Skip to main content
MethodAI Setup & ProductivityAI setupStarter

Improve any prompt

A rewritten prompt with role, context, task, format and constraints, plus why it is better.

This is a practical, copy-paste process for an ai keeps giving vague or wrong answers.. Use it when you want a clear structure, then add your own details and the linked evidence.

Published by Deepstory Research. Reviewed Sep 2026.

How to use this method

  1. 1. Copy or downloadCopy the prompt below, or download the method file and attach it to your chat.
  2. 2. Paste into any AIChatGPT, Claude, Gemini or Copilot. Replace each [PLACEHOLDER] with your details, or let the AI ask you.
  3. 3. Add evidenceAttach the evidence files listed on this page so the AI works from sourced numbers, not guesses.

The prompt

Paste it as-is. The AI will ask for anything still in [BRACKETS].

Download .md
# Improve any prompt
Method by Deepstory Research: deepstoryresearch.com/method/prompt-improver

You are a prompt engineer. Follow the method below step by step. Goal: A rewritten prompt with role, context, task, format and constraints, plus why it is better.

## My inputs
- Your current prompt: [YOUR_CURRENT_PROMPT]  (example: paste)
- What you wanted vs what you got: [WHAT_YOU_WANTED_VS_WHAT_YOU_GOT]  (example: describe)
- Target AI tool: [TARGET_AI_TOOL]  (example: ChatGPT / Claude / Gemini)

Before you start: if any input above is still in [BRACKETS] or missing, ask me for it in one short numbered list and wait. Do not guess. If I attached files (data, briefs, Deepstory evidence files), treat them as the primary source.

## Steps to follow
1. Diagnose what is missing (context, goal, format, examples, constraints).
2. Ask up to 3 questions if critical info is missing.
3. Rewrite the prompt with clear sections.
4. Add an example of the desired output if helpful.
5. Explain the changes briefly.

## Deliver the output in this structure
- Diagnosis
- Improved prompt
- Optional example
- What changed

## Quality rules
- Keep the user’s intent; do not add scope they did not ask for.
- Label every number as FACT (with source and date), ESTIMATE (show the calculation) or ASSUMPTION.
- If a Deepstory evidence file is attached, use its figures as the reference values and cite its source references; tag claims that are not from it as [UNVERIFIED].
- End with: the 3 assumptions that matter most, what would change the answer, and the single best next step.

What you need to give the AI

InputPlaceholderExample
Your current prompt[YOUR_CURRENT_PROMPT]paste
What you wanted vs what you got[WHAT_YOU_WANTED_VS_WHAT_YOU_GOT]describe
Target AI tool[TARGET_AI_TOOL]ChatGPT / Claude / Gemini

Use it when

  • An AI keeps giving vague or wrong answers.

What you get

  • Diagnosis
  • Improved prompt
  • Optional example
  • What changed

The procedure, step by step

Read this before you run it, so you can check the AI actually followed the method.

  1. 1

    Diagnose what is missing (context, goal, format, examples, constraints).

  2. 2

    Ask up to 3 questions if critical info is missing.

  3. 3

    Rewrite the prompt with clear sections.

  4. 4

    Add an example of the desired output if helpful.

  5. 5

    Explain the changes briefly.

Quality checks built into the prompt

  • • Keep the user’s intent; do not add scope they did not ask for.
  • • Every number labelled FACT, ESTIMATE or ASSUMPTION; claims outside attached evidence tagged [UNVERIFIED].

Evidence for this method

This method runs on your own material: your files, brief or code. If your task needs market or economic numbers, attach a sourced context file from the evidence library alongside the prompt.

Browse evidence

Run next

Methods that chain well after this one.

Deepstory methods are process guidance for AI tools. Review AI output before relying on it; legal, tax, medical and investment decisions need a qualified professional.