, uh, s- let's say, search and retrieval research or RAG research-

    18. JLJacob Lauritzen54:04

        Mm

    19. BCBasil Chatha54:04

        ... to

38. 54:05 – 54:51

    Search, retrieval, and late interaction

    1. BCBasil Chatha54:05

       do-

    2. JLJacob Lauritzen54:05

       Yeah

    3. BCBasil Chatha54:05

       ... uh, that is like maybe less glamorous. It's not actually even model training sometimes. It's just like-

    4. JLJacob Lauritzen54:09

       Yeah

    5. BCBasil Chatha54:10

       ... architecture and pipelines. You, you, you did a case study with, uh, TurboParpher, but like, you know, there's also like, uh... do you do late interaction of-

    6. JLJacob Lauritzen54:19

       Yes, absolutely. Yeah.

    7. BCBasil Chatha54:20

       You, you do that?

    8. JLJacob Lauritzen54:20

       Yeah. Uh, we actually don't do that.

    9. BCBasil Chatha54:22

       Right.

    10. JLJacob Lauritzen54:22

        But it's, uh... you're completely right that this is... Uh, so there's one guy on the team, Sung, who's, uh- He just really cares about search, and he c- he basically comes to me all the time, and he's like, "Oh, we should do these things," and like, "There's these new embedding models," and like, "We can do this lid and late interaction." He actually talked to Turbo teams to get them to build multi-vector so that we could do these types of things. But no, there's loads of, uh, low-hanging fruit generally even before models. And even in the harness honestly, like, if you just wanna create a better output for our clients, there's like so much stuff that we can do that has immediate impact before training models.

39. 54:51 – 56:25

    What makes a good legal agent harness and why drafting depends on search

    1. SWswyx54:51

       Yeah.

    2. BCBasil Chatha54:51

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

    3. JLJacob Lauritzen54:56

       Mm

    4. BCBasil Chatha54:56

       ... like, your own custom harness.

    5. JLJacob Lauritzen54:57

       Yeah.

    6. SWswyx54:57

       Yeah, of course.

    7. JLJacob Lauritzen54:58

       Yeah. Yep. The way that we edit files is important. The way that we do an analysis is important. Uh, the way you do legal research is all baked into it. So it's like you might have a problem that comes up, or you see something, then it knows how to go and do the legal research to figure out what the answer is-

    8. BCBasil Chatha55:12

       Mm

    9. JLJacob Lauritzen55:12

       ... what the precedent is. That's all very important, and then of course there's all the governance stuff around it as well.

    10. BCBasil Chatha55:17

        Yeah. It seems like the search is probably, like, would you say the most important tool that you guys are really customizing? 'Cause-

    11. JLJacob Lauritzen55:23

        It's-

    12. BCBasil Chatha55:23

        ... if you can't pull down-

    13. JLJacob Lauritzen55:24

        Yeah

    14. BCBasil Chatha55:24

        ... the right information-

    15. JLJacob Lauritzen55:25

        Yeah, and then you're-

    16. BCBasil Chatha55:26

        Yeah, yeah

    17. JLJacob Lauritzen55:26

        ... screwed.

    18. BCBasil Chatha55:26

        You're screwed. [chuckles]

    19. JLJacob Lauritzen55:27

        It's, uh ... Yeah, I think it's, it's, it's, um-

    20. BCBasil Chatha55:29

        You guys are searching-

    21. JLJacob Lauritzen55:30

        ... search-

    22. BCBasil Chatha55:30

        ... like a lot of documents

    23. JLJacob Lauritzen55:31

        ... and analysis.

    24. BCBasil Chatha55:31

        Yeah.

    25. JLJacob Lauritzen55:32

        Yeah. It's search, it's analysis, and it's drafting probably.

    26. BCBasil Chatha55:35

        Okay.

    27. JLJacob Lauritzen55:35

        'Cause, like, drafting word, drafting huge contracts is actually also not super trivial.

    28. BCBasil Chatha55:39

        Like, what about it is not trivial?

    29. JLJacob Lauritzen55:40

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

    30. BCBasil Chatha55:49

        A specific law firm, how did they do it previously?
40. 56:25 – 57:03

    Which model writes the best draft?

    1. JLJacob Lauritzen56:25

       problem.

    2. SWswyx56:25

       Which model's best at drafting?

    3. JLJacob Lauritzen56:27

       [laughs] So I'll say, I was told I was far from this yesterday, uh, definitely Fable and Opus are extremely chatty. I'm sure you guys have known this. Uh, they're very verbose.

    4. SWswyx56:36

       So that's not good.

    5. JLJacob Lauritzen56:37

       That's generally not good, no.

    6. SWswyx56:38

       Okay.

    7. JLJacob Lauritzen56:38

       So this is super important-

    8. BCBasil Chatha56:38

       I've noticed Astra is pr- pretty good at writing

    9. JLJacob Lauritzen56:40

       ... Astra is, uh-

    10. BCBasil Chatha56:41

        Yeah

    11. JLJacob Lauritzen56:41

        ... yeah, pretty good at writing.

    12. SWswyx56:42

        And is it promptable?

    13. JLJacob Lauritzen56:42

        Much less more concise.

    14. SWswyx56:43

        Um, are you running-

    15. JLJacob Lauritzen56:44

        For, for-

    16. SWswyx56:44

        ... like, 100 different prompts to, like-

    17. JLJacob Lauritzen56:46

        Yeah

    18. SWswyx56:46

        ... be sure?

    19. JLJacob Lauritzen56:47

        We, we can ... Yeah, we can-

    20. SWswyx56:48

        Okay

    21. JLJacob Lauritzen56:48

        ... we can do, we can do certain things, but I think the chattiness verbosity is actually a little bit difficult for us to do.

    22. SWswyx56:53

        Wow.

    23. JLJacob Lauritzen56:53

        So this is ... I think, you know, let's see, but probably the next model from Anthropic is gonna be much better at this. Astra is actually very concise.

    24. SWswyx57:00

        Yeah, yeah.

    25. JLJacob Lauritzen57:00

        And I, I assume they, they all have a Slack channel with

41. 57:03 – 57:41

    Hallucinations and Legora’s citation system

    1. JLJacob Lauritzen57:03

       you, and you're telling them this, right?

    2. SWswyx57:04

       Yeah, yeah, yeah, exactly.

    3. JLJacob Lauritzen57:04

       Like, it's just-

    4. SWswyx57:04

       Yeah, we talk to them about it

    5. JLJacob Lauritzen57:04

       ... this is not news to them. No, no, no, they know this.

    6. BCBasil Chatha57:07

       All right.

    7. JLJacob Lauritzen57:07

       Then the other thing that I really care about is hallucination.

    8. SWswyx57:09

       Mm-hmm.

    9. JLJacob Lauritzen57:09

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

42. 57:41 – 58:19

    Do lawyers check the citations?

    1. JLJacob Lauritzen57:41

       all the way up.

    2. SWswyx57:41

       Yeah.

    3. BCBasil Chatha57:42

       Are you finding that lawyers are, like, verifying that these citations are correct-

    4. JLJacob Lauritzen57:45

       They-

    5. BCBasil Chatha57:46

       ... or not?

    6. JLJacob Lauritzen57:46

       No. In-

    7. SWswyx57:46

       [laughs]

    8. JLJacob Lauritzen57:47

       ... init- initially-

    9. BCBasil Chatha57:47

       It's kinda like code review

    10. JLJacob Lauritzen57:48

        ... some of them were but now ... Yeah, exactly. Same thing

    11. BCBasil Chatha57:50

        ... are you actually, are you actually doing it?

    12. JLJacob Lauritzen57:50

        It's the same thing.

    13. SWswyx57:51

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

    14. JLJacob Lauritzen57:54

        That happens, yeah.

    15. SWswyx57:54

        [laughs]

    16. JLJacob Lauritzen57:55

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

    17. BCBasil Chatha58:03

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

    18. JLJacob Lauritzen58:06

        Yeah, but I think they probably just like we know in code review what to look for-

    19. BCBasil Chatha58:09

        Yeah

    20. JLJacob Lauritzen58:09

        ... like, what is the system or whatever. I think they also know, okay, this is the, the thing. These are the red ... Like, this is the thing that's important. Let me just, like, double-check these things.

    21. BCBasil Chatha58:16

        Yeah.

    22. JLJacob Lauritzen58:16

        Then, like, these sound reasonable, so it's probably fine.

43. 58:19 – 1:00:16

    MapReduce or one big context window for a million-token contract?

    1. BCBasil Chatha58:19

       Okay. Interesting.

    2. SWswyx58:19

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

    3. BCBasil Chatha58:24

       Yeah

    4. SWswyx58:24

       ... this probably is fine. Any other elements of let's call it legal reasoning or what's the, the, the legal frontier that-

    5. JLJacob Lauritzen58:30

       Mm

    6. SWswyx58:30

       ... uh, models are not good enough yet that you want from the next generation of models?

    7. JLJacob Lauritzen58:35

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

    8. SWswyx58:41

       Long, like, million-token, token contracts or something?

    9. JLJacob Lauritzen58:43

       Yeah, exactly. You have a huge contract-

    10. SWswyx58:44

        Yeah

    11. JLJacob Lauritzen58:44

        ... um, and, like, you're making edits across it. It's a difficult thing to do for a model today even.

    12. SWswyx58:50

        Mm.

    13. JLJacob Lauritzen58:50

        Uh, and, like, remember that you changed all these things up here, and, like, the definition's changed and that you ... the ordering changed and whatever else.

    14. SWswyx58:55

        Mm.

    15. JLJacob Lauritzen58:56

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

    16. SWswyx59:00

        Yes.

    17. JLJacob Lauritzen59:00

        You don't do that. You break it up into chunks-

    18. SWswyx59:02

        Yeah

    19. JLJacob Lauritzen59:02

        ... and then you orchestrate edits.

    20. SWswyx59:03

        Yeah. Exactly. Exactly.

    21. JLJacob Lauritzen59:05

        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, we've done, you know, we've done MapReduce, and we've changed, and there was one big one, and there was, like, one big one and multiple times. It's like we keep changing-

    22. SWswyx59:18

        Yes

    23. JLJacob Lauritzen59:18

        ... the, the scaffolding that we build around as models change.

    24. SWswyx59:20

        Yes. I, I, I would say I, I, um, I've ... Recently I do a lot of, like, news reporting-

    25. JLJacob Lauritzen59:25

        Mm-hmm

    26. SWswyx59:25

        ... uh, obviously because of what I do, and I've recently shifted from MapReduce to throw everything into context.

    27. JLJacob Lauritzen59:30

        The entire thing. Yeah. Yeah.

    28. SWswyx59:31

        And it's-

    29. JLJacob Lauritzen59:31

        'Cause now they're-

    30. SWswyx59:31

        ... it's better. [laughs]
44. 1:00:16 – 1:01:53

    Getting anonymized examples and the idea of buying a law firm for its data

    1. BCBasil Chatha1:00:16

       be hard-

    2. JLJacob Lauritzen1:00:16

       ... non-trivial

    3. BCBasil Chatha1:00:17

       ... like you said earlier, to actually make the models better at that 'cause you can't even look at the contracts, right?

    4. JLJacob Lauritzen1:00:23

       Exactly.

    5. BCBasil Chatha1:00:23

       These are real contracts.

    6. JLJacob Lauritzen1:00:24

       Yeah, yeah.

    7. BCBasil Chatha1:00:24

       So do you guys ever ask them for, like, "Hey, can you-

    8. JLJacob Lauritzen1:00:27

       Yes

    9. BCBasil Chatha1:00:27

       ... make example contracts-

    10. JLJacob Lauritzen1:00:28

        Yes

    11. BCBasil Chatha1:00:28

        ... that are similar to your real ones?"

    12. JLJacob Lauritzen1:00:29

        We do. Yeah, yeah.

    13. BCBasil Chatha1:00:30

        Okay.

    14. JLJacob Lauritzen1:00:30

        So we have, we have feedback, and we can receive feedback from them-

    15. SWswyx1:00:32

        Yeah

    16. JLJacob Lauritzen1:00:32

        ... and if they are willing to engage-

    17. SWswyx1:00:33

        Send to the company

    18. JLJacob Lauritzen1:00:33

        ... yeah, exactly, or they're just like, "Hey, this is, like, super important to us and it's not working well." And then we'll be like, "Okay, great. Can you, like, anonymize the documents?"

    19. BCBasil Chatha1:00:39

        Yeah.

    20. JLJacob Lauritzen1:00:39

        And, like- The problem, then whatever, and we'll re- we- if we can recreate it, then we can fix it.

    21. BCBasil Chatha1:00:43

        Yeah.

    22. SWswyx1:00:44

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

    23. JLJacob Lauritzen1:00:47

        Yeah

    24. SWswyx1:00:47

        ... which some people are considering.

    25. JLJacob Lauritzen1:00:50

        Yes, but, uh, there's some... we... There's some stuff there on whether-

    26. SWswyx1:00:53

        [laughs]

    27. JLJacob Lauritzen1:00:53

        ... uh, their data is actually their data or if it's the client's data.

    28. SWswyx1:00:56

        Hmm.

    29. JLJacob Lauritzen1:00:57

        So if the clients are all gone, then maybe it's fine. I actually don't know.

    30. SWswyx1:01:02

        Interesting.
45. 1:01:53 – 1:02:44

    Why Jacob advises against default embeddings

    1. SWswyx1:01:53

       We're gonna wrap up soon. Uh, the last thing I'll point people to is also there's a lot of alpha left on embeddings. If you're-

    2. JLJacob Lauritzen1:01:57

       Yeah

    3. SWswyx1:01:57

       ... if you're a rag-heavy work, workload, uh, you're, you're just looking at like MTEB and you're taking like top model, uh, you're leaving a lot on the table. You should look at like, uh, Voyage or like some of the em-

    4. JLJacob Lauritzen1:02:07

       Yeah

    5. SWswyx1:02:07

       ... uh, custom embeddings. You-

    6. JLJacob Lauritzen1:02:08

       Yeah, yeah

    7. SWswyx1:02:08

       ... you've looked into this.

    8. JLJacob Lauritzen1:02:09

       We've... Yeah, yeah. Absolutely.

    9. SWswyx1:02:10

       Yeah. So basically, don't take default embeddings even like OpenAI embeddings, Gemini embeddings. Doesn't matter. Customize your embeddings.

    10. JLJacob Lauritzen1:02:15

        Yeah.

    11. SWswyx1:02:15

        Right?

    12. JLJacob Lauritzen1:02:16

        Yes.

    13. SWswyx1:02:16

        You, you, you support that?

    14. JLJacob Lauritzen1:02:18

        Yes. Ev- I think that's right.

    15. SWswyx1:02:19

        Okay.

    16. JLJacob Lauritzen1:02:19

        I think that's right. We... The only thing is, uh, need to make sure that you're multi, uh, language. So for us, we, we serve so many languages, so that's been one of the problems.

    17. SWswyx1:02:25

        I mean, Europe is like king of this.

    18. JLJacob Lauritzen1:02:27

        [laughs] Yeah, yeah. Exactly.

    19. SWswyx1:02:28

        Uh, Mistral helpful there?

    20. JLJacob Lauritzen1:02:30

        Um, no. [laughs]

    21. SWswyx1:02:31

        [laughs] Ooh.

    22. BCBasil Chatha1:02:33

        Until-

    23. JLJacob Lauritzen1:02:34

        That's-

    24. BCBasil Chatha1:02:34

        Until now. They just raised a ton of money, right? So maybe.

    25. SWswyx1:02:37

        Yeah.

    26. JLJacob Lauritzen1:02:37

        Let's see.

    27. SWswyx1:02:38

        I mean, you guys basically-

    28. JLJacob Lauritzen1:02:38

        They also raised a ton of money a year ago.

    29. SWswyx1:02:40

        Yeah. I don't know

    30. JLJacob Lauritzen1:02:40

        ... champions like-
46. 1:02:44 – 1:03:26

    Will lawyers work in Legora or through Claude?

    1. JLJacob Lauritzen1:02:44

       Yes.

    2. BCBasil Chatha1:02:44

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

    3. SWswyx1:02:51

       Uh, ex- uh, we, we asked a little bit of that earlier.

    4. BCBasil Chatha1:02:53

       Yeah.

    5. SWswyx1:02:53

       I'll modify it to your second question, which is, uh, in two years, will lawyers do their work inside Legora or will they use, uh, other tools like-

    6. JLJacob Lauritzen1:03:01

       Hmm

    7. SWswyx1:03:01

       ... Claude or ChatGPT-

    8. JLJacob Lauritzen1:03:02

       Yeah

    9. SWswyx1:03:02

       ... and call Legora? Like, you know, the API function.

    10. JLJacob Lauritzen1:03:04

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

    11. SWswyx1:03:17

        Yeah

    12. JLJacob Lauritzen1:03:18

        ... because that's simpler and better.

    13. BCBasil Chatha1:03:20

        Yeah.

    14. JLJacob Lauritzen1:03:20

        Um-

    15. BCBasil Chatha1:03:20

        It kind of reminds me of like open evidence for like medicine.

    16. JLJacob Lauritzen1:03:23

        Yeah.

    17. BCBasil Chatha1:03:23

        Like you're, you're basically that for law.

    18. JLJacob Lauritzen1:03:25

        Yeah.

    19. BCBasil Chatha1:03:25

        Yeah.

47. 1:03:26 – 1:04:24

    Will the model labs cut Legora off?

    1. JLJacob Lauritzen1:03:26

       Exactly.

    2. SWswyx1:03:26

       In coding as well until a point where people, the labs will cut you off for competing with them.

    3. JLJacob Lauritzen1:03:30

       Mm.

    4. SWswyx1:03:31

       And this has happened twice.

    5. JLJacob Lauritzen1:03:32

       Yeah.

    6. SWswyx1:03:32

       Do, do you think that will happen to law?

    7. JLJacob Lauritzen1:03:34

       No, I don't think so.

    8. SWswyx1:03:35

       Yeah.

    9. JLJacob Lauritzen1:03:35

       I think-

    10. SWswyx1:03:35

        Because like, you know, they are re- releasing legal services things.

    11. JLJacob Lauritzen1:03:38

        Yeah, yeah.

    12. SWswyx1:03:38

        Right?

    13. JLJacob Lauritzen1:03:38

        Yeah, yeah. They are. I don't... I mean, we obviously talk to them a lot, but it's also... it's like, "Hey, are you gonna [laughs] what's-"

    14. SWswyx1:03:44

        Your sales reps will say no.

    15. JLJacob Lauritzen1:03:46

        Exactly.

    16. SWswyx1:03:46

        They don't make the call.

    17. JLJacob Lauritzen1:03:47

        Exactly. That's not their call to make.

    18. SWswyx1:03:49

        [laughs]

    19. JLJacob Lauritzen1:03:49

        Right? And they don't even know of- like often what's actually going on. I don't thi- I don't think that's the case. They have so much stuff to capture in knowledge work or in, in, in sort of enterprises knowledge work generally that like legal has to be part of that, just like data analytics has to-

    20. SWswyx1:04:03

        Yeah

    21. JLJacob Lauritzen1:04:03

        ... and sales and marketing and finance. So like they have to do things that are good there, but uh, they're never gonna go as deep as we are. And I think if, if Claude takes a small client, small, uh, you know, corporate clients and they do some of their legal via Claude, like that's, that's great. That's fine. But if you're doing a, you know, $400 million M&A transaction, you're gonna want Legora.

    22. BCBasil Chatha1:04:23

        I had kind of

48. 1:04:24 – 1:05:28

    Law schools and scholarships for computer science majors

    1. BCBasil Chatha1:04:24

       an unrelated question, but I'm curious, are you guys going to law schools and kinda like getting them-

    2. JLJacob Lauritzen1:04:30

       Mm.

    3. BCBasil Chatha1:04:30

       ... to like teach-

    4. JLJacob Lauritzen1:04:30

       Yeah

    5. BCBasil Chatha1:04:30

       ... Legora-

    6. JLJacob Lauritzen1:04:31

       Yeah, yeah

    7. BCBasil Chatha1:04:31

       ... like in classes? Like how does that work?

    8. JLJacob Lauritzen1:04:33

       It-

    9. BCBasil Chatha1:04:33

       Are you guys thinking about that?

    10. SWswyx1:04:33

        Yeah. It's, it's, uh, it's definitely a program that we are... uh, I think we've started.

    11. BCBasil Chatha1:04:37

        Oh, cool.

    12. SWswyx1:04:37

        I actually don't know exactly where we're at, but we, we do want people in law school to-

    13. BCBasil Chatha1:04:40

        Yeah

    14. SWswyx1:04:40

        ... learn to use Legora. Um-

    15. BCBasil Chatha1:04:42

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

    16. SWswyx1:04:46

        I don't know. I, I, I, I-

    17. BCBasil Chatha1:04:48

        Yeah

    18. SWswyx1:04:48

        ... wouldn't know actually.

    19. BCBasil Chatha1:04:49

        Interesting.

    20. SWswyx1:04:50

        I would actually do it a different way. Uh, you should do scholarships for l- for law school for CS majors, for engineers. We will cover your-

    21. JLJacob Lauritzen1:04:57

        After you've done CS-

    22. SWswyx1:04:58

        Yes

    23. JLJacob Lauritzen1:04:59

        ... we'll, we'll put you in law school?

    24. SWswyx1:04:59

        We'll co- Yeah. CS plus some software experience-

    25. JLJacob Lauritzen1:05:02

        Yeah

    26. SWswyx1:05:02

        ... we'll put you in law school.

    27. JLJacob Lauritzen1:05:03

        Yeah.

    28. SWswyx1:05:03

        We'll cover it.

    29. BCBasil Chatha1:05:04

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

    30. JLJacob Lauritzen1:05:09

        Yeah. We'll-
49. 1:05:28 – 1:06:09

    Hiring in New York, Stockholm, and London

    1. SWswyx1:05:28

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

    2. JLJacob Lauritzen1:05:37

       Absolutely.

    3. SWswyx1:05:37

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

    4. JLJacob Lauritzen1:05:41

       We're hiring in-

    5. SWswyx1:05:42

       ... Sweden

    6. JLJacob Lauritzen1:05:42

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

    7. SWswyx1:05:46

       Yeah.

    8. JLJacob Lauritzen1:05:47

       Uh, and all other roles we're hiring everywhere, almost.

    9. SWswyx1:05:50

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

    10. JLJacob Lauritzen1:05:52

        100. About 100.

    11. BCBasil Chatha1:05:53

        Okay. And you guys are planning on how many in New York?

    12. JLJacob Lauritzen1:05:56

        In New York?

    13. BCBasil Chatha1:05:56

        Yeah.

    14. JLJacob Lauritzen1:05:57

        For just like generally?

    15. BCBasil Chatha1:05:58

        Let's just say, yeah, generally engineering.

    16. JLJacob Lauritzen1:06:00

        Um, a lot.

    17. BCBasil Chatha1:06:01

        As many as you can.

    18. JLJacob Lauritzen1:06:02

        I don't... Yeah.

    19. BCBasil Chatha1:06:02

        [laughs]

    20. JLJacob Lauritzen1:06:03

        It's, it's, it's aggressive. [laughs]

    21. SWswyx1:06:04

        [laughs]

    22. BCBasil Chatha1:06:05

        Cool.

    23. SWswyx1:06:05

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

    24. JLJacob Lauritzen1:06:08

        It i- yeah,

50. 1:06:09 – 1:07:21

    Why most work eventually becomes legal work

    1. JLJacob Lauritzen1:06:09

       it is

    2. SWswyx1:06:09

       ... Mid-America is concerned.

    3. JLJacob Lauritzen1:06:09

       New York is, uh-

    4. SWswyx1:06:10

       So like-

    5. JLJacob Lauritzen1:06:10

       Yeah

    6. SWswyx1:06:11

       ... yeah, I mean, I'm looking forward to you buying a law firm and like-

    7. JLJacob Lauritzen1:06:14

       Yes

    8. SWswyx1:06:14

       ... you know, becoming-

    9. JLJacob Lauritzen1:06:14

       Yeah.

    10. SWswyx1:06:15

        Yeah. It, it, it's, it's super exciting to, to... I think like, you know, every industry, especially like the top like doctors, lawyers, coders, you know, th- they all have to have like, you know-

    11. JLJacob Lauritzen1:06:25

        Yes. I agree

    12. SWswyx1:06:25

        ... two or three agent labs that like just-

    13. JLJacob Lauritzen1:06:27

        Yeah

    14. SWswyx1:06:27

        ... sort of dominate the space.

    15. JLJacob Lauritzen1:06:28

        I agree.

    16. SWswyx1:06:29

        So you guys have like a great market. Yeah. Good.

    17. JLJacob Lauritzen1:06:30

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

    18. SWswyx1:06:37

        Yeah. Also, I, 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?

    19. JLJacob Lauritzen1:06:46

        Yes. Yeah.

    20. SWswyx1:06:47

        They're... Okay. Like un- unless you're literally like doing like science-

    21. JLJacob Lauritzen1:06:50

        Navier-Stokes

    22. SWswyx1:06:51

        ... Navier-Stokes and science. Other than that, like most work is like basically c- uh, converges to legal.

    23. JLJacob Lauritzen1:06:57

        Yeah.

    24. SWswyx1:06:58

        Like [laughs]

    25. JLJacob Lauritzen1:06:59

        [laughs]

    26. SWswyx1:07:00

        Yeah.

    27. JLJacob Lauritzen1:07:00

        Uh, yeah.

    28. SWswyx1:07:01

        It's all legal in the end. [laughs]

    29. JLJacob Lauritzen1:07:02

        Yeah.

    30. SWswyx1:07:02

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

Episode duration: 1:07:21