Tweet
Introducing Expect Let agents test your code in a real browser 1. Run Claude Code / Codex to QA your app 2. Watch a video of every bug found 3. Fix and repeat until passing Run as a CLI or agent skill. Fully open source https://t.co/xHfZMIY97s
This has a linked resource worth reading, a tool worth trying, or an idea worth prototyping
Quick Insight
This is announcing "Expect" - a tool that lets AI agents (Claude, etc.) automatically test web apps by actually running them in browsers, recording videos of bugs they find. It's automated QA testing powered by AI agents that can see and interact with your UI like a human would.
Actionable Takeaway
Try running Expect on one of his Chrome extensions or print-on-demand tools to see how AI agents perform compared to his current manual testing workflow. The CLI approach would fit well into his existing dev processes.
Related to Your Work
Perfect for his fintech platform's webhook integrations and analytics dashboards - areas where UI bugs can break critical user flows. Could also automate QA for his web agency tools, freeing up time to focus on building features instead of manual testing.
Source Worth Reading
Yes - the linked repo will show implementation details, setup instructions, and examples of what the AI agents can actually catch. Worth checking if it integrates with his existing TypeScript/serverless stack.