Sign InOpen Brain
OpenAIOfficial ReleaseOfficial Source

Legora reviewed 41 documents in minutes with GPT-6 Astra

Legora says GPT-6 Astra reviewed 41 documents within minutes, caught every planted error, and improved its workflow result by nearly 40%, though the underlying measure is unspecified.

OpenAI · Sep 3, 2026
Open Source Open MarkdownOpen JSON
Source Summary

Legora applied **GPT-6 Astra** to a financial-review workflow covering **41 documents**. It finished in minutes, found **all four planted errors**, and improved performance by **nearly 40%**.

Practical Implication

Builders designing document agents should evaluate the full workflow: retrieval across many files, error detection, completion time, and whether planted issues are consistently recovered.

Agent-Ready Context
Legora applied **GPT-6 Astra** to a financial-review workflow covering **41 documents**. It finished in minutes, found **all four planted errors**, and improved performance by **nearly 40%**.

Builders designing document agents should evaluate the full workflow: retrieval across many files, error detection, completion time, and whether planted issues are consistently recovered.

The material does not define the performance metric, baseline, document complexity, or exact runtime. Planted-error recall also does not establish accuracy on unstructured real-world mistakes.
Connected Context · Feed7 Judgment

This adds workflow-level evidence for Astra in multi-document financial review, but it does not establish a general model-selection result. Against the candidates, it reinforces testing retrieval, detection, and completion together while narrowing the claim to one planted-error setup whose metric, baseline, complexity, and real-world error coverage remain unspecified.

Context Map
modeldataresearch#reasoning#model-selection#agent-evals
Uncertainty
The material does not define the performance metric, baseline, document complexity, or exact runtime. Planted-error recall also does not establish accuracy on unstructured real-world mistakes.