Research

Research Brief Prompt

Objective, Background, Findings, Recommendations, Open Questions — briefs where what was found and what to do stay clearly separated.

Open in Markdown Output Builder

Overview

Research briefs lose credibility in one move: recommendations that smuggle past the findings. This setup generates briefs in five pinned sections with the type rule stated outright — separate what was found from what is recommended; different sections, different claims — plus evidence discipline: state the confidence or evidence behind each finding. Open Questions is pinned so unknowns get documented instead of papered over, and optional tables handle the comparison grids research briefs lean on.

How to use this resource

One brief shape per program

Every study reports in the same five sections — stakeholders learn to navigate them once.
Audit the findings-recommendation seam

Each recommendation should trace to a finding above it; the structure makes orphans visible.
Respect Open Questions

A pinned unknowns section is what separates research from advocacy.

Why This Works

Structural separation enforces the found-vs-recommended distinction reviewers check first
Per-finding evidence statements calibrate stakeholder trust
Pinned Open Questions makes intellectual honesty a formatting requirement

Best for

UX and market research teams briefing stakeholders
Briefs that feed decisions and get challenged
Research ops standardizing deliverables

Not for

Summarizing a published paper — that's the Structured Summary Prompt's research-paper setup
Building the research workflow itself — that's the Multi-Step Prompt Builder

Use cases

Writing research briefs in the same shape per study
Keeping recommendations tied to documented findings
Documenting unknowns instead of hiding them

FAQ

How does this prompt stop recommendations from creeping into the Findings section?

It writes a type rule directly into the DOCUMENT block — 'separate what was found from what is recommended; different sections, different claims' — and pins Findings and Recommendations as distinct '## ' headings. Findings carries what was found with evidence; Recommendations carries what to do, grounded in those findings. The generated prompt draws the seam; confirming each recommendation traces to a finding is on you.

Why does the Findings section ask for confidence or evidence on every point?

The DOCUMENT block adds an explicit rule — 'state the confidence or evidence behind each finding' — so each item in Findings carries its basis rather than a bare assertion, calibrating how much weight a stakeholder gives each point. The Markdown Output Builder bakes this instruction into the prompt; the assistant you run it in supplies the evidence wording, and you confirm it actually holds.

Can I add a comparison table inside a section, given the no-code-blocks rule?

Yes — the TABLE RULES permit a markdown table when content is naturally tabular, like option matrices or parameter lists, each with a header row and a separator row. But CODE RULES bar code blocks outright, and the CONSISTENCY rule says put extra material inside the closest existing section, so a comparison grid lives within Findings or Background, not as its own heading.

Customize This Resource

Opens this setup in Markdown Output Builder. Generate to get the full markdown prompt — then adjust the sections, table rules, and consistency level.

Open in Markdown Output Builder

Prompt Template

Copy it as-is, or use Open in Markdown Output Builder to load it pre-filled and customize it with your own context.

TASK
Write research briefs that keep findings and recommendations clearly separated.
Produce a new markdown document — there is no source text to summarize.

DOCUMENT
The document is a research brief.
- Separate what was found from what is recommended — different sections, different claims.
- State the confidence or evidence behind each finding.

DOCUMENT STRUCTURE
Start with one "# " title line, then use exactly these sections, in this order:
## Objective
The question this research answers.
## Background
Context the reader needs.
## Findings
What was found, with evidence.
## Recommendations
What to do, grounded in the findings.
## Open Questions
What remains unknown.

MARKDOWN RULES
- One "# " title at the top; every section below it is a "## " heading.
- Use markdown lists for enumerations — no walls of prose.
- No HTML tags — pure markdown.

TABLE RULES
- Use a markdown table when content is naturally tabular — comparisons, option matrices, parameter lists; otherwise prefer prose.
- Every table needs a header row and a separator row.

CODE RULES
- Do not include code blocks.

CONSISTENCY RULES
- Use every section defined above, in the order given.
- Do not add new top-level sections — put extra material inside the closest existing section.

OUTPUT RULES
- Return only the markdown document — no preamble, no closing commentary.
- Start directly with the "# " title line.
- Do not wrap the document in code fences.

More resources from Markdown Output Builder

Resource

Markdown Output Prompt — Lock the Document Structure

The contract that stops AI documents from restructuring themselves: a pinned section skeleton, forced tables, and strict consistency rules.

Prompt Engineering

Resource

README Prompt Template

Overview, Installation, Usage, Examples, Configuration — the README skeleton with required, runnable code examples.

Engineering

Resource

API Documentation Prompt

Overview, Authentication, Endpoints, Error Handling, Rate Limits — endpoint docs in an identical structure, with parameter tables and runnable examples forced.

Engineering

Resources that pair well

Resource

Executive Summary Prompt

Summary, Why It Matters, What Happens Next — the executive summary contract for readers who will never open the source.

Operations

Resource

Force JSON Output from AI

Stop getting 'Sure, here is the JSON…' — the output-contract pattern that forces models to return only parseable JSON: schema, example, and a strict rule block.

Prompt Engineering

Resource

Fix Invalid JSON from AI

The JSON won't parse and you can't see why. Deterministic cause-sniffing — trailing commas, single quotes, unclosed brackets — and the repair prompt that fixes it.

Engineering

Related tools

Tool

Markdown Output Builder

Build prompts that produce documents in a fixed structure — headings, sections, and tables.

Structured Output

Guides for this resource

Guide

How to Make AI Separate Facts, Assumptions, and Recommendations

Ask AI to analyze something and it hands back one smooth paragraph where you can't tell what you told it from what it assumed from what it's recommending. Here's how to make it split the answer into visible layers — facts, assumptions, inferences, recommendations, and what still needs checking.

Prompt Engineering

Tip: Save time by exploring related resources and tools that integrate with this resource.