I shipped an Android app mostly by pairing with Claude Code. Writing features went fine. Testing them on a real phone did not. The problem When an AI coding agent tests an app on a device, the usual loop is: take a screenshot, look at it, decide where to tap, tap, take another screenshot. Every step sends an image to the model. A 20-step login-and-checkout flow can cost thousands of image tokens, fill the context window, and the agent still sometimes taps the wrong thing. Most...