Skip to content
// The Playground

Turn your question into a prompt that won’t bluff.

Below is what ChatGPT gives back to a bare question, and what the same model gives back when you stack the prompt — the version that separates what it knows from what it’s guessing, names the risk if it’s wrong, and commits to an answer. See it first, then build one for your own question.

// See it on a real answer

See what the Prompt Stack does to a real answer.

Three real questions. For each, this is what ChatGPT actually returned — first to the bare question, then to the stacked prompt. Real output, nothing invented. Pick one:

“Should I take ibuprofen with my blood pressure medication?”

// Bare question → the answer
Short answer: it depends on the specific blood pressure medication and your health history — but in many cases, you should be cautious. […] Higher-risk combinations — ibuprofen is more likely to cause problems if you're taking ACE inhibitors, ARBs, or diuretics (the "triple whammy"). […] When it might be okay — short-term use, low doses, if your blood pressure is well-controlled. […] What you should do — check the exact BP medication you're on; if possible, ask your GP or pharmacist before taking ibuprofen.

Organised like a helpful FAQ, and reasonable. But it reads as advice you could act on — the uncertainty is buried in “in many cases” and “might be okay.”

Same model, same question — the only thing that changed is the prompt.

Real ChatGPT output (free tier), 15 June 2026, temporary chat — memory off. Trimmed for length where you see …; wording is otherwise unchanged.

// Now your turn

Build one for your own question.

The example above starts loaded. Change the question, change how it’s answered, then copy the prompt and run it in any AI.

Click how you want it answered — each choice adds an instruction. The defaults already make a strong prompt; toggle to make it yours.

ROLE the stance it takes
FILTER fact vs guess
RISK what could go wrong
VERDICT make it commit
// What the Prompt Stack turns it into
ROLE

Be sceptical — assume the easy answer might be wrong until the facts back it up.

FILTER

Split what you actually know from what you're inferring — give me two short lists.

RISK

Name the biggest risk if I act on this and you're wrong.

VERDICT

End with one clear answer and a confidence level (low / medium / high).

YOUR QUESTION

Should I take ibuprofen with my blood pressure medication?

This is the prompt, not the answer. Paste it into your AI and you’ll see the difference in what comes back — the guesses get flagged instead of buried.

// Free — no email

The 30-Second AI Lie Detector

Five checks that catch a confident wrong answer before you act on it. Fits on one page — keep it next to you the next time an AI sounds a little too sure.

Read the five checks →

Open page. No email, no sign-up.

// Or get one a week

One practical idea a week for getting truthful answers out of AI — tested where being wrong actually costs something. Separate thing; the checklist above is yours either way.