Building uReview, Uber’s Multi-Agent Code Review Engine — Will Bond & Ameya Ketkar, Uber
Source
youtube.com
Author
AI Engineer
Date
Context
Uber Engineering's account of uReview shows how an automated code reviewer can be improved by measuring what happens after it comments. The talk's published description says the team tracked developers' replies, whether comments were addressed and the AI agentAn AI system that doesn't just answer once but works toward a goal in a loop — taking actions, reading the results, and deciding what to do next.Full definition →'s sequence of actions. It reports about 25,000 comments a week, with roughly 67% addressed, and a 60% cost reduction against the team's initial implementation. Addressed comments measure developer response, not independently verified correctness. The useful operational change was connecting review output to developer feedback and execution traces, giving the team evidence for tuning its reviewers.
Terms in this piece · Glossary
AI agent — An AI system that doesn't just answer once but works toward a goal in a loop — taking actions, reading the results, and deciding what to do next.
multi-agent — Using several AI agents on one problem — splitting work in parallel, checking each other, or filling different roles like planner and reviewer.
video1,000 Agent Tasks in a Sandbox: What Breaks When LLMs Run Code — Kevin Orellana, AWS
videoHow Inference Keeps Up with Our Insatiable Need for Tokens — Cerebras & Gimlet Labs
videoAuth for Agents: Let AI Sign Up for Your Product with auth.md — Michael Grinich, WorkOS
videoDecoupling the Brain from the Hands: Claude Managed Agents (Part 1 of 4) — Anthropic
