← Noesa

Catch the AI: verify before you trust

For A professional recently handed AI tools at work — an analyst, coordinator, ops/support/marketing person, or PM — who uses AI daily and doesn't want to be the one who forwarded its confident mistake. · 15 days · Concepts

A 15-day course
One short lesson a day · go at your own pace
Log in to start
The days
  1. 1Meet the confident liarBy the end you can explain why an AI answer can be specific, fluent, and wrong at the same time — and point to the exact moment a check was needed.
  2. 2See why it sounds so sureBy the end you can explain, in one sentence, why a language model can produce a polished answer without first establishing that its claims are true.
  3. 3Name the six ways it goes wrongBy the end you can classify an AI mistake as fabrication, bad math, stale information, misreading the ask, overreach, or inherited bias and choose the first check each needs.
  4. 4Catch invented facts, quotes and sourcesBy the end you can trace a factual claim, quotation, or citation to a primary source and reject references that cannot support the exact sentence.
  5. 5Catch numbers that don't add upBy the end you can verify an AI-produced total, percentage, or average by recovering its inputs, recomputing it, and checking whether the comparison makes operational sense.
  6. 6Name the claim, then check itBy the end you can classify a claim as a fact, number, summary, internal claim, or judgment and select the evidence needed before trusting it.
  7. 7Verify a factBy the end you can verify a factual claim by defining its scope, tracing it to an appropriate primary source, and recording a reproducible verdict.
  8. 8Verify a numberBy the end you can produce a number-check record that preserves source inputs, definitions, formula, recomputation, and a sanity verdict.
  9. 9Verify a summaryBy the end you can verify an AI summary by mapping each important source point to the summary and marking omissions, additions, distortions, and misplaced certainty.
  10. 10Verify against your worldBy the end you can identify an internal claim, locate the controlled source or accountable owner, and separate company truth from a plausible industry default.
  11. 11Make the AI check itselfBy the end you can ask an AI to expose sources, assumptions, calculations, uncertainties, and counterarguments while identifying which parts still require independent verification.
  12. 12Match the checking to the stakesBy the end you can set a proportionate verification level using potential harm, audience reach, reversibility, and the authority your output will carry.
  13. 13Know when to stop and escalateBy the end you can recognize when verification exceeds your evidence or authority and escalate with a clear claim, risk, work completed, and decision needed.
  14. 14Build your verification checklistBy the end you can assemble a one-page Verification Checklist that routes claims, scales effort to stakes, records evidence, and triggers escalation.
  15. 15Run the full check on real workBy the end you can run your Verification Checklist on one real AI-assisted artifact and document a ship, revise, stop, or escalate decision.