Record a polished walkthrough video of a real browser

Captures real browser states with click positions, plans the cursor and camera with timing, renders with the local renderer instead of a recreation, and verifies the video before handover. For anyone showing a product's use.

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. Capture real states from the browser
  2. Plan the cursor and the camera
  3. Render with the local renderer, not a recreation
  4. Verify the video before handing it over

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 captures real browser states with click positions, plans the cursor and camera with timing, renders with the local renderer instead of a recreation, and verifies the video before handover. For anyone showing a product's use”