A FREE PROMPT
How to tell when your AI is bluffing.
One paste-in instruction set, built from months of graded AI answers, that makes any assistant show its working before you trust it.
What’s inside
Use. It checks the answer against what you’re about to do with it, not only against the facts.
Scope. It names where the answer is good as of, and stops before it guesses past that.
Filter. Every claim labelled: known, inferred, or a guess. Nothing stated as fact unlabelled.
Risk. It names the one thing that would prove it wrong.
Verdict. A stated confidence level and a usable next step.
I’m Ben. I put the same real questions to six AI assistants and publish every graded answer. The filter is what I run before trusting any of them.
Get your free copy.
The filter is the method, distilled. Here is the thinking it folds down from.
The Prompt Stack
Four stages that turn a vague question into one an AI can’t bluff through: SCOPE, FILTER, RISK, VERDICT. The long-form version of what the filter does in one paste.
See the Prompt Stack →The Guardrails
Seven checks you run on the answer you already have, each backed by a dated receipt where it would have caught something real.
See the Guardrails →One habit inside the checking half earns its own page: the Source Ladder. And the proof any of this matters is the Scoreboard.