Building Legal Agents When You Can't See the Data — Jacob Lauritzen, CTO of Legora
Jacob Lauritzen, CTO of Legora, explains how his team builds and evaluates enterprise legal AI agents under strict client-data confidentiality constraints. He breaks down Legora's core product primitives—including Tabular View, Lists, and Intake—and details why legal AI requires specialized roles like legal engineers alongside forward-deployed engineers. Lauritzen also shares insights on model routing, why Legora resists fine-tuning generalist models in favor of task-specific post-training, and how AI is altering legal billing and the traditional law firm partnership model.
- Law firms rely on partnership equity to retain human capital because individual attorneys were historically the firm's only productive asset. Read →
- Law firms rejected AWS outright during Legora's early sales cycles because their IT teams already maintained security approvals for Microsoft 365. Read →
- Legora splits customer deployment between legal engineers who configure workflows and forward-deployed engineers who write production code. Read →
- Legora CTO Jacob Lauritzen structured the company's platform around Lists, a database primitive modeled after Linear and Notion, to avoid hardcoding individual legal workflows. Read →
- Legora designed Tabular View to turn unstructured data rooms into spreadsheets where each contract forms a row and each extraction query forms a column. Read →