Legora CTO Jacob Lauritzen 谈如何为律师构建 AI 智能体

在本期节目中，我们与 Legora 的 CTO Jacob Lauritzen 进行了对话，此前几周他们刚刚宣布以 88 亿美元估值完成 5.5 亿美元 E 轮融资。我们聊了为律师构建 AI agent 需要什么，以及其他构建 agent 的人能从这项工作中学到什么。

Legora 起步于斯德哥尔摩的一间地下室，最初的产品很简单：ChatGPT、瑞典法律和一个搜索工具。Jacob 在帮助 Max Junestrand 申请 Leya（现为 Legora）时，已经带着自己的创业公司经历过 YC。他后来以工程负责人身份加入，现在是 CTO。

如今，该 agent 可以起草和编辑 Word 文档、一次性审阅数千份合同，并在律师、其客户和其他 agent 之间协调工作。公司在 4 月突破了 1 亿美元的 ARR，距离产品发布不到 18 个月，目前拥有超过 1,800 家客户。它在 3 月以 55.5 亿美元估值融资 5.5 亿美元，随后在 10 月又以 88 亿美元估值融资 5.5 亿美元。其最新收购 Wexler 是今年以来的第五笔。

我们问 Jacob：当你无法看到客户数据时，如何评估 agent；哪些任务仍然需要更好的模型；法律工程师和前向部署工程师如何分工；以及为什么按小时计费作为一种商业模式正在被颠覆。

在 YouTube 上观看完整对话 →

在 YouTube 上打开视频 ↗

按小时计费发生了什么变化？

当 Jacob 第一次读到 Leya 的 YC 申请时，他只有一条反馈：人们已经尝试构建法律科技一百万次了，但从未成功。如果律师按小时收费，变得更快就意味着赚得更少。他们为什么要买一个这样的工具？

他说，发生变化的是律所面临的压力。在美国，像小型审阅这样的常规工作已经在转向固定项目收费。一些律所免费做这些工作以留住客户。钱流向了并购、诉讼以及与客户相处的时间。

我们问这是否意味着律所将不再需要律师助理和初级律师。Jacob 说，这并不是 Legora 看到的情况。一名优秀的初级律师今天比两年前更有价值，因为他们能完成的工作多得多，就像工程领域一样。

跳转到计费模式讨论 →

无法访问客户数据时的评估

大多数团队通过阅读 trace 来改进他们的 agent。Legora 无法读取任何 trace。用户上传的几乎所有内容都是机密，其中很多属于律所的客户，而不是律所本身。

因此，评估团队必须重建客户所做的那类工作。三名工程师和三名律师构建 RL 环境，以模拟客户所做的工作。一个例子是一个包含 10,000 个文件的数据室，agent 在其中进行尽职调查，并且必须生成一份能捕捉到正确危险信号的报告。团队按业务领域和任务将结果绘制在热力图上。新模型往往在某些类型的法律工作上变得更好，而在另一些上变得更差。

团队依托一个约 100 名法律工程师的人才库：这些律师曾在大型律所工作三到四年，通常还拥有计算机科学学位。在生产环境中，Legora 将失败归类为 10 到 20 种已知失败模式，并在功能开关后面运行低成本的基于 LLM 的检查。

这些限制也决定了 Legora 可以使用哪些基础设施。一切都在 Azure 上运行，因为 Legora 起步时，律所不接受 AWS 或 GCP，而微软已经通过 365 成为获批供应商。

跳转到无 trace 的评估 →

更聪明的模型仍然重要的地方

Legora 长期以来一直抵制模型选择器，最终才妥协。Jacob 的观点是，律师不应该去判断一份合同是 Sonnet-high 还是 Opus-mid 级别的任务。Legora 的职责是在质量、成本、延迟、治理和区域可用性之间找到最佳权衡。

他估计模型已经能很好地处理约 60% 的法律工作。对这些任务来说，现在的问题是成本和延迟。跨百万 token 合同的复杂分析和编辑仍然需要更强的智能。

Legora 已开始针对法律研究等狭窄任务对开放权重模型进行后训练，但没有训练自己前沿模型的计划。在起草方面，Jacob 觉得 Fable 和 Opus 过于冗长。Astra 更简洁。为解决幻觉问题，智能体写出的所有内容都会附带引用，在源 PDF 中高亮一个边界框，并向下多层追溯。

跳转到模型讨论 →

几个构建模块，众多产品

上任六个月时，Jacob 给团队看了一张 300 斯巴达勇士的幻灯片，并宣称 Legora 将永远保持 20 名工程师。现在它有 100 名，他说这仍然感觉太小。他现在的职责是构建一个系统，让团队只需交付少数几样东西，客户却感觉收获很多。

团队围绕几个原语构建：存放文件的项目、智能体、表格审查和列表。列表是一个灵活的 Notion 风格数据库，带有触发器和自动化。智能体可以创建和读取列表，列表的变更可以启动智能体。Intake 是一个 Slack 机器人，将请求转化为列表上的工单。

表格审查是被业界抄袭的那一个，连名字都照搬。每一行是一份文档，每一列是一个问题。放入 10,000 份雇佣合同，询问终止期限、知识产权转让条款和遣散条款。它支持多达一百万个单元格，但一开始只显示 10 行，这样你可以在运行其余部分之前先修正提示词。

法律工程师在这些原语上配置新产品，无需编写代码。甚至 Wexler 的事实智能产品也运行在相同的构建模块上。

跳转到原语讨论 →

先是法律工程师，其次是前置部署工程师

Legora 大约九个月前在纽约聘用了第一位前置部署工程师：Di Qi，一位两次创业的 YC 创始人，曾在 Meta 从事搜索工作。法律工程师像高级用户那样配置产品，不编写代码。前置部署工程师编写进入生产环境的代码，构建与律所 CRM 或文档管理系统的集成，并将他们学到的东西反馈到核心产品中。他们仍然不接触客户数据。

当一个大而投入的客户签约时，Legora 会指派法律工程师与他们合作，并在项目需要时增加一名 FDE。Jacob 预计一年内会有一组轮换的 FDE，他们与客户共处几个月，构建所需的东西，然后继续前进。

跳转到前置部署讨论 →

走向何方

Jacob 认为，两年内大型企业将通过 Claude Cowork 等工具使用 Legora，而律所则直接在 Legora 内部工作。他不认为实验室会像对待编程公司那样切断 Legora。对于一笔 4 亿美元的并购交易，他认为人们仍然会想要 Legora。

跳转到预测 →

节目笔记

• Legora — 面向律师的协作式 AI 平台，Jacob 是那里的 CTO。

• Jacob Lauritzen — Jacob 的 LinkedIn。

• Legora 的 E 轮融资公告 — 5.5 亿美元，估值 88 亿美元，ARR 超过 2 亿美元。

• “智能体需要的远不止聊天” — Jacob 在 AI Engineer Europe 2026 上的演讲。

• “将 AI 连接到数十亿份法律文件” — Jacob 与 turbopuffer 的 Simon Eskildsen 在 AI Engineer 上的演讲。

• Legora 如何在 Modal Sandboxes 上并行运行 2,000 个智能体评估 — Legora 评估运行背后的基础设施。

• Legora 收购 Qura — Legora 于四月收购的斯德哥尔摩法律研究初创公司。

• Legora 正在收购 Wexler — 这家伦敦初创公司可从大型诉讼文件集中提取并核实事实。

• Claude for Legal — Anthropic 的法律连接器和插件，也是“实验室是否会进军法律领域”这一问题的背景。

• AIE Europe 回顾 + Agent Labs 论点 — Swyx 谈他在开场时提到的智能体实验室打法。

时间戳

• 0:00 冷开场
• 0:40 认识 Legora 首席技术官 Jacob Lauritzen
• 1:05 从斯德哥尔摩地下室里的弱者起步
• 1:54 Legora 如何从基于瑞典法律的 ChatGPT 成长为法律智能体
• 4:12 从助手到智能体的转变
• 5:23 Legora 使用哪些模型，以及为何加入模型选择器
• 7:48 当今的模型对律师来说够好吗？
• 8:20 九个月前智能体做不到的事
• 9:18 在模拟世界和含 10,000 个文件的数据室中测试智能体
• 10:07 评估团队与 Legora 的 100 名法律工程师
• 11:03 当评估看似不值得时，以及一次发布如何将引用准确率从 70% 提升到 99%
• 12:18 五到十年后法律实践可能是什么样
• 14:18 律所合伙人模式会存续吗？
• 16:40 律师助理和初级律师会怎样？
• 18:00 计费工时，以及早期法律科技为何未能达标
• 19:39 如今钱流向哪里
• 22:44 Legora 如何用自己的产品做收购尽职调查
• 23:59 瑞典与美国律所的区别
• 26:12 当你读不懂追踪记录时的产品指标
• 27:41 转述追踪记录，把失败归并为 10 到 20 种类型
• 28:42 为何数据隐私促使 Legora 把所有东西跑在 Azure 上
• 30:04 开放权重模型与模型套利
• 30:55 转录模型，以及 Legora 为何不用 ElevenLabs
• 33:33 智能体、表格审阅、项目与 Word 插件
• 34:24 律师如何使用表格审阅
• 35:51 为什么电子表格有效，以及从最初 10 行能学到什么
• 37:53 法律接待机器人如何在 Slack 中工作
• 39:11 智能体如何创建列表，列表又如何启动智能体
• 40:15 在这些相同组件上构建产品，以及收购 Wexler
• 42:37 前置部署工程师在 Legora 做什么
• 43:52 法律工程师和前置部署工程师如何为大客户做上线
• 46:43 前置部署团队未来一年的下一步
• 47:24 为何 Legora 抗拒构建 API
• 49:26 智能体能成为 API 吗？
• 50:12 300 斯巴达人幻灯片与保持 20 名工程师的计划
• 51:32 没人要求 Legora 下的赌注
• 53:05 为法律研究后训练开放权重模型
• 54:05 搜索、检索与后期交互
• 54:51 什么造就了好的法律智能体框架，以及为何起草依赖搜索
• 56:25 哪个模型写出的草稿最好？
• 57:03 幻觉与 Legora 的引用系统
• 57:41 律师会核对引用吗？
• 58:19 对百万 token 的合同用 MapReduce 还是一个大的上下文窗口？
• 1:00:16 获取匿名化示例，以及为数据收购律所的想法
• 1:01:53 为何 Jacob 不建议默认嵌入
• 1:02:44 律师会在 Legora 里工作，还是通过 Claude 工作？
• 1:03:26 模型实验室会切断 Legora 吗？
• 1:04:24 法学院与计算机科学专业奖学金
• 1:05:28 在纽约、斯德哥尔摩和伦敦招聘
• 1:06:09 为何大多数工作最终都会变成法律工作

文字稿

自动转录自修订版剪辑；人名和措辞可能有误。

0:00 人们一直在问我们关于 Mythos 的事，尽管我认为现实中很多法律工作并不需要 Mythos 级别的智能。律师助理，没了。对。初级律师，没了。我不需要他们。但实际上我们看到的并非如此，我们遇到过一个引用不正确的问题，然后我们就想，下一个模型版本就解决了。它从大约 70% 提升到了大约 99%。就像我们什么都没做，然后，很好。至少你在做一笔，你知道，4 亿美元的并购交易。你会想要 Legora。在公司余下的历史里我们就只做 20 名工程师，然后，我们会打败所有规模大得多的对手。我们现在有 100 名工程师了，感觉我们还是太小了。但我正在尝试的一件事是，我们的产品有多少可以就只是这个 agent，而不是其他所有东西。好。我们在演播室，请到了特别嘉宾，Legora 的 CTO Jacob Lauritzen。我念对了吗？Lauritzen？没问题。对。没关系。我不是西班牙人。怎么……这是丹麦语。对。没错。它有什么特殊来历吗？就……没有。就像 son，son of。之子。就像你有 son 和……对。所以是 Lauritz 之子。这就是我的名字。很好。我们时不时会碰到。你在 AIE 讲过几次，而且，显然，Legora 是史上增长最快的法律科技之一。对。你在开场前说了一些我觉得很有意思的话。你说你们的起源非常欧洲。嗯。尽管显然你们正在纽约和旧金山扩张。你们的文化感觉有什么不同？我觉得我们骨子里，可能对自己在做的事非常谦逊，因为我们从一开始就一直是弱者。没人相信斯德哥尔摩地下室里的一家小创业公司会，你知道，打败那个在美国远远领先于我们的庞然大物。所以我觉得我们一直是弱者，所以我们一直非常谦逊。我们一直都得为生存而战。我觉得这是我们随着自己也变得越来越……随着我们进入美国、在美国待得越来越多，不得不学会的一件事，就是要更勇敢一点，告诉世界我们有多棒，因为……这对我们中一些人来说，我觉得，并不是自然而然的事。

1:30 我有点想先从你们的产品开始聊，因为我觉得很多这类法律产品，你知道，它们都有点保密，就像，你知道，对。你不应该展示它。对，如果你能谈谈，比如产品长什么样，也许还有，你们是怎么走到这一步的？比如，是什么样的产品迭代让你们达到了今天的位置？我觉得那会非常有意思。对。当然。一切的开端是带有瑞典法律的 ChatGPT。好的。里面有个搜索工具。那真的就是全部了。所以那就是我们的起点。我们从法律研究开始，这基本上是个巨大的市场，律师们花大量时间弄清楚有哪些类似的先例案件，法律先例是什么，比如，你知道，之前的人在这些情况下是怎么做的？这极其重要。所以这一直是我们产品的一部分。基本上，我们是从一个智能体开始的，你可以提问，它会查询法律。那是个非常简单的开始。然后从那里，它扩展了。所以它在智能体能做什么方面扩展了。它现在，你知道，能非常好地起草很多东西。它能编辑 Word 文件。它能，你知道，把你的文件移走，整理一切，运行非常复杂的分析，我们还给它加了一大堆功能。所以我们的一个功能叫表格视图，现在这个名字在行业里被使用了，我们很高兴看到 Claude for Legal 用我们的术语来描述他们正在构建的东西。我们得谈谈那个。我们得谈谈那个。这本质上就是一种批量提取和批量审查大量、大量、大量协议的方式，你在尽职调查和融资等时候会这么做。

3:00 所以那是其中一部分。就像我们帮助律师更高效、更好得多地完成他们的工作。然后除了做工作之外，我们现在还比一年前更多地帮助编排工作。所以我们有不同种类的，我们有一个叫列表的东西，对我们来说有点像 Linear。我们有 intake，这是一种与客户协作的方式，我们还有 portal，这也是一种协作方式，你知道，律师对律师、客户对律师、律师对智能体、智能体对智能体，也许吧。我们在那里花了很多时间，因为只是……坦白说，你十年前或者甚至今天与律师合作的方式真的很痛苦，说实话，有很大的空间可以用好得多的方式来做。所以那些，我想，是两件事。就是做工作和编排工作。你们什么时候开始做或构建智能体的？所以，我的意思是，我们都……我们基本上经历了从助手到智能体的转变。对。我们这么叫它。对吧？我猜智能体……我不知道。我想说大概一年前。对。所以对了解 YC 2023 的人来说，这是个粗略的时间线。是的。我知道你是 '24 的 YC 创始人。

4:30 YC 24。是的。我参加过 YC '23。是的。Legora 是 '24。好的。然后……所以，有那么一点……这算是，稍微在……在 agent 真正爆发之前。没错。然后，使用模型显然改变了一切。是的。我的意思是，你知道，从某种意义上说，今天我们预览了产品。看起来确实……嗯，预览。我们搞了个私下的活动。嗯，我们会在 YouTube 上放个视频。它基本上就是给律师用的 ChatGPT。对。对吧？就像，非常，非常贴切地说，但侧边栏有很多不错的定制工具，比如表格视图，比如 intake，我真的很喜欢，还有一堆其他的。没错。就是这样。它就是同事或者 ChatGPT，只是真的、真的非常适合法律工作。而且……是的。工作流程，比如，面向企业内部律师，比如，查找法规的人。是的。所有这些。我们可以多聊聊那边的产品。是的。你们底层用的是什么模型？能聊聊吗？我是说，我们根据任务用一堆不同的。对吧？那就是……然后律师看不到这个。你们还是 agent？是的。嗯，我们在这上面来回讨论过。是的。就像其他人一样，我觉得。在 agent 里，主模型有个模型选择器，但有些工具我们用不同的模型，比如表格视图，而且，我们试着……我觉得我们发现最有效的是细分问题，然后随着我们细分任务来路由。但我们现在在 agent 里确实有个选择器。嗯。说实话，我不确定它会不会一直留在那儿。所以……是的。

6:00 是的。我的意思是，我对此有一点背景，因为我是 Cognition 的顾问。对。当我加入时……你知道，我关于什么是 agent lab 的部分论点就是，agent lab 理想情况下是一个特定领域的 GPT 包装器。对。对吧？就像我们我们我们运行……我们是领域专家。我们会关注你。我们会远远更多地满足你的需求，远超前沿实验室，并且我们会根据我们的判断给你前沿实验室中最好的。对。所以我们的工作就是为你做决定，因为你不是……你的工作不是……完全正确。我们会始终让你保持在帕累托前沿上。对。并确保它一直都很棒，你不必深入所有细节。因为，就像我经历过的那些事……正是说到这一点，如果你去找律师，问他们，哦，你要根据这个先例起草这份合同，你觉得这是 sonnet 高还是 opus 中等的任务？实际上，他们不会知道。就给我这个……我有这个模型。就，确保它能用。我们的时薪是一千美元一小时。完全正确。就像……让它能用就行。所以，是的，我最初就是带着这个想法来的。就像，哦，对。这就是 Devin 做得不一样的地方。而现在我们的模型选择器里有五个东西，包括 Fable 和 Opus。对。Astra。是的。而且人们想用那些花哨的新模型做实验。对。你……这是同样的吗？我觉得是。我觉得可能……在法律领域肯定比在编程领域少得多？工程。对。但肯定有人会想立刻就要表一，而且，你知道，人们一直在问我们关于 Mythos 和其他一切的事。对。对。尽管我认为，现实中，很多法律工作并不需要 Mythos 级别的智能。对。有

7:30 完全正确。就像，我觉得，基本上，你会说，好吧。我们会给你这个选项。你你要求这个，没错。但你的积分会消耗得比他们快10倍。是的。我本来会很喜欢……我们为引入这个功能争论了很久，最后我们基本上就妥协了。我们说，好吧。如果你想要这种程度的控制，是的。你知道，那我们就给你。是的。所以你觉得这些模型已经达到律师需要的水平了吗？就像，它们不需要再变得更好了？这是一个……我觉得这是权力分配的问题。所以，大概有60%的工作，是的。我们现在可以做得很好，你知道，从现在开始，就是成本和延迟的问题了。但还有剩下的部分，特别是对于非常复杂的分析，我们仍然需要更多的智能。然后我觉得还有工作范围的问题。就像，那是我们现在的工作，但还有Fort Lauderdale的工作，所以可能会随着智能而扩展。是的。我想象得到。早期，比如你们刚开始的时候，我猜，转向智能体的时候。嗯。或者构建智能体的时候，比如，你们用的是什么模型？我猜应该是Opus 4.6之类的？那应该是……是的。Sonnet 4.6、Opus 4.6大概是对的。那时候智能体不擅长什么？而现在它们好多了，尽管只过了大概九个月？子智能体委派是其中之一，我们现在已经让它运行得很好了，比如用于扇出型检索查询。现在对我们来说效果极好。以前这很难。我们基本上追踪……所以我们有一个团队专门做评估，我们追踪所有模型在不同实践领域中的表现，这些领域是法律的分支，以及所有这些领域中的不同任务。所以我们基本上有一个大的热力图，然后我们可以看到它们的变化，通常它们会改进大部分东西，但实际上有很多模型发布中，它们改进了一些，在其他方面也有进展。好的。而这实际上发生的频率比你想象的要高得多。

9:00 比如，那些任务具体是哪些？你们是怎么跑大量评估的，你熟悉吗？我想问的是，你们关注的那些不同子部分是什么？是的。所以，有不同的框架性内容。基本上，我们有不同的世界，本质上就是 RL 环境，也就是这样的……因为律师或多或少总是在项目中工作，所以就像是，这里有 10,000 个文件的数据室，你在做尽职调查，最终一份 GRIP 报告长这样，它包含所有这些红旗警示，而且不包含那些奇怪的东西，我们希望它简洁，等等等等。这大概就是我们构建它的方式。所以有不同的任务，其中一部分是起草报告。比如，草稿看起来好吗？它包含所有正确的内容吗？措辞合理吗？分析合理吗？还有一部分是发现红旗警示，也就是在那之前的分析，所以我们可以稍微细分一下，这就是我们跑评估的方式。有意思。等等。你们的评估团队是什么样的？比如，你们会雇律师来做这个吗？是的，是混合的。我们有工程师，也有律师，是一个团队。所以现在大概有三个工程师和三个律师，然后我们有一个我们称之为法律工程师的人才池，也就是在大律所工作过三四年的人。通常，他们可能有计算机科学学位，非常懂技术，然后他们来找我们……因为他们想帮助改变这个行业。

10:30 他们是大律所里的IT人员吗？还是不是。他们是大律所里的律师。他们是大律所里的律师。拥有计算机科学学位。是的。我的天。这是一个维恩图，那……对，没错。那就像是我们最难招到的人，但他们同时也是如此强大的力量倍增器，因为我们可以借助他们来做评估相关的工作和产品开发，就像你有一个100名专家的池子，他们每天都使用产品，每天都去和客户交谈，而且，他们还亲身经历并一直经历着这一切，我们就借助他们来做评估相关的工作，并帮助我们塑造产品，这真是一个巨大的优势。我很好奇，你们当初是怎么组建那个团队的？评估团队在某个时候是从助手智能体团队中衍生出来的。我觉得直到最近，一直有那么一个阶段，说实话，做这件事真的不太值得，因为所有模型都在变好。所以问题就是，我们是想把大量时间花在真正复杂的评估上，还是只想构建……因为构建更好的运行框架能带来很多收益，并且顺应一切都会变好的趋势，而一切确实都在变好。嗯。但是，是的，每两三个月，你就会得到一个不同的模型。对。没错。我是说，我们让它通过。对吧？没错。我是说，我们遇到过一个这样的问题，比如它不能正确引用，所以很难跟进，然后下一个模型版本就解决了，从70%提升到了99%。就像我们什么都没做，然后，太好了。对。也许真正的工作是，你知道，保持所有数据私密，让它可打标签、可排序，添加新功能，比如表格视图。那是，你知道……你是指超出ChatGPT之外的功能吗？是的。但显然，现在你们也在做评估。我猜你们对开放模型的使用也在增加。我们可以谈谈这个。所以，是的，我不知道我在这里说什么，除了，你知道，工作是什么？工作也许不是……在早期，主要不是做评估，因为那主要是向律师展示模型能力。

12:00 是的。其中很大一部分就是弄清楚，有了这些东西，法律行业在五年、十年后会是什么样子。比如，编程领域可能领先一两年，我们可以稍微参考一下，但是，那些基本构件是什么？人们如何工作？如果不是靠一封200条回复的邮件线程、来回传五个Word文件，你们如何协作？那会是什么样子？而这甚至不一定纯粹是AI。那只是打造一个更好的产品体验。是的。并且要确保你在做这件事时带上审计日志、数据留存，以及受监管行业中所有那些真正重要的东西。然后还有AI那部分，就是让工作更快更好，还有主动型智能体，在事情进来时做出反应，这样你就不必，你知道的，事事都手动启动。所以我认为很多工作就是弄清楚我们认为五年后会是什么样子。如果，你知道的，模型能力持续提升，价格持续下降，我们能做什么？你能不能登录进去，就像一个指挥中心，就像，你需要对智能体最近一直在做的这五件事做出反应，然后审查、检查并改进系统？也许那就是我们要去的地方，或者那正是我们要去的地方。是的。是的。我本来想问，你能不能更深入地谈谈这个？比如，是的，几年后法律行业会是什么样子？

13:30 我得先声明，我并不确定。我是说，谁真的知道呢？但我认为我们可以多看看编程领域。我认为所有律师都会比以往高效得多。他们能以更低的成本、更高的质量完成更多工作。我认为这个职业本身、工作本身都会大幅改善。会变得更多……我认为律师会把更多时间花在他们当初成为律师时想做的事情上，比如判断什么是合适的风险画像、什么是可管理的风险、什么是……他们所有的判断、战略判断，以及与客户合作，他们会做更多这些，而少做那些像在大堆文件里翻找确凿证据，或者做许多律师一直在做的那些琐碎又烦人的工作。你觉得合伙制模式会发生什么？你觉得它会保留下来，还是说会怎样？我……其实就在上周，我认真思考过这个问题。是的。就是合伙制模式……我不想讲太多细节，但合伙制模式之所以存在，某种程度上是因为这些公司唯一拥有的资本类型就是人力资本。所以，不像我们或者软件工程公司或者制造业之类的。你有实物资产，或者某种随时间积累的无形资产，它们为股东带来回报。但如果你身处专业服务这样的行业，咨询公司等等也是一样，你所有的价值都在你的人身上，而你并不能真正拥有人力资本。你知道，你不能……你知道，奴隶制已经废除了。你不能拥有人，但你可以租用他们。你可以付钱给他们。所以合伙制本质上是一种结构，让人力资本成为公司的所有者，这样他们就会留下来。是的。这会改变吗？我不……它不一定非得改变，但我认为我们真正想用律师做的事，其实是希望律师能够……律所能够建立某种无形资产、某种持久资本，比如你可以建立一个学习你工作方式的系统。

15:00 现在很多公司都在考虑，比如，有前律所的做法，我认为我们可以把它编纂成文，我们可以构建一个系统，无论是自我改进的知识图谱还是别的什么，还有先例文件和文档，其中有一种能产出极佳成果的工作方式，那可以成为他们的知识产权。所以这就像是一种将人类专业知识和判断力编纂进系统的方式。我觉得这……现在我只是在完全胡扯了，但比如，那是我们想要帮助赋能的事情。那这会改变合伙模式吗？因为激励机制不同了。在合伙模式下，你只需要带来更多客户，而你不想把带来客户的时间拿去编纂你的信息，基本上是这样。嗯。因为，比如，你获得的回报来自，你知道的，吃你杀死的猎物或者做成这笔交易之类的。这需要稍微改变一下。我们需要设计一种激励结构，让合伙……合伙人被激励去编纂东西，为公司构建资产，但现在没有，因为一旦他们离开合伙关系，他们就无法从自己构建的资产中获得任何分红。

16:30 是的。所以有一个……对。我觉得整个商业模式是……我们拭目以待吧。对。对。现在一切都存疑。对。我另一个实际的看法……你知道，在合伙层面，那像是行业的高端。嗯。实际上，我的看法更多是关于低端的。对吧？对。那里发生了什么？律师助理没了。对。对吧？比如，初级律师没了。我不需要他们。比如，那实际上不是我们看到的。所以，是的，是……我觉得是……我知道。你会说我们在工程领域也看到这种情况吗？对。所以初级工程师真的有点完蛋了。你基本上得……从大学退学时就已经完全成熟，否则你……你不会成功的。我觉得我……我为了喜剧效果有点夸张了。但是，比如，是的，我认识很多律师。他们从律师助理做起。他们去法学院，所有这些。对吧？而现在他们不……他们不被需要了。他们真的就是不被需要了。对。对。是的。这……合伙模式发生了什么很有意思，比如金字塔。我觉得总的来说，很多律师，你仍然需要你的……你需要下一代。至少对工程来说，我的想法是，你今天有一个好工程师，他们的价值甚至比两年前高得多，因为他们能产出多得多的东西，比如，他们很优秀。我觉得法律领域也是一样，如果他们优秀，他们实际上能做很多非常出色的工作。所以我觉得更多的是，真正优秀的律师或初级律师价值高得多。对。一直都是这样。对吧？对。似乎甚至更加……但这是，是的，更加两极分化了。

18:00 是的。我其实对这一点很好奇。所以，整个法律业务基本上是按小时收费的。嗯。所以，是的。你知道，如果现在每个项目都能……是的。快得多，那会不会便宜很多？就像这其实是……说来有趣。我当时在看 Max 的 YC 申请，帮他进 YC。当时它叫 Leya，是 YC。而这就是我当时关注的一点。我当时想，而且好奇，Leya 在丹麦语里是某个意思吗？不。瑞典语。瑞典语？不。它也没有任何含义。有个……好吧。好吧。有个特别好笑的故事，在……我想是一家西班牙报纸在我们早期写了关于我们的报道，Leya，然后他们解释说这个缩写是“legally efficient Yoda assistant”（法律高效尤达助手）。为什么是尤达？是的。我不知道。所以我就想，为什么为什么是它。你看，幻觉不只是来自 LLM。不。我觉得记者也会产生幻觉。但是，不，它没有任何含义。所以他写了申请。他写了……是的。而我对他的反馈是，你知道，人们已经尝试过一百万次了。法律科技从来就没成过气候，因为律师没有动力去……他们为什么要更高效？他们会赚更少的钱。这完全说不通。但我认为律师确实愿意采用这个的原因是他们明白形势的严峻。他们知道，商业模式和一切都面临压力，而且他们需要改变，因为竞争压力太大了。计费模式本身，我认为也会改变。我们已经……我们已经看到，尤其是在美国，很多东西实际上按项目收费而不是按小时收费，尤其是这些，怎么说，低端一些的东西，比如，不管是什么，比如审查之类的。老实说，有些甚至是免费做的，有些只是按固定费率定价。那么，在哪里

19:30 那钱是从哪儿赚的？是……因为在战略业务里。对。我感觉你们聊的很多都是并购，比如，那是最容易举的例子，钱都在那儿。哦，好吧。好吧。诉讼也是。大业务还在那儿，而且非常有价值。所以他们会花……律师会把更多时间花在那儿。客户关系，也超级重要。像 CRM 那样？不。就是花更多时间和客户待在一起。比如，很多律所会，或者说历史上基本上免费做事情，就为了维持和客户的关系。对。对。所以现在他们可以这么做，但不必在这上面亏很多钱。我以为我以为我只是……我得付律师钱就为了让他当我朋友。就像，在这个 对。不就是那个聘用定金的事吗？对。对。那个……那是 你跟我说我可以免费做？就像 对。你只需要找到对的律师。对。行吧。酷。或者 Latent Space 得发展得大得多。我不知道。对。对。我们在努力。你知道吗？对。所以……好吧。所以所以所以你是说，你知道，显然，战略业务和所有这些高附加值的东西还在，但我们的律师费并没有下降。但你也说了律师助理不受影响，或者，就像，他们只是在转移。而这也是我们在……Cognition 上担心过的事。就像 对。人们担心那种措辞，比如，我们会取代你的初级工程师，因为没人喜欢那种说法。但实际上，是的，就像，其中一部分确实会发生。其他初级工程师拥抱它，他们变得更有生产力，这就像你刚才说的。所以我猜，就像，这个角色或者这个工作有没有一个新术语，正在……正在你的客户中流行起来？

21:00 你是说那个超级AI派的初级律师投票吗？我还没找到任何相关信息。也许我们应该造一个词。这难道不合法吗？这就是我们的……而且现在也成了一个行业话题。是的。是的。CSJD们。没错。是的。是的。是的。是的。也许这就是……还有那些最适合做这类事情的人。我想到了那个贬义词“肉身代理”，就是你坐在机器前，输入别人让你输入的东西，然后你重复机器让你说的话。对。但是，我确实认为一个非常优秀的肉身代理就像……嗯，你很了解agents，你也很了解Legora。对。而且你知道如何，就像，这是我的工具箱，你知道，每个行业都有工具箱。对。我可以用我的工具去做你需要我做的事。但我想那你就不是真正的代理了。对吧？你实际上只是在做有意义的工作。是的。就像我不再……就像，你知道，嗯，我会谈谈表格审查，因为那……那是一个经常发生的事情。我有成百上千、数百万、千……上千。我想我们最多能处理一百万个单元格。在一个单一的……那很厉害。对。我们应该谈谈那个表格和窗口化。是的。至少，你知道，我有，就像……我在处理一个大案子。我有一百万份文件。我把它输入进去。通常，我会扔一对……扔，就像，一队律师助理锁在房间里。在那里，所以，就像，凌晨4点。就像，那……那不需要发生。对吧？因为现在他们可以提取它，你可以去重新提示一切。嗯。所以，就像，是的，我想现在我不需要律师助理来做那个了，但是，就像，一个好的、超级AI派的律师助理会做别的事情。

22:30 你知道吗？是的。对。没错。不管是什么。他们可以做更多事情，或者把更多时间花在他们以前没时间做的事情上。或者真的去睡觉，谁知道呢？不。我有个问题。所以你们收购了一家公司，Qura。是的。是这么念的吗？不是。你们用自己的产品来做并购？是的。我们一直这么做。那具体是怎么运作的？比如，你能稍微谈谈吗？可以。不。效果很好。我们经常这么做。我们的法务团队是……我是说，intake 就是和我们的法务团队一起搭建的。因为现在，我们有一个 Slack 工作流，大家把东西都扔进去，然后他们说，这很烦人。对吧？而且效率低，所以就觉得，太好了。我们应该用 Legora 来做这个。你能稍微谈谈那个吗？比如，那个流程是什么样的？当然可以。所以它是……很多尽职调查我们自己就做了，因为我们可以用表格审查和其他工具来做。我们仍然会有律师介入，嗯，来评估某些风险，或者，你知道，有些……所以 Qura 很简单，因为它全在瑞典，但你知道，我们在加拿大和澳大利亚各做过一个，所以澳大利亚那边有薪资问题。好。我们要不要找人来更战略性地看看这个？所以在那里，我们仍然会用律师来处理战略部分，他们可以真正成为 sparring partner，在很多方面帮我们很多，比如弄清楚如何以正确的方式构建这个。但很多更琐碎的事情，我们其实可以自己做。所以，很多早期的事情我们会自己发现，而且我们有过这样的案例：我们发现了某些东西，那是个危险信号，然后我们就踩了刹车。你能稍微谈谈其中任何一个吗？不，我想可以。好的。早些时候，你说你……你的早期客户是瑞典的？嗯。比如瑞典律所？是的。你有没有看到和瑞典法律 versus 美国律所合作之间的差异？嗯。那种事情？而且你们主要和大型、大型律所合作。对吧？

24:00 嗯，我们也是……小型律所也一样。哦，我们确实是从非常非常大的律所起步的，但50名律师的律所也能获得很多价值。是的。那么，你在与瑞典的律所合作时，有没有看到差异？是的。与美国律所相比，也许甚至，嗯。我不知道，亚洲的律所？是的。是的。我觉得欧洲的律所行动得稍微慢一些。美国律所非常前卫，行动非常快。我觉得在美国公司中，这件事在议程上的优先级也高得多，比欧洲公司更甚。这就像是一件战略性的、超级重要的事情。我们需要在这里做很多事。美国公司，无论是企业还是律所，通常也更有意愿去定制构建东西。这是他们都想做的事情。就像，嘿，我们想和你们一起构建这个巨大的东西，并以任何方式构建它，而欧洲人则更像是，我们就直接用现成的。他们想自己构建的东西有什么例子？集成到他们自己的……比如，一些客户构建自己的CRM和自己的文档管理系统以及自己的各种东西，他们想构建这些，然后他们想构建触发器，比如，你在Salesforce中进行审查，由于某种原因它转到某个人那里，他们做了一些事情，然后它进入Legora，然后又返回。所以这是简单的一端，还有一些非常雄心勃勃的，比如他们想和我们一起构建一个全新的产品，而你知道，我们真的做不到。是的。是的。但这绝对是一个现象，美国公司真的比欧洲公司更想构建自己的东西。

25:30 而欧洲的客户则像是，嘿，你知道的，他们会给你产品建议或者……对，当然。我的意思是，我们和所有这些客户都有很好的合作。对。所以他们会说，嘿，这个很烂，这个很棒，我们想要更多这样的，然后我们就会直接构建一个满足这些需求的产品。好的。所以他们不觉得自己的业务面临生存威胁？我是说……而美国的客户则有这种感觉，或者……我不确定这是不是他们想要定制化构建与否的原因。我认为他们双方都知道这对他们公司的成功和企业的成功极其重要和关键。所以他们……这双方都极其重要。我认为只是实现方式不同而已。好的。另一个问题，我想也许你想提出来的是，比如产品指标。比如，你怎么知道我们在这里确实做得不错？对。对。你怎么看待这个问题？我猜这也和评估有关。所以我们有我们非常关注的常规产品指标。人们是否在我们的产品上花了很多时间？他们是否似乎从中获得了很大的价值？他们会续订吗？他们会经常回来吗？对于企业软件来说，我们的数据非常好，比如我们的DAU/MAU，以及每月在产品上花费的时间都非常高。然后我们还会做一些……我们也会做在线评估，就是试图大致弄清楚，我们是否解决了这里的问题？就用非常便宜的LMS地址，试着有一个在线指标，然后我们也可以在做新功能发布时使用它。我们可以直接按功能标志来比较，好的，它是改善了还是灾难性地下降了？因为实际上有一件可能很有趣的事，对我们的业务来说很困难的是，我们基本上不能查看任何追踪记录。我们不能查看任何数据，因为全都是超级机密的。这在工作中极其令人沮丧，因为你基本上不知道人们在做什么。所以就像，这里有一个智能体，它可以做很多了不起的事情，而我完全不知道人们实际在做什么。

27:00 我本以为你们会和律所签某种协议，结果他们说，哦，但愿如此。是啊，但愿如此。不。但问题是，他们手里的很多数据甚至都不是他们自己的。对吧？那是他们客户的。哦。而且高度机密，所以我们不能看。所以基本上，我们有一个评测团队，试图推测我们认为每个人都在做什么，并把它构建到评测集里。哇。所以这只是业务中一个超级烦人的小毛病。你能做改写吗？比如，ChatGPT 有个斜杠反馈功能，嗯哼。它能直接完整地设定其完整轨迹。嗯哼。但显然，那对你们来说……那是不可能的。嗯哼。但你可以用 LLM 来改写，比如从真实的东西出发，对。造一个合成的东西，差不多接近，但改掉所有名字，改掉所有细节，但仍然，对。是啊。我们不能……有……我是说，总有一个范围，对吧，比如如果你一路改写到只剩三个值，然后你选其中一个，那显然没问题。如果你只是去掉名字，那也许行也许不行。是啊。就像，我们一般选最安全的方式。是啊。因为，我们尽可能限制自己，因为你知道，应该完全没有风险。是啊。但有些情况是，好吧，我们知道失败模式大概是这 10 或 20 种，所以我们可以把它归类到其中之一，那就是，对。一个有用的信号。我们可以把它归类到任务类型和专业领域，然后我们就有了概念。这是我们一直试图想办法聪明地去做的事情。

28:30 另外，在隐私方面，我猜，即便是两年前，要让律师事务所接受这个也一定极其困难。是的。但是，就像 对。他们会怎么看待自己的数据被发送给 Anthropic 或者 对。对。对。这一定是个大问题。我们所有的基础设施都在 Azure 上。对。主要就是这个原因，因为，我们刚开始的时候，律师事务所说，AWS？不行。就像 对。绝对不行。不信任 AWS。对。对。现在不一样了。不。但它……当时有亚马逊、谷歌。我们不能信任他们来处理我们的数据，所以我们……基本上，我们不得不把所有东西都托管在 Microsoft 上，因为他们已经有 365。哦，所以现在他们能接受 Microsoft 了？没错。因为他们已经完成了，比如，针对他们所有文档和所有 Word 之类的安全审查等等。所以，Microsoft 在他们眼里是获批供应商，因此我们不得不把所有东西都托管在 Azure 上，而过去几年这种情况变了。所以，现在人们明白了，好，我们需要上云，我们需要做这类事情。当时还有更多人在谈论本地部署。那也完全消失了。人们明白，你应该直接在云上做，而且它是安全的，而且可能比你在做的更安全。对。所以这变化很大。但我当时 而且顺便说一句，这才三年，所以，实际上就像 对。是 对。对。这是个巨大的转变。这 这 这 这很好。我是说，我为你们高兴，但是，对。我是说，我不指望，你知道，律师事务所……法律行业在过去十年里不知怎么地忽视了这一点。对。对。我觉得 我觉得我们需要 AI

30:00 给大家敲响警钟，让大家明白我们需要稍微改变一下方式。好的。好的。那么，还有，现在开源模型真的越来越好了。嗯哼。所以，是的，你是怎么考虑这一点的？是的。我们只是在想，就像你说的，让我们的客户始终处于帕累托前沿上。是的。还有，就像所有模型的地图，以及它们擅长什么、它们的延迟、成本、治理以及区域可用性，我们如何在这所有方面进行优化？所以，一些开放权重模型在某些任务上很棒，那我们就在那些地方使用它们。有些会进行后训练，还有些就只用前沿模型。是的。你称之为模型套利。是的。你有不同的最爱。你你对此做过一些研究，年初时你坚定地站在 Anthropic 一边。是的。Grok 进步很大。是的。你想举一个整体排名不高，但你想为它打 call、说它出奇地好的模型例子吗？是的。我觉得不是整体好。Gemini，早期的一个 Gemini 版本，是的，在某些类型的转录方面极其出色。是的。还有说话人归属。所以我们用它来做转……转录，实际上。你们有……是的。你们为什么要转录？Granola？我们没有……我们实际上可能会构建一个类似会议的东西。是的。但这只是，比如，语音转文字、文字转语音，就像任何其他有这个功能的应用一样。而且我们实际上也会转录文件。如果你上传听证会之类的……哦。我们会，比如，转录它们，把它们转成文本，这样我们就能对它们进行所有分析。没有 ElevenLabs。出于 DPA 原因没有用 ElevenLabs。和数据处理的协议一样，我应该说。所以，比如，我们的数据处理协议上供应商很少。是的。

31:30 因为我们只需要先把它保留下来。完全正确。我们需要在数据流向的任何地方都保持极其严格。所以我认为，不，这其实是 Gemini 和 OpenAI 这类平台的优势之一——它们会说，你来找我们，我们拥有你需要的大部分东西，这实际上非常有价值。即使它不是最先进的也没关系。只要它对所有任务来说基本够用就行。是的。那谁还在乎呢？是的。就像，对。不。绝对如此。我其实还应该特别提一下微软的转录模型。他们可能想要 MAI-Transcribe？是的。好的。它很棒。好的。它比旧的 Gemini 更好。是的。是的。是的。他们确实取得了一些不错的成果。我不知道……甚至不知道，就像……我觉得，通常它们全都在 Arena 分数上排前二、前三、前四，这就够好了。是的。完全正确。而且你有全套治理机制，它极具可扩展性，那大概就够好了。是的。我想说，到了这个阶段，我们的……基本上语音转文字模型已经好到你会觉得，哦，这里或那里错一个词，如果它出错了，那也……不？不？不。当然。就像，我做过很多次了。尤其是在法律领域，有一些……我们遇到过这种情况，我想是……我忘了是不是在澳大利亚，法庭上对某个人有某种特定称呼，而他们会一直把它转写成 condom。哦。所以那里……是的。有些东西是你不希望在那里出现的。是的。但是……所以通常，你会在上面跑一层 LLM。是的。然后你提取一些关键词，再用这些关键词重新跑一遍转录模型。嗯。这大概就是我目前的工作流程。是的。但是，是的，如果你……如果你只是在大规模场景下做这件事，你会在任何不是日常普通对话的领域里发现大量大量的转录错误。

33:00 是的。绝对。如果里面有任何术语，是的。那就会很难。是的。比如，我觉得 Whisper 和 ElevenLabs 仍然把 Claude Code 转写成 Cloud Code。是的，而且，就像，是的。我实际上遇到过这种情况。非常常见。是的。所以，就像，这就是你识别它的方式。还有，就像，有很多需要改进的地方。是的。绝对。我确实想稍微谈谈代理产品方面。所以我们已经覆盖了一些，比如，顶层的东西。对吧？我们已经命名了 job tabular review。嗯。我们命名了 jobs intake。是的。而且你还有一些我们甚至还没触及的其他东西。但我只想覆盖两大块，我们称之为，就像 是的。是不是……那是不是可以说它们是两大块？Agent 和 tabular review？还有我们的 还有 projects。大概是 是的。是的。还有我们的 Word 插件 好的。也是某种……因为那个……很多人在 Word 里面工作，所以我们的 Word 插件是一个巨大的……还有 Outlook 插件也是。是的。所以我只想覆盖，比如，每个人必须知道的大块。是的。所以 tabular review 基本上就像是扇出，比如，横跨每个文档的大量内容。你可以对所有文档问同一个问题 完全正确。在表格上 是的。然后来回工作。然后可以 是的。百万很令人印象深刻。有什么……还有其他，比如，工程考虑或性能方面的事情吗？比如，什么……这难在哪里？在我们做那个之前，你能不能，比如，走一遍，比如，对律师来说用户体验是什么？然后，比如 好的。实际上，想用表格视图？是的。是的。比如，所以，比如，他们在做什么，比如，用 tabular review？是的。然后我们可以进入那个。

34:30 当然。是的。是的。所以他们……通常……我的意思是，一个很好的例子就是尽职调查，对吧，比如我们需要审查所有雇佣合同、所有供应合同、所有类似的东西。所以雇佣合同，你把一万份雇佣合同放进去，然后你……就像，每个单元格是一份雇佣合同？每一行是一份雇佣合同。然后对于单元格，你基本上就是提问。所以，比如第一个问题……第一个……不，抱歉，是按列。所以第一列可能是，终止期是多长？然后它就会为所有人填写。是三十天还是什么。下一个问题是，是否有知识产权转让条款之类的。再下一个是，比如，多少钱，你知道，如果我们解雇他们需要付多少钱，或者类似的东西，比如他们拿多少工资？然后它就会把整个东西填完。你也可以直接让智能体来做这件事。比如，如果你直接把一万个文件丢给智能体，说，对这个做尽职调查，它就会启动一个表格审查，运行所有内容，等它完成，然后分析结果，然后它可以高亮，比如危险信号。好的。这个……CEO的薪酬高得离谱，或者有这种奇怪的奖金结构。好的。然后，比如，显然，我们需要看这个，然后智能体可以据此起草一份备忘录发给客户，或者它可以只做审查，然后让，你知道，律师、用户，就说，好的，让我们看看这个，这些是危险信号。还有协作幻灯片，你可以在上面评论供其他人查看，等等。那你为什么选择这种，比如电子表格格式？是的。就是好得多……它超级容易操作……在里面工作。很容易快速获得整体概览，了解情况并进行审查。所以我们生成的所有内容也都有指向源文档的引用，所以你基本上可以超级容易地审查它。如果你只是想确保一切正确，你也可以，比如，高亮单元格，这些是已审查的或什么的，这些是被标记的，你可以评论和协作。这比我们尝试过的任何其他形式都容易得多。是的。

36:00 我得说，电子表格这种形态在某些领域很有吸引力，但不知为何一直没有真正普及开来。嗯。我……我觉得这很奇怪。比如 Clay 就是 GTM 领域的另一个例子，你知道的，以电子表格著称。是的。你们……我不太确定还有没有别人在做大型电子表格 AI 这类东西。没有。没有。之前有个 V7 之类的，好像尝试过推出……还有 sheets 之类的……即使在金融领域，我也说不上来有哪个顶尖名字是做电子表格的。就是真的非常……对。不。我同意。我觉得这是个很棒的……如果你有 fan out，你做完全相同的事情，然后你……你在提取内容，这真是个绝佳的形态，能让你理解正在发生什么。你有没有发现，你必须导出到 Excel，还是人们乐意待在你的电子表格里？人们乐意待在那里。你们用的是 AG Grid 还是自己的？我们确实用 AG Grid。AG Grid。那似乎是领先的那个。我是说，他们做这个已经，我不知道，十五年了。对。对。而且他们知道怎么……对。所以所以……好。对。我是说，我对这个……电子表格的角度很满意。我是说，我觉得从工程角度唯一其他有趣的事情就是 fan out。对。工程师们也许能……他们很擅长理解权衡，比如，好吧，在你对一百万份文档使用 fan out 之前，也许先在两份上测试一下。

37:30 Mhmm. Yep. And... Yeah. Yeah. Does that work before you go nuts? Yep. Do they do that? Yeah. They will. Our tabular view actually will run the first 10 rows. Yeah. Just check. Right? Yeah. Does this make sense? Did it did it show us what we thought it was gonna show us? Yeah. That's a... That's really good. Oh, but also for people, when people build this, it's just really good for them to iterate quickly on the 10 rows until, like, they have a... They're getting the results that they want, and then they can go ham. Yeah. I am happy to move on to the next thing, intake, which is your Slackbot. Yep. Yep. Everyone has a Slackbot. What's different about yours? So ours is just legal specific, 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 kick off an agent that then adds a task to our list. So we have this list thing, which is like linear, for for... You know, that's the closest equivalent, and so it will add it to a specific intake list, and then lawyers and agents can go into 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 legal team in a big corporate. We can kick off agents for them, we can collaborate on them, and then we can just like mark them as done, and then it gets sent back in Slack. So it's more of a... It's not just like kicking off an agent, it's more of a like, I don't know, storefront thing where it's like, hey, here's the ticket, I want this thing reviewed. Okay. Now it's not... Here it is. It's back. No one needs to change anything, and the legal team just sits in Legora and, like, manages the agents and everything there. I think the the data structure for this kind of thing is really interesting because it's, like, basically the inbox, right, for all these kinds of queries that can potentially translate into a thing, into something else, into And, something like, I I don't know. Is it hard to integrate all these with all the other features, or do you just not worry about it?

39:00 It's... No, it's not. I think we have some primitives that work really well. So, like, lists is a great primitive because it's essentially... It's extremely flexible. Also like Notion database. Yeah. A Notion database. It's like a Notion database, and so you can basically configure it for whatever you want, and we, of course, invest a lot into making this super scalable and work really well, and you can have triggers on them, automations on them, and it's like a great glue to glue everything together, because then you can kick off an agent run based on a list if something happens, and then that comes back and populates a field or whatever, adds new documents or whatever it is, and so it's like just like you might coordinate a bunch coding agents with linear or some sort of task management tool, we can do it similarly with lists. And so agents can create lists, and lists can create agents, and agents can read lists, and so it's like, the agent swarm comes alive. Yeah. Do people get excited or overwhelmed by that? You know, like, I I feel like Yeah. This is basically end user programming. You're... You know, you can let people set up crazy automations. Some people get super obsessed by it, and they become, like, like, you know, it'd be cool to have, like, Yeah. We have influencers. Yeah. Is that worth it? Too overcomplicated? 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 our legal engineers to basically build a lot of products extremely fast. So you can build custom fund management dashboards. You can basically build that on lists with your own generative UI, then you basically have a new product that some people are gonna love, and we can have a marketplace of just a bunch of specialized products that we can scale super quickly, because all of our legal engineers can just build new ones. If they're out with a client, oh, you want your own? Easy. We'll just fix one for you, so it's like a Lovable inside Legora a little bit, and if we don't wanna expose it, that's also how we built our own custom feature. 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 for a lawsuit or whatever, and then we extract facts from those with like named entities and dates and whatever, and then when you have all the facts, you can basically hold them up against each other and see which ones are corroborated and which ones are, what do call it, disagreement.

40:30 They, you know, and that's extremely powerful, because then you can also transcribe a court hearing, and you can like, oh, he said this thing, but actually, the email over here says that he was not there. And it's like, if you see it live, it's like so fucking cool Yeah. And that we can also build on this primitive. And so, like, we can build a lot of really cool things on this one primitive, basically. That's how we think about it. It's like we have to be... As we scale the company, we just have to solve so many things, and like, so so I think a lot about how do we build a core primitive that we can scale to to many different end products and create very customizable experiences. Okay. So you have... What what core primitives do you have? Let's just restate for for people. This a core one. Yeah. Oh, it's core configurable one. Yeah. Projects Yeah. Basically containers of files, file systems. Yeah. The agent, of course, you can kick that off and run that in very different configurations.

42:00 Do you have a name for the agent, by the way? No. We don't. No. Okay. Yeah. No. You mean, like, we called it, like, Leya or it's like we gave it a name? No. Yeah. Yeah. Leya would be cool. Yeah. Yeah. People used to talk about Leya as, like, an a named entity. Yeah. But, yeah, we we stopped that. Okay. Maybe I'll bring it back. It might be confusing. I don't know. So list, Tabular agent review Tabular review. Which, like, we're considering is that actually an instantiation of... Like, you can take this as far down as you want. Right? But those are probably the big the big ones. Yeah. Yeah. So I actually wanted to talk a little bit about, like, FDEs because this sounds kinda like Yeah. That, and I think Max has talked about that a little bit. That, like, okay, when you onboard a new, like, big customer, you wanna get them value, like, ASAP so that, you know, they stay on Exactly. Stay on Legora. Yep. Yeah. How has that evolved? Like, when did you guys start that forward deployed team? So we hired our first forward deployed engineer. That was our first time in New York, also YC founder, nine months ago maybe? I'm not actually sure. They considered legal engineers or no? No. Okay. True engineers. But we do... It it is something that I think about is, like, how do we exactly enable that at scale? 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 to, 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. It's like almost a first line, second line defense, whereas, 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 customer situations or whatever, 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 Can with

43:30 you walk through, like, an example? Like, okay, so you just got you just got this new client, like, what's step number one? Like, are you guys like, okay, hey, we have a forward deployed engineer for you guys, they're gonna go build Yeah. Some kind of product for you, like, how does So that it's very different client to client, right? Yeah. But if it's a big client and they're super engaged and they like want... They have all these dreams of things that they would want to do, or they already have... Typically, they have already tried to build something and it's failed, and they're like, this is what we... This is a problem that we'd like to solve, 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 a legal engineer, and some of that will require a forward deployed engineer. What is that separation, I guess? If you could, like, talk about that a little bit. Legal engineers configure the product as a power user would. They don't write code. Yeah. Yeah. And a forward deployed engineer writes code into production, basically. I guess that's the the Yeah. What kind of background do the forward deployed engineers normally have at the He said, YC founder. Yeah. Founders, regular engineers,

45:00 old Yeah. Yeah. D was your Yeah. Exactly. D was our first. Yeah. Two YC companies and worked on Search at Meta. Yeah. She's awesome. Okay, that's a high bar. She's great. Yeah. Yeah. First first boots on the ground in the US. Yeah. So what are some examples of, I don't know, workflows or things that these people are building for the clients? Or do you guys have, like, oh, these are like things. You know, there's a couple use cases that, like, all the law firms are like, you know, this is the first thing that our FDEs are gonna do when they when they go in. It's very different. Okay. Some core workflows everyone have, and we can just build in Legora, and that could be anything from, like, this is how we handle these types of NDAs or whatever. And then it's just like, you activate it, and it's more like skill building, really, for Elise. And most of the FDEs, that's more like, there's something that we can't do yet, like we need some more flexibility in some of the primitives or whatever it might be, or we just have this really complex system that we need to integrate into, and then they'll go out there and they'll build the integration against our APIs and maybe expand our APIs or whatever to make that work. And how does the, like, legal structure work there? Because you said you guys yourselves can't even work on deals. Yes. Yeah. So, like, how do they work on client projects? You mean the law firms, how do they work on client projects? How are Sorry. How how do your FDEs work on client projects So they don't touch the data still. So they'll just build the system. Okay. But they will also be onboarded like an employee sometimes. So, like, they might get a laptop and everything. Like, to the law? Yeah. Yeah. Because they need to. Interesting. That doesn't happen very often because, like, usually, they just build an integration and, like, kinda works. But they, yeah, they can if they need to.

46:30 And you only onboard FDEs into a customer, I'm assuming, if they're a certain size? Yeah. Yeah. Okay. And these two make sense. Because our FDEs can also work on core product. Right? So it's like... It's a constant prioritization thing. Is there a rule, like, I guess, does every... Like, know, so Palantir famously had, like, you know, four days you spend on-site, one day you come back and contribute back to products. Anything like that? No. We we don't. I am... To be fully honest with you guys, it's still it's still, you know, it's still early days in a lot of this. I mean, where do you see it headed? Maybe over the next year? I do think that it's gonna be more... Maybe not exactly like Palantir, but, like, we... I think we will have a larger, in constant circulation group of FDEs 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, etcetera, etcetera. Yeah. But I I do imagine us rolling in with legal engineers and forward deployed engineers to, like, work on specific projects. Yeah. The API business is actually interesting, like like you said, because, know, that's another rule that you can have, where you will CTO maintainer of the Legora platform. Yep. Right? Like, we will offer everything that we have in the Legora web app Yep. As an API, and then you guys can use whatever. Is is that is that a promise that you make? Or That's not something we're promising now. Yeah. We do have APIs that you can build against, but not the entire surface of the product. That's the curious thing, like, is that the strategy? Or... And obviously, you know, some people will love it because I don't have to learn a new tool, I can just use the existing tool I have. Right? And then I just, like Yeah. Install Legora, for example, with the the Word document stuff. Other than that, you know, I I do think, like, then you have to maintain it.

48:00 Exactly. That's that's... So that's been my thing. That's why we've tried not to do it. We haven't we haven't had APIs. I mean, we started our APIs, like, six months ago or something. We fought it for a very long time, mostly because, yeah, I just don't wanna... We we move so quickly in in the product that I don't wanna be, like, slowed down by having to maintain old API versions for, like, a data model that we've changed. I mean, now we're bigger and things are different, so now it's it's a cost that we can take on, But when we're 20 engineers, it's just like we we move so quickly that we can't do this. I have to point with this. Right? Like, it's just generally good for all companies to have a platform team and a product team because the product team, you have one, but then you can easily spin up a second one as long as the platform is not super tied to product. Yeah. Yeah. Yeah. You know, like, a very simple one is web app mobile app. Right? Or, like, web app mobile app RTP and and then, like, you know, whatever, like Yeah. Other other integrations. Then your FDEs just are one more client to the overall platform anyway. Yeah. And I think, like, even the agent, you can think about it this way. There's, a harness team or, like, a... That runs the agent, and then you can even... You can build a product around it with, like, skills and automations and whatever else. Yeah. This this is, like, very famously the Amazon web services mandate. Mhmm. Like, Bezos was like A of things in the API. No more backdoor access. You only offer other teams your APIs, the same APIs you offer customers. Mhmm. If you don't have it, you build it. Yep. And then the customers also get it. Yep. I think I think that's also changing a little bit. A lot of a lot of APIs now... Like, one thing that we're toying with is, can the agent be the API? I know it sounds weird, but, like, for some of this stuff, what they actually want to do is they want to trigger certain things to happen. For some part of this, it could... You could just be... I'm not saying that we're doing this, but it's like a thing that I'm toying with in my head is, could that just be like, okay, you 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 had 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?

49:30 Well, you know, unbounded execution and cost and latency. That's the... That's... Is that the only whole bag? That's... Yeah. And then I think deterministic, like, maybe in, you know, a 100 out of or in two out of a 100 times, it's gonna do something whack that we didn't want it to do. We were gonna go into, like, harness and and model fine tuning in a bit. But I think there's a there's a product question about restraint Mhmm. About what you don't do Yep. Because you could do all that, and obviously, there's a prioritization issue. Like, are are you at... More on a point of let's say no to most things and then only do a short number of stuff? Or no. Actually, we wanna do more things, and we just need to hire, like, 100 people? I was I was very strongly the first thing for a very long time. Let's just say no to everything, like, keep the eng team... I I think I've said this before, but, like, one of our presentations that, like, after I've been at Legora for half a year, I I pulled up this slide of, you know, the 300 Spartans and and and Yeah. 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. We're a 100 engineers now, and it feels like we're way too small. I wanted to do that, but I think in the real world, we're in, like, fierce competition, people want so much stuff, it's like, I could be a puritan and just be like, no, we have to stay 20 people and we can only build, you know, whatever, but then we just lose, and, like, people would go elsewhere. So we have to build more, and so I think my job is to figure out how do I build a system where we can build a lot, but actually only... Like, where we can... The customer feels like we've built so much stuff, but we've actually only built a few things. That's that's how I think about my job right now.

51:00 Yeah. I mean, primitives is right, you know? Yeah. Exactly. I think that's gonna be... That's really powerful. 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... We haven't made... I mean, we've made certain strategic bets Yeah. But we've not tried anything that we don't have a lot of confidence in already, mostly because we just have, like, amount... Enough demand. Yeah. It's like, we want all of these things, and so it doesn't... It hasn't really made sense for us to try to be like, hey, what... Maybe this thing could work, because, like, there's so many people screaming for the other things, and so we mostly build those, and then sometimes we'll disagree with clients and we'll be like, actually, I think this thing over here will make a lot of sense strategically, and then we'll try to build that anyway. Like, strategically for you? Yeah, exactly. What are the ones that we see? One of those things was the agent, actually. So, like, no one was actually asking for, like, I wanted to be... I want the assistant that I'm using to have more agency and do things without me asking it, like, no one no one ever, but we're just like, this is definitely where the industry is going. This is gonna empower you to do so much cool stuff. 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 few of those.

52:30 And then how... Like, once you say, okay, yeah, we want you guys to use agents, I'm assuming, like, internally at the law firm, you know, it's gonna take a lot for them to actually learn how to do that. Yep. And so that's where you kinda, like, say, hey, FDEs go in there and teach them what they Yeah. Legal engineers mostly Oh, legal. Don't be. Yeah. That makes sense. But they're like, some people call them forward deployed legal engineers if you want, but that's essentially what they are. Then they go in, yeah, and help and help them structure their workflows around the capabilities of the agent. You guys said previously, I think Max said this, but that early on specifically, you guys weren't fine tuning your own models. Is that still the case? Yeah. So we haven't fine tuned any models up until I think now in the past few months, open weights models have become extremely capable, and so we will do it for certain tasks where we think there's a huge delta between what a frontier model can do at the cost and latency versus what we think a post trained model can do. Legal research is a great example. It's like you have to make... It's a it's a fan out retrieval problem, and you can make a really effective model through those queries super quickly and super cheaply at low latency. So specifically, you're post training them to be better at? Very specific Yeah. Bounded Exactly. Okay. Yep. We're not trying to, like, train our own Fable Yeah. To, like, be the main agent. I I don't think that's like a... We won't win that, you know, versus Anthropic, most likely. There's still a lot of, let's say, and retrieval research or RAG research Mhmm. To do Yeah.

54:00 That is, like, maybe less glamorous. It's not actually even model training sometimes, it's just like architecture and pipelines. You You did a case study with turbopuffer, but, like, you know, there's also... Like, do you do late interaction of Yes. Absolutely. You you do that. Yeah. We actually don't do that, but it's... You're completely right that this is... So there's one guy on the team, Song, who's... He just really cares about search, and he 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 late... And late interaction. He actually talked to turbopuffer teams to get them to build multivector so that we could do these types of things, But, no, there's loads of low hanging fruit generally, even before models, and even in the harness, honestly, like, if you just 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. Yeah. Like, what makes a good harness for, like, the law industry, I guess? Like, you guys are making, I'm assuming, like, your own custom harness. Yep. Yeah. Of Yep. Way that we edit files is important. The way that we do an analysis is important. The way you do legal research is all baked into it. So it's like, you might have a problem that comes up or sees something, then it knows how to go and do the legal research to figure out what the answer is, what the precedent is. That's all very important. And then, of course, there's all the governance stuff around it as well. Yeah. It seems like the search is probably, like, would you say the most important tool that you guys are, like, customizing? Because It's if you can't pull in the right information Yeah. And then then you're Yeah. Screwed. You're screwed. It's... Yeah. I think it's it's it's You guys are searching, like, a lot of documents. And analysis. Yeah. Yeah. It's search, it's analysis, it's drafting, probably. Okay. Because, like, drafting word... Drafting huge contracts is actually also not super trivial.

55:30 Like, what about it is not trivial? Because you have to... Let's say you're drafting a huge contract from scratch, then you have to find precedents of, how do we do this previously? Do we need this type of clause A or specific law firm? How did they do it previously? Yeah. So I am the law firm, and I'm about to draft a huge... Whatever. NDA is very simple, but, like, there's... There are contracts that are way more complex, and then you need to find the right precedent first, because, like, lawyers just don't don't, like, sit and, like, start typing stuff. They they figure out what clauses have we used in similar deals, and similar can mean a lot of different things. As I'm sure you know in search, it could be like same industry, same type of companies, same whatever. And so you need to identify the right person, and you might have like multiple documents that you then try to figure out which part should I take from what document, and that's actually nontrivial. So it's essentially also a search problem. Which model's best at drafting? Yeah. So I'll say... I was told that was perfect this yesterday. Definitely Fable and Opus are extremely chatty. I'm sure you guys have known this. They're very verbose. So that's not good. That's generally not good. No. I noticed Astra's been pretty good at writing. Astra's... Yeah. Pretty good at writing. Is it much more concise? You've running, like, a 100 different prompts to, like Yeah. Be sure. We we can... Yeah. We can we can do we can do certain things, but I think the chattiness verbosity is actually a little bit difficult for us to do. Wow. 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.

57:00 Yeah. Yeah. And I I assume they they all have a Slack channel with you and you're telling them this. Right? Like, Yeah. This is not news to them. No. No. They know this. Then the other thing that I really care about is hallucination. Mhmm. Do they make stuff up? So we have a system of... Citation system where we basically check what they're writing has a link, so the user has a link, they can click and it highlights with a bounding box, like in the PDF or whatever, where where this information was taken from, and we can sort of make sure that what it says always is citable somewhere, even multiple layers down. So, like, if the agent writes something based on a tabular review, you know, it can cite the cell in the tabular review or the row in the tabular review, so you can actually click multiple layers down and find, you know, sort of validate it all the way up. Yeah. Are you finding that lawyers are, like, verifying that these citations are correct or not? In in in in initially, it's kinda like Some other work, but now... Yeah. Exactly. It's the same thing. Shit, like, hallucinated links to Supreme Court. They don't care. That happens. Yeah. Exactly. That happens. Yeah. I I think it's like coding, you know, you have engineers that just don't give a shit and just, like, send agents, and you have people that, like, sit and read every comma. Same description. There's just, like, so much that, like, how can one human do that? Right? Yeah. But I think they probably... It's just like we know in code review what to look for Yeah. Like, what is the system or whatever. I think they also know, okay, this is the the thing, these are the red... Like, this is the thing that's important, let me just, like, double check these things, and, like, these sound reasonable, so it's probably fine. Okay. Interesting. Just like if you if you receive something from a junior lawyer, it's the same thing you do, right? Just like, I should double check this, and, like, this probably is fine. Any other elements of, let's call it, legal reasoning, or what's the the the legal frontier that models are not good enough yet that you want from the next generation of models? Nothing I can think of specifically right now. I think long document reasoning is still difficult. Long, like, million token token contracts is basically You have a huge contract Yeah. And, like, you're making edits across it, it's a difficult thing to do for a model today even. And I remember that you changed all these things up here, and, like, the definitions changed, and that you... The ordering changed, whatever else. So, the simplest would be one shot, you feed everything in, and then one shot output.

58:30 Yes. You don't do that, you break it up into chunks, and then you orchestrate edits. Yeah. Exactly. Exactly. And this is one of those things that are funny, that are fun to be part of in this industry. Right? So our Word add-in, it was like, we've done, you know, we've done MapReduce, we've changed, and there was one big one, and there was one big one in multiple times. It's like, we keep changing Yes. The the scaffolding that we build around as models change. Yes. I I I would say I I I've recently... I do a lot of news reporting Mhmm. Obviously because of what I do, and I've recently shifted from MapReduce to throwing between these context. It's better. Yeah. But it's also... It's different. I mean, we had this problem with search where it's like, you're searching for certain things in a huge contract, and you can map reduce it, but then it might... If you're summarizing any sort of thing, then it might lose some important nuance Yep. In between the chunks, essentially, if you just summarize the individual parts up. So this has been a problem where it's like, we can do two types of search, we can also do the other one where it's like, you need to have reasoning in the different steps there in between. So I'm trying to think of a really good example here. There's some documents where they talk about something at length over, like, let's say, two pages or whatever, and then each individual chunk is not necessarily relevant to the search term or what they're trying to figure out, but together it's extremely relevant. And so, yeah, these are some of the, you know, problems where it's... And it must be hard,

1:00:00 like you said earlier, to actually make the models better at that, because you can't even look at the contracts. Right? Exactly. Do you guys ever ask them for like, hey, can you Yes. Make example contracts that are similar to the real ones? Yeah. So we have we have feedback, we can receive feedback from them, and if they're really engaged, yeah, exactly. Or they're just like, hey, this is, like, super important to us and it's not working well, and then we're like, okay, great. Can you, like, anonymize the documents and, like, the problem, whatever, and we'll... We... If we can recreate it, then we can fix it. Yeah. I mean, so one version of this is you buy a law firm Yep. Which some people are considering. Yes. But there's some... We... There's some stuff there on whether their data is actually their data or if it's the client's data. So if their clients are all gone, then maybe it's fine. I actually don't know. Interesting. Yeah. But it's... Yes. It's it's a way to get a lot of data. Yeah. People like Google is buying Spiritualize. Exactly. Yeah. Bought Yeah. They bought the... Yeah. Yeah. Like, you know, if you have a failed company, you still have your Slack. You can sell your Slack. I think there's like there's like a YC company that buys your failed company. Yes, there is. Yeah. Yeah. Because, like, it's just like, oh, I just want real people doing work. Exactly. And then, yeah, just so it was like Exactly. Pull stuff out. Exactly. The problem with buying law firm data is do... Well, you get all the inputs, the real inputs, which is great. The outputs are a little bit more difficult, because you just get what their end result was, and it's difficult to figure out if, like, the way... You have to basically, like, reverse engineer how they got there. So in our product, when we get real traces from really users, it's extremely high value, But if we just got this output, and we don't know if it's good or bad or how it was created, it's a little bit difficult.

1:01:30 We're gonna wrap up soon. The last thing I'll point people to is also there's a lot of alpha left on embeddings. You're if you're a RAG heavy work... Workload, you're just looking at MTEB and you're taking, like, top model, you're leaving a lot on the table, you should look at Voyage or some of the custom embeddings. You've gone into this. Yeah. So basically, don't take default embeddings, even OpenAI embeddings, Gemini embeddings, doesn't matter. Customize your embeddings. Yeah. Right? Yes. You you you will support that. Yes. I think that's right. I think that's right. The only thing is you need to make sure that you're multi language. So for us, we we serve so many languages, so that's the world is the king of this. Yeah. Yeah. Exactly. Mistral, helpful there? No. Until... Well, until now, they just raised a ton of money. Right? So maybe Yeah. Let's see. You guys better They also raised a ton of money. You're gonna be your champions. Like I think we need way more model companies out of the... Out of Europe. Yes. I just wanted to ask you, like, what predictions do you have maybe, like, over the next year for, like, the law industry? We we asked a little bit of that earlier. Yeah. I'll modify it to your second question, which is in two years, will lawyers do their work inside Legora, or will they use other tools like Claude or TrejoC and call Legora, like, you know, the API?

1:03:00 Yeah. Yeah. Yeah. Yeah. I think both. It really depends. I think if you're an an big enterprise, you might have Claude Cowork, and then you'll... It's... I think it's similar to, like, how I use Linear through Claude, but I still go to Linear. Think I enterprise will do that. I think law firms will just use Legora Yeah. Because that's simpler and better. Yeah. It kinda reminds me of, like, OpenEvidence for, like, medicine. Like, you're you're basically that for law. Yep. Yeah. Exactly. In coding, it's going to a point where people... The labs will cut you off for competing with them, and this has happened twice. Yep. Do you do you think that will happen to law? No. I don't think so. I think Because, like, you know, they are releasing legal services. Yeah. 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 Your sales reps will say no. Exactly. They don't make the call. Exactly. That's not their goal to make. Right? And they don't even know, often what's actually going on. I don't think I don't think that's the case. They have so much stuff to capture in knowledge work or in in sort of enterprises knowledge work generally, that, like, legal has to be part of that, just like data analytics has to, and sales, and marketing, and finance. So, like, they have to do things that are good there, but they're never gonna go as deep as we are. And I think if if Claude takes small clients, small, you know, corporate clients and they do some of their legal via Claude, like, that's that's great, that's fine. But if you're doing a, you know, $400,000,000 M and A transaction, you're gonna want Legora. I had kind of an unrelated question, but I'm curious, are you guys going to law schools and kinda like getting them to like teach Legora like in classes? Like, how does that work?

1:04:30 Yeah. It's it's definitely a program that we are... I think we've started. I actually don't know exactly where we're at, but we we do want people in law school to Yeah. Learn to use Legora. Like, are you seeing that, like, law schools are changing their curriculums a lot or not really? I don't know. I I I wouldn't know, actually. Interesting. I would actually do it a different way. You should do scholarships for for law school for CS majors, for engineers. We will cover your done CS? Yes. We'll we'll put you in law school? CS plus some software experience Yeah. We'll put you in law school. Yeah. We'll cover it. Or you do, like, the MA... Like, master's plus JD programs? Yeah. They don't care about the master's. Yeah. Well, meaning meaning, like, because there's a lot of people who didn't do CS undergrad, so then they do, like, master's just to kinda, like, get get caught up. Yeah. Yeah. I I don't know. I don't see that as as often. Yeah. Yeah. People do JD MBA. That's a thing. Yeah. But JDCS, I haven't seen it. Yeah. Happens. Yeah. Yeah. Yeah. Okay. Look. Overall, you know, super impressive progress. I mean, congrats on all your success. Like, are you still gonna keep up the pace? Like Absolutely. Yeah. You know? And I think you're hiring in SF New York. We're hiring in... Yeah. Engineering, we're hiring in New York, Stockholm, and London. Yeah. And all other roles, we're hiring everywhere. How many people do you have in New York right now? A 100. About a 100. Okay. And you guys are planning on how many in New York? In New York? Yeah. For just, like, generally? Let's just say, yeah, generally and generally.

1:06:00 A lot. As many as you can. Yeah. It's it's it's aggressive. Yeah. Mean, that... That's the home of corporate law, right, as far as, like It is. Yeah. Mid America's history. So, like, yeah. I mean, I'm looking forward to you buying a law firm and, like, you know, become... Yeah. Yeah. 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, they all have to have, like, you know, two or agent labs that, like, just completely dominate the space. I agree. So you guys have, like, a great market. Yeah. Good. I think so. And I think it's only gonna get much bigger as, like, law changes and get... Becomes more available to more people. Yeah. Also, I think, like... I mean, we're already, like, super over, but, like, the problems that you work on are very... Like, the frontier knowledge work. You know? Yep. They're... Okay. Unless you're literally, like, doing, like Navier Stokes. Science Navier Stokes and science. Other than that, like, most work is, like, basically converges to legal. Yeah. It's all legal in the end. Yeah. Hiring, finance, everything, I just have to consult my lawyer. Yeah. Know. I know. Which is why I think it's a really exciting thing to work on, because modern society runs in some way on legal. Yeah. Yeah. Cool. Alright. That's it. Thank you. Cool. Thank you. Thanks.

Thanks for reading