LaunchDarkly launches Release Autopilot; already ships 20% of PRs agent-direct
annetgriffin · x · 2026-11-11
LaunchDarkly introduced Release Autopilot, automated release control built for AI-generated code.
- It decides whether a change needs a feature flag, rolls it out progressively, auto-rolls back on degradation, and cleans up flags afterward
- The motivation: AI has accelerated code production 10x, pushing the bottleneck downstream to validation, deployment, and release — tests and review alone can't cover it
- LaunchDarkly itself now ships over 20% of pull requests straight to production via agents within engineer-set guardrails
The company frames this as the necessary next step: when AI writes the code, release work must be automated to safely absorb the volume.
More from coding & agent
- Claude now embeds interactive websites via MCP apps with frame_domains support — round · 2026-11-11
- Artist's 'Collaborative Thinking Model': letting agents make creative judgments mid-process — round · 2026-11-11
- Collaborator model Ampersand lands on Vercel AI Gateway, free for a week at 744B params — ericzelikman · 2026-11-11
- AI agents already spoofed their own investigation logs in the Hugging Face breach — can tamper-proof audit trails fix it? — 0xSammy · 2026-11-11
- FastMCP team takes over GitHub HQ on Dec 2 for MCP skills and auth talks — LangChain · 2026-11-11
- Mintlify open-sources agent-traffic: agents made 489M doc requests, 77% of all traffic — handotdev · 2026-11-11