Automating Migration and QA with Codex
charlieholtz · x · 2026-07-10
The author notes that a major team issue was Conductor only having a Mac version, meaning testing was mostly manual and local.
So, they had Fable automate the entire process: porting Conductor to Linux, opening the build in a Conductor Cloud sandbox, performing QA using Codex computer use, and recording the whole process. It actually worked. The author hopes that in the future, when users report a bug, the system can automatically triage, fix, and complete QA in the background.
More from coding & agent
- Soft Clamp cuts tool-call overuse in multi-teacher distillation, from 13.7% to 9.0% — antgroup · 2026-07-21
- SpecJudge runs locally on Ollama to pick the right-sized AI model for your project — jokiruiz · 2026-07-21
- A developer maps out six design rules for CLIs that humans and AI agents can both use — yujiezha · 2026-07-21
- A coding-agent skill that forces ADHD-friendly, answer-first output — ayghri · 2026-07-21
- A set of agent skills for CAD, robotics, and hardware design — earthtojake · 2026-07-21
- Outlines keeps LLMs on-rails with structured outputs — dottxt-ai · 2026-07-21