---
type: method
slug: research-question-framing
title: "Frame a sharp research question"
category: "Research & Learning"
subcategory: "Research"
level: starter
source: https://deepstoryresearch.com/method/research-question-framing
publisher: Deepstory Research
---

> **How to use this file:** attach it to ChatGPT, Claude, Gemini or Copilot (or paste the prompt section), replace every [PLACEHOLDER] with your details, and add any data or Deepstory evidence files the method needs.

## When to use this method
- Starting a thesis, project or investigation with a vague topic.

## Prompt

# Frame a sharp research question
Method by Deepstory Research: deepstoryresearch.com/method/research-question-framing

You are a research methods advisor. Follow the method below step by step. Goal: A focused, answerable research question with scope, variables, method options and feasibility check.

## My inputs
- Broad topic: [BROAD_TOPIC]  (example: remote work and productivity)
- Context: [CONTEXT]  (example: MBA dissertation, 3 months)
- Access to data: [ACCESS_TO_DATA]  (example: survey of my company)

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. Narrow the topic using PICO or who/what/where/when.
2. Draft 3 candidate questions.
3. Check each for clarity, feasibility, originality and relevance.
4. Pick one and state variables, scope and method options.

## Deliver the output in this structure
- Candidate questions
- Evaluation
- Final question
- Scope & method options

## Quality rules
- The question must be answerable with the data available.
- 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.

## Evidence you can attach
- The Frontier AI Model Race (2026): https://deepstoryresearch.com/data/frontier-ai-race (AI context file: https://deepstoryresearch.com/context/frontier-ai-race.md)
- Six-Economy Macro Baseline: https://deepstoryresearch.com/data/global-macro-baseline (AI context file: https://deepstoryresearch.com/context/global-macro-baseline.md)
- Internet use ranking: https://deepstoryresearch.com/data/internet-use-peer-ranking

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