--- title: Building AI for Lawyers - Jacob Lauritzen, CTO of Legora description: Legora's CTO Jacob Lauritzen explains how the legal AI company evaluates agents without ever seeing customer data, since nearly everything uploaded is... canonical: https://daily.dev/posts/building-ai-for-lawyers---jacob-lauritzen-cto-of-legora-s9tyhxq0d twitter:card: summary_large_image twitter:site: @dailydotdev og:type: website og:site_name: daily.dev og:title: Building AI for Lawyers - Jacob Lauritzen, CTO of Legora | daily.dev og:description: Legora's CTO Jacob Lauritzen explains how the legal AI company evaluates agents without ever seeing customer data, since nearly everything uploaded is... og:url: https://daily.dev/posts/building-ai-for-lawyers---jacob-lauritzen-cto-of-legora-s9tyhxq0d og:image: https://api.daily.dev/og/posts/S9TyhxQ0d.png og:image:alt: Building AI for Lawyers - Jacob Lauritzen, CTO of Legora og:image:width: 1200 og:image:height: 630 og:locale: en --- > ## Documentation Index > Fetch the complete documentation index at: https://daily.dev/llms.txt > Use this file to discover all available pages before exploring further. # Building AI for Lawyers - Jacob Lauritzen, CTO of Legora **[Latent Space](https://daily.dev/sources/latentspace)** · 87 min read · 0 upvotes · 0 comments ## Summary Legora's CTO Jacob Lauritzen explains how the legal AI company evaluates agents without ever seeing customer data, since nearly everything uploaded is confidential client material. Instead, a team of three engineers and three lawyers builds simulated RL environments, like a 10,000-file due diligence data room, and plots model performance on a heat map by practice area. Legora passed $100 million in ARR in April, less than 18 months after launch, and raised $550 million in October at an $8.8 billion valuation. Models already handle about 60% of legal work well, Jacob says, while complex analysis across million-token contracts still needs more intelligence. Everything runs on Azure because when Legora started, law firms wouldn't accept AWS or GCP, and Microsoft was already an approved vendor through 365. ## Full article daily.dev links to this article rather than hosting it. Read it at the original source: ## Questions this post answers ### How does Legora evaluate its AI agent performance without access to customer data? Legora cannot read customer traces because nearly all uploaded data is confidential and often belongs to the firm's clients rather than the firm itself. Instead, a team of three engineers and three lawyers builds simulated RL environments, such as a 10,000-file data room for due diligence, and plots model performance on a heat map broken down by practice area and task type. _Teams building agents for regulated industries can follow similar evaluation approaches surfaced on daily.dev._ ### Why does Legora run all its infrastructure on Azure instead of AWS or GCP? Legora hosts everything on Azure because when the company started, law firms would not accept AWS or GCP but already trusted Microsoft as an approved vendor through their existing Office 365 contracts. That early trust decision shaped Legora's entire infrastructure stack, even though law firms have since become more comfortable with cloud providers generally. _Developers weighing cloud vendor choices for regulated clients can track similar infrastructure decisions on daily.dev._ ### What percentage of legal work can current AI models handle well according to Legora's CTO? Models already handle about 60% of legal work really well, according to Legora CTO Jacob Lauritzen, meaning that portion is now primarily a cost and latency problem rather than a capability gap. The remaining work, especially complex analysis and editing across million-token contracts, still requires more model intelligence to complete reliably. _Anyone gauging how far AI agents can go in professional domains can follow these benchmarks on daily.dev._ ## Similar posts on daily.dev - [Building Legal Agents When You Can't See the Data - Jacob Lauritzen, CTO of Legora](https://daily.dev/posts/building-legal-agents-when-you-can-t-see-the-data---jacob-lauritzen-cto-of-legora-0bg2vqfqo) · Latent Space · 2 upvotes · 1 comments - [Legal AI startup Legora raises $550M Series E at $8.8B valuation](https://daily.dev/posts/legal-ai-startup-legora-raises-550m-series-e-at-8-8b-valuation-pvkgm0qo0) · TechCrunch · 0 upvotes · 0 comments - [Swedish legal AI firm Legora raises $550M led by Atreides at $8.8B valuation](https://daily.dev/posts/swedish-legal-ai-firm-legora-raises-550m-led-by-atreides-at-8-8b-valuation-b1wjofd63) · The Next Web · 0 upvotes · 0 comments - [Legora is building the agentic operating system for legal work](https://daily.dev/posts/legora-is-building-the-agentic-operating-system-for-legal-work-smkj4zc2x) · OpenAI · 1 upvotes · 0 comments --- Tags: [#ai-agents](https://daily.dev/tags/ai-agents), [#llm](https://daily.dev/tags/llm), [#claude](https://daily.dev/tags/claude), [#legal](https://daily.dev/tags/legal) [View this post on daily.dev](https://daily.dev/posts/building-ai-for-lawyers---jacob-lauritzen-cto-of-legora-s9tyhxq0d) ```json {"@context":"https://schema.org","@graph":[{"@type":"Organization","@id":"https://daily.dev/#organization","name":"daily.dev","url":"https://daily.dev","logo":{"@type":"ImageObject","url":"https://daily.dev/apple-touch-icon.png","width":180,"height":180},"sameAs":["https://twitter.com/dailydotdev","https://github.com/dailydotdev","https://www.linkedin.com/company/daily-dev-ltd"]},{"@type":"WebSite","@id":"https://daily.dev/#website","url":"https://daily.dev","name":"daily.dev","publisher":{"@id":"https://daily.dev/#organization"},"potentialAction":{"@type":"SearchAction","target":{"@type":"EntryPoint","urlTemplate":"https://daily.dev/search?q={search_term_string}"},"query-input":"required name=search_term_string"}}]} {"@context":"https://schema.org","@type":"TechArticle","headline":"Building AI for Lawyers - Jacob Lauritzen, CTO of Legora","url":"https://daily.dev/posts/building-ai-for-lawyers---jacob-lauritzen-cto-of-legora-s9tyhxq0d","mainEntityOfPage":{"@type":"WebPage","@id":"https://daily.dev/posts/building-ai-for-lawyers---jacob-lauritzen-cto-of-legora-s9tyhxq0d"},"datePublished":"2026-11-02T23:03:40.610Z","dateModified":"2026-11-02T23:04:11.929Z","description":"Legora's CTO Jacob Lauritzen explains how the legal AI company evaluates agents without ever seeing customer data, since nearly everything uploaded is...","image":"https://media.daily.dev/image/upload/f_auto,q_auto/v1/posts/998f74188b2c176a7bdddc3da3e04d84?_a=AQAEuop","thumbnailUrl":"https://media.daily.dev/image/upload/f_auto,q_auto/v1/posts/998f74188b2c176a7bdddc3da3e04d84?_a=AQAEuop","isAccessibleForFree":true,"articleSection":"Latent Space","inLanguage":"en","publisher":{"@type":"Organization","name":"daily.dev","url":"https://daily.dev","logo":{"@type":"ImageObject","url":"https://daily.dev/apple-touch-icon.png","width":180,"height":180}},"author":{"@type":"Organization","name":"Latent Space","logo":"https://media.daily.dev/image/upload/s--DnJ9laFj--/f_auto,q_auto/v1780213196/logos/latentspace?_a=BAMAMiWQ0","url":"https://daily.dev/sources/latentspace"},"commentCount":0,"discussionUrl":"https://daily.dev/posts/building-ai-for-lawyers---jacob-lauritzen-cto-of-legora-s9tyhxq0d","interactionStatistic":[{"@type":"InteractionCounter","interactionType":{"@type":"LikeAction"},"userInteractionCount":0},{"@type":"InteractionCounter","interactionType":{"@type":"CommentAction"},"userInteractionCount":0}],"keywords":"ai-agents,llm,claude,legal","timeRequired":"PT87M"} {"@context":"https://schema.org","@type":"BreadcrumbList","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https://daily.dev"},{"@type":"ListItem","position":2,"name":"Latent Space","item":"https://daily.dev/sources/latentspace"},{"@type":"ListItem","position":3,"name":"Building AI for Lawyers - Jacob Lauritzen, CTO of Legora"}]} {"@context":"https://schema.org","@type":"FAQPage","@id":"https://daily.dev/posts/building-ai-for-lawyers---jacob-lauritzen-cto-of-legora-s9tyhxq0d#faq","mainEntity":[{"@type":"Question","name":"How does Legora evaluate its AI agent performance without access to customer data?","acceptedAnswer":{"@type":"Answer","text":"Legora cannot read customer traces because nearly all uploaded data is confidential and often belongs to the firm's clients rather than the firm itself. Instead, a team of three engineers and three lawyers builds simulated RL environments, such as a 10,000-file data room for due diligence, and plots model performance on a heat map broken down by practice area and task type. Teams building agents for regulated industries can follow similar evaluation approaches surfaced on daily.dev."}},{"@type":"Question","name":"Why does Legora run all its infrastructure on Azure instead of AWS or GCP?","acceptedAnswer":{"@type":"Answer","text":"Legora hosts everything on Azure because when the company started, law firms would not accept AWS or GCP but already trusted Microsoft as an approved vendor through their existing Office 365 contracts. That early trust decision shaped Legora's entire infrastructure stack, even though law firms have since become more comfortable with cloud providers generally. Developers weighing cloud vendor choices for regulated clients can track similar infrastructure decisions on daily.dev."}},{"@type":"Question","name":"What percentage of legal work can current AI models handle well according to Legora's CTO?","acceptedAnswer":{"@type":"Answer","text":"Models already handle about 60% of legal work really well, according to Legora CTO Jacob Lauritzen, meaning that portion is now primarily a cost and latency problem rather than a capability gap. The remaining work, especially complex analysis and editing across million-token contracts, still requires more model intelligence to complete reliably. Anyone gauging how far AI agents can go in professional domains can follow these benchmarks on daily.dev."}}]} ```