DoorDash automates removal of obsolete software feature flags

Automating Feature Flag Cleanup at Scale with Multi-Agent LLM Systems: An Industrial Experience at DoorDash

Software EngineeringArtificial IntelligenceMultiagent Systems

Summary

Feature flags are like on/off switches for software features, but old ones can clutter code and cause problems. The authors show how DoorDash used advanced language AI programs to quickly and cheaply clean up these old flags across many software projects. The system checks data, reads tickets, and makes code fixes automatically, succeeding in most cases tested. This shows how smart automation can handle complicated coding chores effectively.

What this means in practice

  • For software engineering teams: Automatically identify and remove outdated feature flags in large codebases to reduce maintenance effort and operational risk.
  • For devops teams: Integrate multi-agent language model systems to automate routine code cleanup tasks and streamline software deployment pipelines.

Authors

Atharv Chandratre, Jai Datar

Abstract

Feature flags are runtime configuration mechanisms used for gradual feature rollouts, experimentation, and kill switches. Once a feature is fully rolled out, the flag and its gated code become technical debt and can introduce operational risk through inadvertently enabling dormant code paths. At DoorDash, over 56,000 feature flags span 623 repositories, with 1,659 currently stale as of May 2026, with internal estimates of one to two hours per manual cleanup. Existing rule-based cleanup tools proved insufficient in DoorDash's codebases. Our contribution is an end-to-end automated LLM-based feature flag cleanup system that integrates querying live feature flag rollout data using MCP, Jira ticket processing, and end-to-end pull request creation. Our system successfully produced engineer-approved flag removal PRs for 45 (90%) of the 50 stale flags it was evaluated on, proving the system's operational viability at scale with each cleanup averaging only $4.79 and 13.8 minutes. We evaluated the system's quality and reliability boundary based on success rates, cost per cleanup and time metrics. Furthermore, we discuss our lessons learned when architecting this system, to provide practical guidance for developing similar multi-agent systems.