LLM Digest

Story

infoq_ai_ml · Sep 18, 2026 · news

Source brief

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

infoq.comSep 18, 2026
original source linked

In brief

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, isolat...

Feed lens

agentevaluation

Read the original at infoq.com →Open in live feed

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

Earlier in this thread 4 items

DoorDash’s Flux Runs 130,000 Engineering Tasks Through Cloud-Based Agents

DLLM: Minimal, clean coding agent built directly on llama.cpp without overhead

How DoorDash Built an AI Shopping Assistant That Doesn’t Rely on the LLM Alone

PageToMD – A CLI tool to turn web pages into clean Markdown for AI agents