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

8.2 relevance

DoorDash's multi-agent LLM system for feature flag cleanup is deeply technical, actionable, and directly matches reader interests.

AI/ML infoq.com

Answer the board on AI readiness

Arrive with evidence, not opinion. See how your foundation benchmarks against your peers, get a clear read, and leave with a ranked place to start.

Why It Matters

This demonstrates a practical, cost-effective multi-agent LLM workflow for large-scale codebase maintenance, directly relevant to platform engineering and developer experience at scale.

Key Takeaways

Evaluate multi-agent LLM systems with isolated worktrees and MCP for automating complex, cross-file code cleanup tasks in your own platform.

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

Summary

DoorDash deployed a multi-agent LLM system on Google's Agent Development Kit, using Claude Sonnet for orchestration and Claude Opus for cleanup in isolated Git worktrees, to automate removal of stale feature flags across 623 repositories. The system handles dependency-injected wrappers that require changes across 5-20 files per flag—a pattern Uber's Piranha couldn't address—and produced 45 usable pull requests from 50 evaluated flags, averaging 13.8 minutes and $4.79 per cleanup versus 1-2 hours manually. No bugs or regressions were reported, and DoorDash plans to add confidence scoring and post-cleanup code quality passes.

Author

Leela Kumili