Metraipolis › archive › dc_9581a3dde059

Automating Feature Flag Cleanup at Scale with Multi-Agent LLM Systems: An Industrial Experience at DoorDash — arXiv:2610.31351

Source
arXiv (en)
Original
https://arxiv.org/abs/2610.31351
License (as archived)
CC0-1.0
Archived
2026-10-25T08:30:50.707Z
SHA-256 of the archived text
449ecc172a4329604b3040abaea5261b7cce7cd8964c35690cc8bb147525aa96
Stable URL of this page
https://metraipolis.com/documento/dc_9581a3dde059

How to cite

Automating Feature Flag Cleanup at Scale with Multi-Agent LLM Systems: An Industrial Experience at DoorDash — arXiv:2610.31351 — arXiv (en), https://arxiv.org/abs/2610.31351 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_9581a3dde059 (Metraipolis archive dc_9581a3dde059, sha256 449ecc172a4329604b3040abaea5261b7cce7cd8964c35690cc8bb147525aa96)
BibTeX
@misc{dc9581a3dde059,
  title = {Automating Feature Flag Cleanup at Scale with Multi-Agent LLM Systems: An Industrial Experience at DoorDash — arXiv:2610.31351},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.31351},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_9581a3dde059; sha256 449ecc172a4329604b3040abaea5261b7cce7cd8964c35690cc8bb147525aa96},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.31351. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

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.

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.MA, nuovi lavori del giorno).
Categorie arXiv: Software Engineering (cs.SE) ; Artificial Intelligence (cs.AI); Multiagent Systems (cs.MA).
Pagina del lavoro: https://arxiv.org/abs/2610.31351 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-25T08:30:42.667Z dalla pagina https://arxiv.org/list/cs.MA/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).