Sullivan & Cromwell builds legal tool Agreement Analyzer with OpenAI
Law firm Sullivan & Cromwell has developed Agreement Analyzer, an AI tool created in collaboration with OpenAI to assist lawyers in reviewing draft agreements. Initially created as a single-user proof of concept using Codex by partner John Savva, the tool now integrates ChatGPT Enterprise, curated firm precedents, and negotiating playbooks into a multi-user workflow.
Key points
- Sullivan & Cromwell created Agreement Analyzer in collaboration with OpenAI to automate draft agreement reviews.
- The tool uses ChatGPT Enterprise and multi-agent adversarial processing to evaluate contract terms against firm playbooks.
- Partner John Savva noted that reasoning capabilities in models like GPT-6 Astra advance complex legal analysis.
Agreement Analyzer uses specialized agents that perform review cycles in parallel to analyze contract terms against client priorities and market practice. The process uses an adversarial setup where agents challenge each other's conclusions, distinguishing verified findings from unverified issues. The system outputs a memorandum and suggested tracked changes for lawyers to review, adapt, or reject.
Sullivan & Cromwell partner John Savva noted that improvements in AI analytical capabilities have enabled automation for complex tasks beyond basic administrative work. He highlighted advances in reasoning capabilities with GPT-6 Astra as a key factor in improving the quality of legal research and writing workflows.
Model page: GPT-6-Astra →
Sullivan & Cromwell brings legal expertise into agreement review
OpenAI · 15 October 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 · 10 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
- B2B buyers increasingly trust AI agents over sales reps for vendor research · 3 src
Comments
via GitHub Discussions