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.
More from coding & agent
- uivoid turns any API into a hosted, authenticated MCP server with zero code — Necessary_Client_114 · 2026-11-21
- Your personal agent can badger airlines over every past delay until they pay up — nickbaumann_ · 2026-11-21
- MIT's Sutherland Verifies Riemann Hypothesis Lean Proof: All 175,187 Modules Compile — altryne · 2026-11-21
- Dev Laments: AI Coding Offloaded the Fun Parts, Leaving Only Reviewing and Correcting — pritisinghhhh · 2026-11-21
- Route agents by task type, not fixed rules: not every request needs a frontier LLM call — rohanpaul_ai · 2026-11-21
- OpenClaw's Skill Workshop 2.0 lets your agent review and improve its own skills — heyneighbor · 2026-11-21