How Legora Evaluates Legal AI Agents Without Customer Traces
Latent Space interviewed Legora CTO Jacob Lauritzen about building AI agents for lawyers while customer uploads and work traces remain confidential. Legora’s evaluations team recreates legal workflows with simulated customer data, including a 10,000-file data room, while the company reportedly provides document drafting, contract review, due diligence, and multi-agent coordination. Latent Space also reported that Legora passed $100 million in ARR and has more than 1,800 customers.
Legora’s use of simulated evaluations offers agent builders a practical approach to testing systems when privacy rules prevent access to production traces, though the company’s capability and performance claims remain unverified.
In this episode, we chat with Jacob Lauritzen, CTO of Legora, following the announcement of their $550M Series E at an $8.8B valuation a couple weeks ago. We talk about what it takes to build AI agents for lawyers and what other people building agents can learn from that work.
Legora started in a Stockholm basement with a simple product: ChatGPT, Swedish law, and a search tool. Jacob had already been through YC with his own startup when he helped Max Junestrand with the application for Leya (now Legora). He later joined as head of engineering and is now CTO.
Today the agent drafts and edits Word documents, reviews thousands of contracts at once, and coordinates work between lawyers, their clients, and other agents. The company passed $100 million in ARR in April, less than 18 months after launch, and now has more than 1,800 customers. It raised $550 million in March at a $5.55 billion valuation, then another $550 million in October at an $8.8 billion valuation. Its latest acquisition, Wexler, was its fifth just this year.
Some source content is omitted. Continue reading on the original site.