AI ships code faster than QA can test: 22 releases, zero rollbacks, one new bottleneck
alex_verem · x · 2026-11-15
A services team running the platform for a performance-marketing company shares three years of experience: the client's CTO writes production code via their own AI agent, while the team owns architecture, review, QA and releases—all code passes the same repo and quality gates. Q1 2026: 22 production releases, zero rollbacks.
The catch: AI now pushes code out faster than QA can check it, making testing the bottleneck. The team flagged it proactively, ran a QA retrospective, and wrote a fix plan. Advice: count last month's merges and how much a tester actually verified before release—if nobody tests faster, customers find the bugs first.
More from coding & agent
- Anthropic's guide to always-on agents: sleep all day, wake for short runs, not 24/7 — udmrzn · 2026-11-15
- Database Architect: a Claude Code agent that designs schemas before you code — adnan_hashmi · 2026-11-15
- Teknium says his Hermes agents are now far more effective than Claude Code — Teknium · 2026-11-15
- Adobe hands CEO role to Anil Chakravarthy, previews local MCP for Photoshop, Illustrator, Premiere — shashib · 2026-11-15
- Running fully local AI to build a prompt-to-music-video pipeline: a deep walkthrough — julianharris · 2026-11-15
- CodeClimb: a coding agent whose reviewer keeps or reverts GraphRAG tuning experiments — blaizedsouza · 2026-11-15