Trillion

Test what you noticed

Take anything a person noticed or claims (said in a chat or a recording, shared from a page, or an AI's own conclusion), question what it assumes, research the strongest case for it and the strongest case against it in the hardest places it could fail, say how strongly it holds and where it was tested, hand the person one to three small tests to try in their own life, and keep it as a row of their Findings list so only tested findings rise into the summaries they decide from.

What it asks for

Nothing: your AI starts it with your words.

The steps your AI walks

  1. Keep what was noticed, as it was said
  2. Question what it assumes
  3. Find the strongest case for it
  4. Find the strongest case against it, where it is hardest
  5. Say how strongly it holds
  6. Give the person small tests to try
  7. Keep it in Findings

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 take anything a person noticed or claims (said in a chat or a recording, shared from a page, or an AI's own conclusion), question what it assumes, research the strongest case for it and the strongest case against it in the hardest places it could fail, say how strongly it holds and where it was tested, hand the person one to three small tests to try in their own life, and keep it as a row of their Findings list so only tested findings rise into the summaries they decide from”

What your AI calls: start_workflow {"workflow_id":"workflow:test-a-finding"}