DoorDash Uses Multi Agent LLMs to Clean up 60,000 Feature Flags

DoorDash built a multi-agent LLM system to automatically remove stale feature flags. In a test on 50 flags, the system produced working pull requests for 45 of them, spending an average of 13.8 minutes and $4.79 per cleanup versus 1–2 hours of manual work.

InfoQ Open source

DoorDash Uses Multi Agent LLMs to Clean up 60,000 Feature Flags

DoorDash manages over 60,000 feature flags across 623 repositories, creating about 2,300 new ones monthly
A flag is considered stale if unchanged for 90 days, still used in code, and not archived
Orchestrator on Claude Sonnet and agents on Claude Opus work in isolated Git worktrees, up to 4 agents per repository
Of 50 cleanups: 31 accepted first try, 14 reworked, 5 engineer interventions, no bugs found

#DoorDash#Anthropic#Google

DoorDash Uses Multi Agent LLMs to Clean up 60,000 Feature Flags

OpenAI details six real model misalignment incidents

Space Daily Published AI Slop Under Fake NASA and ESA Expert Bylines

Fastly launches AI Runtime Control and AI Firewall for enterprises

Leak: Gemini 4 Pro Enters Arena Testing for Multimodal AI