Skip to main content
MethodResearch & LearningResearchIntermediate

Produce a desk research brief

A sourced research brief answering a specific question with confidence levels and gaps.

This is a practical, copy-paste process for you need a reliable answer to a business or policy question quickly.. 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
# Produce a desk research brief
Method by Deepstory Research: deepstoryresearch.com/method/desk-research-brief

You are a research analyst at a think tank. Follow the method below step by step. Goal: A sourced research brief answering a specific question with confidence levels and gaps.

## My inputs
- Research question: [RESEARCH_QUESTION]  (example: how fast is EV adoption growing in India vs China)
- Audience: [AUDIENCE]  (example: leadership team)
- Depth: [DEPTH]  (example: 2 pages)
- Sources to prefer: [SOURCES_TO_PREFER]  (example: official statistics, attach Deepstory evidence files)

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. Break the question into sub-questions.
2. Gather evidence from provided files first, then (if browsing is available) primary sources.
3. Tier sources: official/primary, reputable secondary, opinion.
4. Answer each sub-question with confidence level.
5. Note conflicting data and what explains the difference.
6. List what remains unknown.

## Deliver the output in this structure
- Bottom line
- Findings by sub-question
- Source table with tier and date
- Conflicts
- Unknowns

## Quality rules
- Every number has a source and date.
- Say "cannot answer from available sources" when true.
- 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
Research question[RESEARCH_QUESTION]how fast is EV adoption growing in India vs China
Audience[AUDIENCE]leadership team
Depth[DEPTH]2 pages
Sources to prefer[SOURCES_TO_PREFER]official statistics, attach Deepstory evidence files

Use it when

  • You need a reliable answer to a business or policy question quickly.

What you get

  • Bottom line
  • Findings by sub-question
  • Source table with tier and date
  • Conflicts
  • Unknowns

The procedure, step by step

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

  1. 1

    Break the question into sub-questions.

  2. 2

    Gather evidence from provided files first, then (if browsing is available) primary sources.

  3. 3

    Tier sources: official/primary, reputable secondary, opinion.

  4. 4

    Answer each sub-question with confidence level.

  5. 5

    Note conflicting data and what explains the difference.

  6. 6

    List what remains unknown.

Quality checks built into the prompt

  • • Every number has a source and date.
  • • Say "cannot answer from available sources" when true.
  • • Every number labelled FACT, ESTIMATE or ASSUMPTION; claims outside attached evidence tagged [UNVERIFIED].

Evidence to use with this method

Methods tell the AI how to think. Evidence gives it sourced numbers to think with. Download a context file and attach it with the prompt.

Run next

Methods that chain well after this one.

Research & LearningFact-check a claimA verdict on a claim with evidence for and against, source quality and what is missing.Pitch & CommunicationWrite an executive summaryA one-page summary of a long document that leads with the answer and the ask.Research & LearningWrite a literature reviewA thematic literature review with synthesis, gaps and a references table from the papers you provide.Research & LearningDesign a surveyA survey with objectives, unbiased questions, answer scales, sampling plan and analysis plan.

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.