The UX Research & Design Protocol
134 copy-paste AI prompts for designers and researchers — interview scripts that do not lead, usability tests that find real failures, synthesis without cherry-picking, journey maps and design critique.
Key Capabilities & Features:
- •The Research Primer: paste your product, users, decision at stake and budget once — every prompt after it plans research that can actually change that decision
- •Interview questions about what people did rather than what they would do, since predicted behaviour is the least reliable data in research and the easiest to collect
- •A leading-question check, because the questions you cannot hear yourself asking are the ones that produce the answers you wanted
- •Synthesis that resists cherry-picking, including a prompt for reporting a finding that contradicts the roadmap
- •A first question in every study plan: what decision does this change, and what would we do differently if the answer went the other way
- •134 prompts across 8 sections — research planning, recruiting participants, interview scripts, usability testing and more
- •Works with ChatGPT (GPT-5), Claude Opus 5 and Gemini 3.7 Flash — fill the bracket, paste, done
One-time payment • Lifetime access & future updates
What's Inside
8 modules134 promptsEvery module below is included in the single purchase.
- 1
Research Planning
18 promptsDeciding what question the research is actually answering, choosing a method that can answer it, sample size at your budget, and the study that will not change any decision.
- 2
Recruiting Participants
16 promptsScreeners that exclude the professional participant, finding people who are not your existing power users, incentives, and the recruitment that quietly biases the whole study.
- 3
Interview Scripts
22 promptsQuestions about what people did rather than what they would do, avoiding the leading question you cannot hear yourself asking, and the silence that produces the real answer.
- 4
Usability Testing
20 promptsTasks phrased without giving away the interface, what to do when someone struggles, thinking-aloud protocols, and separating a discoverability problem from a comprehension one.
- 5
Synthesis & Findings
20 promptsGetting from raw sessions to findings without cherry-picking the quote that suits you, severity that reflects impact, and reporting a result that contradicts the roadmap.
- 6
Journeys & Service Maps
16 promptsMaps built from observed behaviour rather than from the happy path, the step that happens outside your product, and the handover where people are lost.
- 7
Design Critique
14 promptsCritique on the problem being solved rather than on taste, receiving feedback without defending, the stakeholder who redesigns in the review, and critique that ends in a decision.
- 8
Accessibility In Practice
8 promptsDesigning for assistive technology rather than retrofitting, colour and contrast decisions, the accessibility issue that is really a copy problem, and testing without a lab.
Test Workflow Execution in Your Browser
Verify actual prompt structure, token speed, and reasoning depth before downloading.
Frequently Bought Together
Technical Specifications
Architecture & System Overview
The most expensive research is the study that was beautifully run, thoroughly reported, and could never have changed anyone's mind — because the decision had already been made and the team wanted evidence.
The UX Research & Design Protocol is a 134-prompt playbook covering research planning, recruiting participants, interview scripts, usability testing, synthesis and findings, journeys and service maps, design critique, and accessibility in practice.
Start with the Research Primer — paste in your product, your users, the decision at stake and your budget — and every prompt after it plans research that can actually move that decision.
That framing is the first question in every study plan: what would we do differently if the answer came back the other way? A study with no answer that changes anything is not research, it is reassurance, and it costs the same.
The interview prompts ask about what people did rather than what they would do. Predicted behaviour is the cheapest data to collect and the least reliable — people are sincerely, confidently wrong about their own future actions — and the whole section is built around getting at past behaviour instead. There is also a check on your own script for the leading question you cannot hear, which is nearly always present in the first draft.
Synthesis is where research most often fails quietly. Fifteen hours of sessions offer enough material to support almost any conclusion, and the prompts work against that: coding before concluding, counting rather than remembering, and a specific prompt for the situation where the finding contradicts a roadmap someone has already committed to.
Scope note: PRDs, user stories, roadmap prioritisation and experiment design live in The Product Management Playbook. This one is about understanding behaviour and designing the interface.
Compare with Similar AI Templates
| Specification | ||||
|---|---|---|---|---|
| Customer Rating | 4.75(4) | 4.91(43) | 4.93(45) | 4.91(38) |
| AI Models | GPT-5, Claude Opus 5, Gemini 3.7 Flash | GPT-5, Claude Opus 5, Gemini 3.7 Flash | GPT-5, Claude Opus 5, Gemini 3.7 Flash | GPT-5, Claude Opus 5, Gemini 3.7 Flash |
| Formats Included | PDF Prompt Playbook | PDF Prompt Playbook | PDF Prompt Playbook | PDF Prompt Playbook |
| Lifetime Updates | Yes | Yes | Yes | Yes |
| Creator Rating | Aria Thorne (98.2%) | Dr. Lucas Vance (99.2%) | Marcus Sterling (99.3%) | Elena Rostova (99%) |
Prompt Architect & Author Spotlight
Works with Roblox creators on retention and monetisation design. More interested in why players leave in the first two minutes than in what brings them in.
Community Reviews & Ratings
Verified buyer ratings & prompt benchmarks
Write a Review
Sign in to leave a review for this system.
Verified User Feedback
It found the question where my bias lived
I told it what I privately suspected and it pointed at the one question guaranteed to produce that answer. I had read that script four times and never seen it.
What would we do differently if it went the other way
We could not answer that for a study we had already scheduled. Cancelled it and saved three weeks. That question now opens every research request we get.
Would you use this, versus when did you last try
Such a small change and the answers stopped being polite and started being useful. Half my old scripts were hypotheticals.
Research-heavy
The design critique and accessibility sections are the smallest. If you wanted visual design guidance this is mostly not that — it is research and behaviour.
Frequently Asked Questions
Do I need to be a trained researcher?
No. The Primer asks your experience level and the prompts adapt — a designer running their first five interviews gets more scaffolding, including the parts that are easy to get wrong without noticing. The leading-question check is useful at any level.
Will it analyse my session recordings?
It structures synthesis from notes and transcripts you provide, and pushes you to code before concluding rather than reaching for the memorable quote. It does not process recordings for you and the judgement about severity remains yours.
Does it overlap the Product Management toolkit?
Lightly, on research and surveys. That toolkit's research is about product decisions and prioritisation; this one is about understanding behaviour and designing interfaces. PRDs, user stories and roadmaps are deliberately not here.
Is the accessibility section enough for compliance?
No. It covers designing for assistive technology in practice and testing without a lab. Formal conformance assessment against a standard is audit work and sits in The Risk & Compliance Blueprint, and neither is legal advice.
How is it delivered?
You receive a PDF with all 134 prompts organized into 8 sections, delivered within 24 hours of purchase. No app or account required — copy a prompt, fill in the bracketed variables, and paste it into ChatGPT, Claude, or Gemini.
Can I use this for client work?
Yes. Your purchase includes a single-user commercial and personal license, so you can use every prompt in your own business or for client deliverables without restriction.