All work — Machine learning — 2026
Screen Solver
Captures whatever is on screen, asks Gemini to solve it, then types the answer into the app you're focused on.
Runs natively — not a browser app
Ask me about this
The problem
Copying a problem out of a screen into a chat window and back is most of the work.
How I approached it
Screen capture, model call and synthetic keyboard output are chained into one action, so the answer lands in the focused field without a round trip.
The outcome
Screen to answer in a single keystroke.
Next project