⚡ Launch sale — 67% off the Everything Bundle · 7-day money-back guarantee Get the deal →

The Prompt Engineering Cheat Sheet — 10 Patterns That Fix Bad AI Output (Free)

Most disappointing AI output comes from under-specified prompts, and the fix is mechanical. These 10 patterns work in ChatGPT, Claude, Gemini and Copilot. Copy the template, fill the brackets, stack patterns freely.

The 10 patterns

  1. Role. You are a [senior email copywriter for e-commerce brands]. — sets expertise and tone in one line.
  2. Context dump. Context: [audience, product, goal, constraints]. — the model cannot use what it does not know; give it everything relevant, ugly formatting is fine.
  3. Output format. Answer as: [a 5-row markdown table with columns X, Y]. — kills rambling instantly.
  4. Show an example. Here is one example of the style I want: […]. Match it. — one example beats three paragraphs of description.
  5. Constraints. Max 120 words. No exclamation marks. Grade-7 reading level. — boundaries produce discipline.
  6. Think step-by-step. Reason through this step by step before giving your final answer. — for anything with logic or numbers.
  7. Critique-then-rewrite. Now critique your answer against [criteria] and rewrite it stronger. — the single highest-leverage second message.
  8. Audience lens. Rewrite this for [a busy founder who skims]. — same content, different reader, different words.
  9. Iterate narrow. Change one thing per follow-up (“same, but shorter hooks”) instead of re-prompting from scratch.
  10. Demand honesty. If you are not sure, say so. Mark any claim that needs a source with [verify]. — cheap insurance against confident nonsense.

FAQ

Which AI tool do these work with?

All major chat models — ChatGPT, Claude, Gemini, Copilot. The patterns are model-agnostic because they fix the prompt, not the model.

What is the fastest way to level up from here?

Stack three patterns per prompt: Role + Context + Format solves most everyday tasks. Add Critique-then-rewrite when quality matters.