Harvey uses GPT‑6 Astra to create more structured legal drafts
Harvey, a platform for law firms and in‑house legal teams, now runs on GPT‑6 Astra. The model can ingest larger amounts of legal context, enabling the system to generate drafts that are more structured and better reflect the underlying material.
Key points
- Harvey runs on GPT‑6 Astra, letting it ingest larger legal context for draft generation.
- A memory panel lets lawyers set preferences like numbered lists, EDGAR priority, or colour‑coded issue tags.
- Customers report better formatting and more complete documents compared with earlier models.
The service pulls court filings, firm documents, case‑law research and other sources, then synthesizes them into memoranda, pleadings or merger documents. A memory panel lets each lawyer encode personal drafting preferences—such as using numbered lists, giving priority to EDGAR filings, or applying colour‑coded issue tags—and these settings appear alongside source excerpts and the draft.
Harvey says the move to GPT‑6 Astra has produced noticeable improvements in document formatting and completeness compared with earlier models, allowing lawyers to spend more time on strategy rather than manual assembly.
Model page: GPT-6-Astra →
Harvey turns legal context into stronger drafts with GPT-6 Astra
OpenAI · 23 September 2026
Loading the full article…
This text was published by OpenAI. It is reproduced here with attribution so you can read it in full; the rights remain with the publisher. Read it at the source ↗
The headline, key points and digest above were generated by Digest AI's editorial model from the linked sources. Automated summaries can contain errors: the sources are the record. Spotted a mistake? Tell us. Published by Martin K., who runs Digest AI and handles corrections.
More in Enterprise & Industry
All →- Anthropic replaces Git with Scion after AI agents drive merges from 2,500 to 30,000 per day · 12 src
- Sullivan & Cromwell builds legal tool Agreement Analyzer with OpenAI · 1 src
- Opsin raises $21M to track enterprise AI agents and flag risky behavior · 1 src
- Microsoft adds deepfake detection to Teams in November 2026 · 1 src
- Access Construction launches agentic AI layer Evo for estimating, project management and ERP · 1 src
Comments
via GitHub Discussions