Building Legal Agents When You Can't See the Data - Jacob Lauritzen, CTO of Legora
- ID
- 42205
- Status
- summarized
- Published
- 03 Nov 2026, 6:54 AM
- Fetched
- 03 Nov 2026, 7:45 AM
- Provider
- Latent Space
- Category
- developer-ai
- Original URL
- https://latent.space/p/building_legal_agents_when_you_can_t_see_the_data_-_jacob_lauritzen_cto_of_legora/
- Source URL
- https://www.latent.space/feed
Summary
- Score
- 8.0
- Created
- 03 Nov 2026, 7:46 AM
- Tags
- Audience
- developersai_ml_learnersai_agent_userssaas_founders
What happened
Jacob Lauritzen, CTO of Legora, describes building legal agents whose production traces the company cannot read because the data belongs to law-firm clients. Legora tests with three engineers and three lawyers using environments modeled on customer work, finally added a model picker after resisting for years, and saw citation accuracy move from 70% to 99% in one release. Its agent can draft and edit Word documents, review 10,000 contracts in a single table, run due diligence, and coordinate work between lawyers, clients, and other agents.
Why it matters
If you ship agents over client-confidential data, you likely cannot debug through production traces; the concrete move is to budget for customer-shaped test environments and a citation eval, because Legora's jump from 70% to 99% shows citation correctness is a release-level metric, not a prompt tweak. Legora also delayed a model picker for years, so don't assume exposing model choice is required early.
Discussion angle
When production traces are legally off-limits, what does a minimum viable eval 'world' look like, and how do you staff it with engineers and domain experts without slowing releases?