Jon Perl retweeted
It's 2026 and you're still loading some TestFlight build on your personal device and calling it tested.
Get serious about testing iOS and Android apps. QA Wolf's agent now writes, runs, and maintains deterministic E2E tests in open-source Appium.
qawolf.com/changelog/mobile-…
full circle. qa wolf v1 was a recorder. now we have an AI recorder.
why build a recorder? isn't that old school?
i was against it at first. it's much lower friction to give AI high level direction and let it do the grunt work of figuring out the test.
but sometimes you need to show the AI exactly what to test, and in what order. some systems require a specific path that can't be intuited.
our AI recorder lets you do that, then turns it into high quality code. it cleans up redundant steps, uses POM, and makes the test resilient
I really enjoyed building this one at QA Wolf!
Instead of explaining to an agent what you want to test, you can just show it in the browser. The agent can then take over, clean things up, and turn it into a Playwright test.
qawolf.com/blog/how-qa-wolf-…
Jon Perl retweeted
I really enjoyed building this one at QA Wolf!
Instead of explaining to an agent what you want to test, you can just show it in the browser. The agent can then take over, clean things up, and turn it into a Playwright test.
qawolf.com/blog/how-qa-wolf-…
Jon Perl retweeted
Today, our team is excited to announce @InspiredCap Fund IV, $450M in new capital to back early-stage founders.
There has never been a moment in history when more is possible. It takes just one person with exceptional ambition to take on the world’s problems and change billions of lives for the better.
Jon Perl retweeted
A lot of what we do at QA Wolf is designing agentic systems to do what humans do naturally. Humans are great at sorting test failures by a root cause, but slow. Agents are fast but need explicit rules to work together. Check it out: qawolf.com/blog/how-qa-wolf-…
Jon Perl retweeted
AI investigation is now live for everyone.
The moment a test fails, an agent jumps in. Broken tests are updated, bugs are filed, flakes are re-run.
QA cycles run 6.5x faster because you're not waiting for the whole suite before triaging failures.
qawolf.com/changelog/ai-inve…
tried to resolve a customer support ticket assigned to me but the ai held me accountable to a proper solution 😅
Jon Perl retweeted
how it feels to interact with my human family after another 14 hour day of interacting with Claude
Jon Perl retweeted
'twas no small feat building the infrastructure for Windows testing — check it out 👇
not just tests, even our ai chats get a computer. here is why:
A new model launches every other week. GPT-6.1 Sol, Gemini 4 Argon, Claude Opus 5.5, each new release beating the last on some benchmark. But on its own, even the smartest model can only tell you how to fix a broken test. To actually fix it, it needs somewhere to work: your code, a browser to open your app, and a way to run the test and see it pass, that’s the sandbox.
QA Wolf AI’s is warm in milliseconds, with a real file system, a git clone of your test suite and a live browser you can watch. When the task is big, it spins up 50 more sandboxes, each with its own browser and branch.
Here’s how we built it: qawolf.com/blog/every-ai-age…
