One-liner: Catch an AI making a confident mistake — and build a simple verification process you'll use every time.
Pick a topic you know well — your industry, your hobby, your area of expertise. Something where you can spot errors.
Step 1 — Get a confident answer. Send this prompt:
Give me a detailed overview of [topic you know well]. Include specific facts, statistics, and examples. Be thorough and authoritative.
Read the output carefully. Find at least one claim that feels off. It might be a statistic that seems too round, a date that feels wrong, a name that's slightly off, or a causal claim that oversimplifies reality.
Step 2 — Make the AI check itself. Send this:
Look at your previous response. I want you to fact-check yourself. For each specific claim, statistic, or example you cited:
- Rate your confidence (high / medium / low)
- Flag anything you might have fabricated or estimated
- Identify which claims are most likely to be wrong and why
Be ruthlessly honest. I'd rather know what you're uncertain about than have you defend everything.
Step 3 — Verify. Pick the 2-3 claims the AI flagged as lowest confidence. Google them. Were they accurate, close but wrong, or completely fabricated?
Step 4 — Build your check. Based on what you just learned, write a 3-line "verification prompt" you can append to any AI output:
Before I use this, tell me:
- Which specific claims are you least confident about?
- What did you estimate or approximate vs. know with certainty?
- What should I verify independently before sharing this?
Save this somewhere you'll see it. Use it as a default follow-up to any AI output you plan to rely on.
Here's what you're about to do:
"Done" looks like: You've caught at least one AI error, you understand why the AI got it wrong, and you have a saved verification prompt you can use going forward.
The community's Ethical Prompting score is 75% — the highest of all five pillars. Most people know they should verify AI output, but few have a systematic process for doing so. This exercise closes the gap between awareness and practice by giving you a concrete, reusable tool. The verification prompt you build here becomes a habit — a 30-second step that catches errors before they become problems. At the intermediate level, you'll build a more comprehensive verification checklist; this exercise establishes the baseline behavior.
Ready for more? Try EP-Intermediate-01 — where you'll build a comprehensive verification checklist and stress-test it against real AI outputs.
Back to Ethical Prompting & Judgment