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.
Related event: Uber Reveals 3,600 AI Agents Now Handle 70% of PRs While Costs Fall 52%(5 posts)→
More from coding & agent
- Turning code into knowledge animations: 4 prompt styles plus a take on Skills vs prompts — vista8 · 2026-10-16
- Tool lets AI agents use your accounts without ever seeing your login credentials — cneuralnetwork · 2026-10-16
- Claude Code plugin /ambition rewrites your task into the version a more ambitious person would ask for — jakedahn · 2026-10-16
- arXiv paper "Self-Evolving Agent Harness" formalizes harness self-evolution with admission rules — rohanpaul_ai · 2026-10-16
- Self-improving agents should only accept harness edits that beat the current version on fresh tasks — rohanpaul_ai · 2026-10-16
- Bland launches iMessage business agents: send a link, get a branded agent in 30s — EXM7777 · 2026-10-16