Hey! I built Bytesalt and excited to share it here.
Every engineering team I've been part of has had the same problem. Playwright (or similar) scripts pass, yet critical bugs showed up when real users used our software. I don't think this is because Playwright is inherently bad - it is doing its job perfectly well - testing exactly what we told it to test.
The problem is - real world bugs happen because we didn't think to test a particular path - think a support widget covering the checkout button on smaller screen phones, or a race condition when clicking through buttons in a particular order. These kind of things need real humans to test software - but that is too expensive, slow and doesn't scale, especially with the pace of software development today.
With Bytesalt - you can describe what you want in plain English (for example- "Test the checkout flow on mobile") and Bytesalt fans out the work across parallel AI agents that simulate real users. Each agent explores the app with a different lens such as - functional QA, UX/Visual, usability, accessibility and security. Finally an agent collects all the results and produces a final bug report.
It has a web interface for humans as well as a CLI that can be integrated with CI/CD tools or used by coding agents.
You can try it on bytesalt.com (free tier - no credit card). A simple prompt, for example - "Test https://www.craigslist.org for usability on an iPhone. Check only above the fold. Report a single issue and stop. Do not explore."
Would love to hear any feedback. What would make this useful for your workflow? What's missing?
Comments URL: [https://news.ycombinator.com/item?id=48746576](https://news.ycombinator.com/item?id=48746576)
Points: 1