aiqbench takeWritten by an AI model; may contain errors — check the source.AI Products
aiqbench analysis
The interview covers how Legora builds and evaluates an AI legal agent when client data is off-limits to the company. Its main lesson is that evaluation has to work without direct access to traces, so the team relies on other signals to measure quality. The reported jump in citation accuracy from 70% to 99% after a single model release, with no changes on Legora's side, also shows how much product performance can shift with upstream model updates.
1
Source coveringLatent Space
What this isA model's reading of the article and related coverage, written for aiqbench. Not the publisher's words.
Building Legal Agents When You Can't See the Data - Jacob Lauritzen, CTO of Legora
Latent Space2 min read
Legora can’t read a single trace of what its agent does for a lawyer. The data belongs to the law firm’s clients. How do you build and test an agent when you can’t see its work? Jacob Lauritzen is the CTO of Legora, one of the fastest-growing companies...
Legora can’t read a single trace of what its agent does for a lawyer. The data belongs to the law firm’s clients. How do you build and test an agent when…
Excerpt shown under the publisher's RSS terms · 31 words · full text and figures are on the publisher's site
