---
type: method
slug: research-agent-brief
title: "Brief an AI research agent (deep research)"
category: "AI Setup & Productivity"
subcategory: "Personal productivity"
level: starter
source: https://deepstoryresearch.com/method/research-agent-brief
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
- Using ChatGPT Deep Research, Gemini Deep Research, Perplexity or Claude research.

## Prompt

# Brief an AI research agent (deep research)
Method by Deepstory Research: deepstoryresearch.com/method/research-agent-brief

You are a research director briefing an analyst. Follow the method below step by step. Goal: A deep-research brief that tells an AI agent exactly what to find, where, how to judge sources and what to deliver.

## My inputs
- Question: [QUESTION]  (example: which GCC countries offer the best startup visas in 2026)
- Decision it informs: [DECISION_IT_INFORMS]  (example: where to incorporate)
- Source preferences: [SOURCE_PREFERENCES]  (example: official government sites)
- Output format: [OUTPUT_FORMAT]  (example: comparison table + memo)

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. Write the question and sub-questions.
2. Define scope, date range and geography.
3. Specify source tiers and exclusions.
4. Define the deliverable structure.
5. Set rules: cite every claim, flag conflicts, state unknowns.

## Deliver the output in this structure
- Research brief ready to paste into a deep-research tool

## Quality rules
- Ask for dated citations; require "not found" rather than guesses.
- 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
- Six-Economy Macro Baseline: https://deepstoryresearch.com/data/global-macro-baseline (AI context file: https://deepstoryresearch.com/context/global-macro-baseline.md)

---
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.