Ship: an autonomous QA agent that tests PRs and hands bugs to Claude or Codex

rohanpaul_ai · x · 2026-10-06

ContextQA launched Ship, an AI agent positioned as an autonomous QA engineer: it reads a PR, figures out which user flows the change affects, and runs those flows against the deployed app. It can also reproduce bugs reported in Slack or Linear, pinpoint likely causes, and hand evidence to developers or coding agents like Claude and Codex to fix. The author notes generating PRs is now cheap, but verifying they didn't break user flows still eats engineering time — and if agents ship more code, something other than a human has to exercise the result.

Related event: ContextQA Launches Ship: An Autonomous QA Engineer That Tests PRs and Hands Off Fixes(8 posts)→

Original post →

More from coding & agent

coding & agent channel →