A gold coin weighed on a brass balance scale beside testing acid, a jeweler’s loupe, and an assay ledger with one entry circled — verifying authenticity before trusting it.

Sub-Module 2.2

Before You Trust

An output can look correct and be wrong. It can cite sources that do not exist. It can omit the one fact that changes the answer.

  1. Identify the specific claim or output you are relying on.
  2. Identify the consequence if it is wrong.
  3. Check the claim against a primary source you already trust.
  4. Ask the AI what is uncertain, what assumptions were made, and what is missing.
  5. Run the same query with different wording and compare outputs.
  6. Record the human decision, not just the AI output.

Verification checklist

  • Did I run this prompt more than once, with variation?
  • Did I check at least one specific claim against a primary source?
  • Did I ask the AI what it might have missed or assumed?
  • Is there a human reviewer before this output influences a decision or action?
  • If I am wrong, what is the consequence?
Plausible output is not validated output. Build your verification step before the result reaches a decision — not after something breaks. The difference is invisible until it costs you, and it applies to any high-stakes use.