Just did this locally by giving my AI agent full ADB access to a test phone I have. It's actually kinda amazing just watching it swipe, open the app launcher, and find issues to fix later.
What was the modality of interpreting the UI/interacting with the phone via ADB? Did you/your agent use screenshots + vision model to essentially target coordinates on screen? I ask because I'm curious if you found a non-screenshot + coordinate based ADB method to do so (that doesn't rely on UIAutomator). I wrote an APK that gives access to the accessibility service via an in-Android http server, which talks to a dae…
Would be great if you have a way to do it programmatically.