AI & Tech··1 sources verified
Uber's Legal Redlining Agent Cuts Contract Review Time by 20% Using RAG and Rules
Summarised by Relevant News AI · Read time: 3 min
Uber's Legal Redlining Agent reviews contract changes directly in Microsoft Word, combining retrieval-augmented generation over historical lawyer feedback with deterministic policy rules. Built with LangGraph, OpenSearch, and Redis, the system reports more than 20% lower average contract review time and 91% accuracy in its AI-generated decisions. Uber is also exploring agentic harnesses, skills, legal ontologies, and knowledge graphs for future versions.
Why it matters: It is a concrete production example of how teams can pair RAG and rule engines in an agent workflow to get measurable efficiency gains in a high-stakes, document-heavy process.
All sources