Dev3 min reading time

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

InfoQ (AI, ML & Data)
Read the full article
DoorDash developed a multi-agent LLM system using Google's Agent Development Kit and Model Context Protocol to automate cleanup of over 60,000 feature flags, reducing manual effort significantly. The system produced usable pull requests for 45 of 50 tested stale flags, cutting cleanup time and cost compared to manual methods.

More in Dev

Dev2 min read

Moonshot releases Kimi K3.1 Pro and says it cut its hacking skills

Covered by 4 sources
Dev5 min read

Microsoft Open-Sources Agensh: A Multi-Agent Harness for 1,024 Agents

MarkTechPost
Dev5 min read

Cognition Open-Sources an Agent Plugin that Helps Secure Systems against Recent Cybersecurity Threats

MarkTechPost