HaiAI123

Curated Global AI Tools Directory

Industry update
Flat

Uber's legal review agent cuts contract review time by over 20%

11/16/2026 — 11/16, 23:19·1 sources (all)·1 reports (all)

Key takeaways

  • InfoQ reports that Uber's legal redline review agent reviews contract edits inside Microsoft Word, combining RAG, past lawyer feedback and d…

Background & analysis

On November 16, 2026, InfoQ published a piece in its AI/ML section covering the latest work from Uber on a legal redlining Agent. The system reviews contract changes directly in Microsoft Word, combining RAG with historical lawyer feedback and deterministic policy rules. According to Uber's own report, the approach has cut average contract review time by more than 20%, while the accuracy of AI-generated decisions in the process stands at 91%.

Technically, the system is built on LangGraph, OpenSearch, and Redis. The same report notes that Uber is also exploring agentic harnesses, skills, legal ontologies, and knowledge graphs, indicating that work in these directions is still in an exploratory phase rather than a settled deployment.

As of now, this InfoQ report is the only available source on the subject, so there is no independent confirmation of the reported figures, and no further details on rollout scope, user groups, or what happens next. The available material therefore stops at the stage of a single vendor-reported result and an outline of the technical stack and future directions under consideration.

AI-generated from 1 reports · updated 13 hours ago

updream
24-hour heatHeat index 66 · peak 99 · 13h ago
24 hours agonow

Reports on this story headlines open the original

Yesterday
  1. Uber's legal redlining agent reviews contract changes inside Microsoft Word using RAG, historical lawyer feedback, and deterministic policy rules, cutting average contract review time by more than 20% with 91% decision accuracy, InfoQ reports. The system is built on LangGraph, OpenSearch, and Redis, and Uber is exploring agentic harnesses, skills, legal ontologies, and knowledge graphs.

    InfoQ · AI/MLAI score 57

Other stories people are talking about

How is heat calculated?About the method

Heat counts how many independent sources covered a story in the last 48 hours: one source counts once no matter how many posts it published, decaying with a 24-hour half-life. What ranks first is what many people are talking about.

This page aggregates public feeds. Headlines and summaries are machine-organized and remain the property of the original authors; verify important facts at the source. If you believe a headline or summary infringes your rights, email the contact address in the footer with the page URL and basis of your claim, and we will remove or replace it after review.

Surge
Discussion rising fast
New
First report within 6 hours
Rising
Still gathering discussion

Back to AI industry updates →