Build a Research Brief Generator
Create a repeatable workflow that turns a vague question into a structured research brief with sources, open questions and a confidence rating. The output is something you can hand to a colleague, not a wall of text.
Why this one
A single "research this for me" prompt produces confident prose with invented citations. Splitting the work into three passes — scope, gather, verify — produces something you can defend, because each pass has one job and you can inspect its output before the next one runs.
Steps
Pass one: scope the question
Before any searching, force the model to narrow the question and state what would count as an answer. This is the step everyone skips and it is the one that determines whether the rest is useful.
PromptI want to research: [your question]. Before answering, do three things: 1. Restate the question in a narrower, answerable form and explain what you cut. 2. List the 4-6 sub-questions that together would answer it. 3. State what kind of evidence would settle each sub-question (statistics, primary documents, expert consensus, first-hand accounts). Do not answer the question yet.
Pass two: gather against the sub-questions
Take the sub-questions from pass one and research them one at a time, in a tool that can actually search. Doing them one at a time is deliberate: a model asked six questions at once will answer the easy ones well and bluff the hard ones, and you will not be able to tell which is which.
Pass three: verify before you trust
Paste the gathered material back and ask for an adversarial read. The instruction to distinguish "the source says this" from "I am inferring this" is the one that catches most fabrication.
PromptHere is a research draft. For each claim: mark it [SOURCED] if a cited source directly supports it, [INFERRED] if it is your reasoning from the sources, or [UNSUPPORTED] if neither. List every claim you marked UNSUPPORTED at the end. Do not rewrite the draft. DRAFT: [paste]
Assemble the brief
Combine the three passes into a fixed format: the narrowed question, findings grouped by sub-question, an explicit "what we still do not know" section, and a confidence rating with reasoning. The unknowns section is the most valuable part and the one a single-prompt approach never produces.
Test it on something you already know
Run the whole workflow on a topic you are genuinely expert in. This is the only reliable way to calibrate how much to trust it — you will spot the plausible-sounding errors that you would miss in an unfamiliar field.
You should end up with
A three-pass prompt workflow and one completed research brief.
Done when
- The brief separates sourced claims from inferences
- It includes an explicit list of unresolved questions
- Running it on a familiar topic surfaces no confident errors you would have missed
If you want to go further
- Add a fourth pass that argues the opposite conclusion and see what survives
- Turn the output format into a document template you reuse
Useful alongside this
Try next
Topics
Related across the site
n8n and AI: Build Your First Real Automation
A practical walkthrough of wiring an AI model into an n8n workflow — the node structure, the prompt that makes it reliable, and three automations worth building first.
Project: Research → Position → Launch Assets
Deliverable: a complete mini campaign kit for a real or invented product. Steps: 1.
AI agent
An AI agent is a system where a model plans and takes actions through tools in a loop, rather than producing a single response. It decides what to do next, does it, observes the result, and continues until the goal is met.
AI Marketing
Use AI for market research, copywriting frameworks, and audience segmentation — with prompts that produce genuinely usable marketing assets, not generic filler.
AI SEO & Search Visibility
Use AI to do keyword research, optimize content for search, and get your brand cited by AI answer engines like ChatGPT, Perplexity, and Google AI Overviews.
Competitor Content Gap Analysis
Paste a competitor's page structure (headings, topics covered) alongside yours and ask AI to find gaps — subtopics they cover that you don't, questions they answer, and angles they missed that you can own..