Review screens before they ship

Runs lint, captures each screen at narrow and wide widths, probes keyboard, focus and loading traps, and walks the criteria. For a team deciding whether screens are ready to release.

What it asks for

  • about (Optional, words): What this run is for, in the person's words.
  • known (Optional, words): What is already known, decided or done, so the run starts from it instead of asking again.

The steps your AI walks

  1. Say what is reviewed
  2. Run the project's own checks and capture the render
  3. Probe each screen's traps on a local build
  4. Walk the criteria at each width
  5. Sort findings into blocking, should-fix, note, dismissed
  6. Write the verdict last
  7. Record what was found and what matters most

Use it from your AI

Connect the AI you already use to Trillion once. Then ask in your own words; your AI finds this workflow by what it does and runs it.

Say to your AI: “Use Trillion to runs lint, captures each screen at narrow and wide widths, probes keyboard, focus and loading traps, and walks the criteria. For a team deciding whether screens are ready to release”