Reverse-engineer the prompt behind an output
Works backwards from text, code, or an image to the prompt that likely produced it.
The prompt
Reverse-engineer the prompt that likely produced this output.
Output (text, code, or image description):
[PASTE]
The tool it came from (if known): [TOOL]
Analyze its tone, structure, length, format, vocabulary, and constraints to infer the instructions behind it. Then give:
1. The most likely original prompt.
2. A cleaner, reusable template version with [PLACEHOLDERS].
3. Your reasoning: which features of the output point to which instructions.
4. How to tweak the prompt to change the result (e.g. more formal, shorter, different format).
Highlighted [brackets] are blanks to replace with your own details.
Fill in the blanks and use this promptMore Working with AI prompts
What to fill in
- PASTE
- TOOL
- PLACEHOLDERS
How this prompt is built
This prompt follows the RTF structure (Role, Task, Format). RTF tells the model who to be, what to do and what shape the answer should take. It is the quickest structure that still gives noticeably better results than a bare request.
Related prompts
- Turn a one-off AI chat into a reusable prompt pack for my teamExtracts the prompts, fixes, and checks from an AI chat that worked into a step-by-step workflow and prompt pack colleagues can reuse.
- Score an AI output against the prompt that produced itA requirement-by-requirement scorecard for an AI output, separating prompt problems from output problems, with prompt fixes.
- Find where AI can help in my work or businessInterviews you about a process and identifies where AI genuinely helps — and where it doesn't.
- Check AI output for errors and hallucinationsA verification checklist to catch fabricated facts, faulty logic, and unsupported claims before you rely on AI output.