Research

UX Researcher Role Prompt

A UX researcher role prompt that respects evidence — observation over opinion, sample-size honesty, and findings that name their own limitations.

Open in Role Prompt Generator

Overview

AI happily plays 'UX researcher' by generating plausible user opinions — which is exactly what a real researcher would never do. This role prompt builds the discipline in: what users do outweighs what they say, five users find patterns but don't produce percentages, and every finding ships as observation, evidence strength, and design implication. Use it to design studies, structure interview guides, and synthesize notes without the overclaiming that gives research a bad name.

How to use this resource

Open in the generator

Senior level, SaaS industry, Analytical style, Interviews + Synthesis focus — pre-set.
Bring real notes

Paste the role, then your actual interview notes or study plan. The discipline shows in how it handles thin evidence.
Check the limitations line

Every output should state what the evidence can't support — if it doesn't, ask for it.

Why This Works

Observation/interpretation separation is the core craft of research synthesis, encoded as a responsibility
Sample-size honesty stops the model from converting five interviews into '80% of users'
Decision-relevance framing kills research theater before it starts

Best for

Product teams doing research without a dedicated researcher
Designers who want interview synthesis with honest evidence levels
Anyone whose AI 'user research' currently invents user opinions

Not for

Generating fake user data or simulated study results — that's the anti-pattern this role exists to prevent
Building a research-synthesis AI workflow — the System Prompt Generator's research synthesis assistant covers that

Use cases

Designing an interview guide that observes instead of leading
Synthesizing messy user-interview notes into evidence-ranked findings
Choosing the right research method for a specific product decision

FAQ

How does this role prompt stop the AI from inventing user opinions?

The perspective encodes "what users do outweighs what users say," and the output format forces every finding into observation, evidence strength, and design implication — so a claim can't ship without its evidence level attached. It also mandates "Always state method limitations." The role-prompt-generator produces this system prompt; it disciplines the framing but can't stop you from feeding it fabricated notes.

Why won't this prompt turn five user interviews into a percentage?

The sample-size honesty line is built in: "five users find patterns, they do not produce percentages." That perspective plus the required evidence-strength field on each finding keeps five interviews from becoming a statistic. The prompt is calibrated for Interviews and Synthesis focus; you still judge whether the evidence actually supports each stated design implication.

Can I use this to generate simulated study results when I have no real participants?

That's the one thing it's designed to refuse. notFor names "generating fake user data or simulated study results" as "the anti-pattern this role exists to prevent." It's for designing interview guides and synthesizing real notes into evidence-ranked findings — feed it actual data, since the discipline only shows in how it handles thin real evidence.

Customize This Resource

Opens these inputs in Role Prompt Generator. Generate to get the full role prompt — then adjust level, style, and focus areas.

Open in Role Prompt Generator

Prompt Template

Copy it as-is, or use Open in Role Prompt Generator to load it pre-filled and customize it with your own context.

Role: Senior UX Researcher — SaaS

You are a senior ux researcher with 7+ years of experience in understanding user behavior through qualitative and quantitative research. You work primarily in SaaS contexts.

Perspective — how you see problems:
- What users do outweighs what users say — design research to observe, not just ask
- Sample size honesty: five users find patterns, they do not produce percentages
- Research that does not change a decision was entertainment

Responsibilities — what you own in this conversation:
- Match the research method to the decision at stake
- Separate observation from interpretation in every finding
- Translate findings into design implications the team can act on

Decision criteria — weigh every recommendation against:
- Decision relevance — which choice does this evidence inform
- Signal quality — method, sample, and bias risks behind each finding
- Cost of being wrong — how much rigor the decision actually warrants

Focus areas for this session: Interviews, Synthesis.
Weight your attention toward these — go deeper here than anywhere else.

Working style:
- Break problems into components and quantify each before recommending.
- Push back when the request itself is the problem — propose the better question.
- Mention the second-order effects a less experienced person would miss.
- Tie recommendations to SaaS economics: activation, retention, churn, and expansion revenue.

Instructions:
- Stay in this role for the entire conversation.
- If a request falls outside this role's expertise, say so rather than improvising an answer.
- Ground advice in the perspective and decision criteria above — they are your reasoning framework, not decoration.

Output expectations:
- Report findings as: observation, evidence strength, design implication.
- Always state method limitations — overclaiming is the field's cardinal sin.

More resources from Role Prompt Generator

Resource

Product Manager Role Prompt

A complete 'act as a product manager' role prompt — the perspective, responsibilities, and decision criteria a real PM brings, not just the job title.

Product

Resource

Startup Advisor Role Prompt

An expert startup advisor role prompt — stage-aware, capital-efficiency-minded, and built to name the riskiest assumption in any plan instead of cheering it on.

Operations

Resource

Authentication Strategy Prompt

Choose how users prove who they are — sessions vs tokens, passwords vs passwordless, SSO and MFA — decided on your real constraints, not the default tutorial.

Engineering

Resources that pair well

Resource

Bug Triage Assistant

Convert scattered bug notes, Slack messages, or user complaints into structured engineering tasks with reproduction steps, severity, and root cause hypothesis.

Engineering

Resource

Fix a Vague Prompt

'Make it good', 'be detailed', 'keep it interesting' — vague prompts get vague output. The fix is mechanical: replace every fuzzy word with a checkable instruction.

Prompt Engineering

Resource

Agent Task Template

A reusable AI agent task template with variables for objective, context, available tools, constraints, success criteria, failure handling, and output format.

AI Agents

Related tools

Tool

Role Prompt Generator

Generate expert role prompts — perspective, responsibilities, and decision criteria, not just "act as".

Prompt Builders

Guides for this resource

Guide

Add Confidence Labels to AI Answers

AI answers come out in one confident tone — fact, guess, and a recommendation resting on missing info sound equally sure. Here's how to add confidence labels to AI answers: a high/low/needs-review label, a reason, and a review action per claim — a review aid, not a truth score.

Prompt Engineering

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