NEWS · COMPANIES · #3664
Uber’s Legal Redlining Agent cuts contract review time by ~20% using RAG and rules
Uber says its Legal Redlining Agent reduced average contract review time by more than 20% and achieved 91% accuracy in AI-generated decisions. The Microsoft Word add-in combines retrieval-augmented generation with historical lawyer feedback, deterministic rules, a React/TypeScript front end, a Python backend orchestrated via LangGraph, OpenSearch vector stores, and Redis session state; lawyers retain final review and approval responsibility.
KEY POINTS
- Uber says its Legal Redlining Agent reduced average contract review time by more than 20% and achieved 91% accuracy in AI-generated decisions.
- The Microsoft Word add-in combines retrieval-augmented generation with historical lawyer feedback, deterministic rules, a React/TypeScript front end, a Python backend orchestrated via LangGraph, OpenSearch vector stores, and Redis session state; lawyers retain final review and approval responsibility.
- This shows a practical enterprise pattern—RAG plus rules and feedback loops—that measurably speeds legal review while keeping humans in the loop.
WHY IT MATTERS
This shows a practical enterprise pattern—RAG plus rules and feedback loops—that measurably speeds legal review while keeping humans in the loop.