I build a mobile app on my own. Unit tests pass, the app works on my phone, and then someone on an iPhone SE with large text finds a button hidden under the keyboard. I wanted something between unit tests and real beta testers, so I built this:
One GitHub Actions workflow that builds your app, starts up to 20 iOS Simulators and Android emulators, and gives each one to an AI agent with a persona. Each agent uses the app like a new user and writes a bug report with numbered screenshots.
It's open source (MIT): github.com/pierridotite/mobile-agent-testers
Update: 20 phones at once on LocalSend
I then ran all 20 personas at once on LocalSend , a 100k-star Flutter app: 10 Android emulators and 10 iOS Simulators, 14 languages, phones and tablets. 103 issues in 69 minutes, for $4.62 of model usage.
The worst one: on an iPhone SE at iOS's largest text size, the "type a message" dialog overflows by 149 px, so the text field and Confirm are off screen and you can't send text at all.…