aiqbench takeAI Products

DoorDash demonstrates a practical application of multi-agent LLMs to solve a specific engineering debt problem: automating the cleanup of 60,000 stale feature flags that traditional static analysis tools missed. By integrating live experimentation data via MCP and human-in-the-loop validation, the system generated usable pull requests in under 14 minutes per task at a fraction of the manual cost. This case study highlights how agentic workflows can handle complex semantic dependencies in dependency-injected architectures where rule-based methods fail.

Source coveringInfoQ

What this isA model's reading of the article and related coverage, written for aiqbench. Not the publisher's words.

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

InfoQSeptember 18, 20263 min read

DoorDash built a multi-agent LLM system to automate stale feature flag cleanup across more than 60,000 flags and 623 repositories. The workflow combines live experimentation data through MCP, engineer approval, isolated Git worktrees, parallel agents, and automated validation. In an evaluation of 50 flags, 45 produced usable pull requests at an average of 13.8 minutes and $4.79 per cleanup. By Leela Kumili

DoorDash has built a multi-agent LLM system to automate stale feature flag cleanup across its codebase, combining live experimentation data, engineer approval, isolated Git worktrees, and automated validation. In an evaluation of 50 stale flags, the system produced usable pull requests for 45, averaging 13.8 minutes and…

Excerpt shown under the publisher's RSS terms · 47 words · full text and figures are on the publisher's site

Read at InfoQ ↗Ask about this article