Uber's Software Factory: 70% of PRs Attributed to AI Agents
JohnAlexander · x · 2026-08-30
Uber's engineering blog details how they run AI agents at scale across their software development lifecycle. Over 70% of Pull Requests are now attributed to local or cloud agents. The article discusses strategies for optimizing a fleet of specialized managed agents, arguing that pairing agents with dedicated benchmarks and Pareto-efficient models is more cost-effective and scalable than optimizing individual terminal sessions for thousands of engineers.
More from coding & agent
- Enter Pro launches tool to build apps and agents — FellMentKE · 2026-08-30
- Enter Pro enables complex apps via natural language — FellMentKE · 2026-08-30
- Agent framework Atomic introduces Recursive State Machines — brandon_galang · 2026-08-30
- Background removal model suffers from reload overhead due to lazy loading — Acceptable-Work8202 · 2026-08-30
- Running agents in production: failures were mechanical, not the model — Wonderful-Match-6256 · 2026-08-30
- Tool solves agent context and memory loss by writing plans to repo files — SSShken · 2026-08-30