Analysis
An October 28 OpenAI customer story describes Legora using AI across legal workflows and its own product development. The concrete example is an internal NDA playbook: Legora’s lawyers used previously signed agreements to define acceptable terms, and the system takes a first pass at new documents, flagging departures for attention.
Legora’s general counsel estimates that NDA review fell from around a fifth of the team’s capacity to under one percent. Separately, its chief executive cites a Fortune 100 customer reporting 90 percent faster contract turnaround and 9.5 hours returned per lawyer each week. These are company and customer outcomes presented in a vendor case study, not an independent comparison.
The broader claim concerns what gets reviewed. Legora describes examining large contract collections across multiple questions, with lawyers assessing the information surfaced. Our reading: increased coverage is useful only if the result makes its scope legible. A reviewer needs to know which documents were processed, which questions were answered and where the system could not reach a conclusion.
That suggests a more demanding finish line than producing a fluent summary. The handoff should connect each finding to its source and distinguish an unresolved issue from an unremarkable document. The case study illustrates the workflow opportunity, but does not establish a measured error rate or prove that broader automated review consistently improves legal outcomes.
Source: Legora is building the agentic operating system for legal work · 2026-10-28
Why it matters
More documents reviewed should produce a clearer evidence trail, not merely a longer answer.