HomeCasa Usability test plan and moderator script for a prototype
Prepare a complete usability test: research questions, participant screener, neutral tasks with success criteria, a moderator script, a note-taking template and an analysis plan. Designed for ChatGPT, Claude, Gemini and Microsoft Copilot. It includes 6 customizable variables and you can copy it for free in one click.
Intermediate · Text · Pending editorial review
Prompt
Act as a senior UX researcher with experience running moderated and unmoderated usability tests.
Context:
- Product: {{product}}
- What we are testing (prototype and fidelity): {{prototype}}
- Research goals: {{goals}}
- Participant profile: {{participants}}
- Format: {{format}}
- Session length: {{duration}}
Deliverables:
1. 3-5 research questions and the hypotheses we want to confirm or reject.
2. Recruitment criteria and a 5-8 question screener, marking which answers disqualify a participant. Suggest how many participants per profile and why.
3. 5-7 tasks based on realistic scenarios, without using interface labels or leading words. For each: scenario, success criterion, metrics (completion, time, errors, perceived difficulty on a 7-point scale) and neutral follow-up questions.
4. A full moderator script with timings: welcome, consent, think-aloud explanation, warm-up questions, tasks, wrap-up and a final questionnaire (e.g., SUS, optional).
5. A note-taking template for observers.
6. Analysis plan: how to cluster findings, a severity scale and the report format.
7. Logistics checklist: pilot session, tools, recording and handling of personal data in line with applicable privacy law.
Constraints:
- Word everything neutrally; no questions that suggest the answer.
- Do not invent results or user data; use [FILL IN] where information is missing.
- If the goals are too broad for the session length, tell me and suggest what to prioritize. If key information is missing, ask first.
Format: a document with numbered headings, tables for tasks and the screener, and the script in timed blocks.How to use it
- Describe which part of the prototype you want to validate and for whom. 2. Check that no task uses words from the interface. 3. Run a pilot session with a colleague and adjust timings before the real sessions.
Usage example
Product: tennis court booking app · Prototype: booking and payment flow in Figma · Format: remote moderated · 45 minutes.
Sample output
1. Research questions
- Can players find an open slot on their chosen date without help?
- Do they understand the total price before paying?
- Do they complete payment without hesitating at any step?
Hypothesis: the date and time picker is the biggest point of friction.
3. Tasks
| # | Scenario | Success criterion | Metrics |
|---|---|---|---|
| T1 | "You want to play this Saturday afternoon with a friend. Find a court you can use." | Reaches an open Saturday slot | Completion, time, errors, difficulty 1-7 |
| T2 | "Before deciding, you want to know how much you'll pay in total." | States the total out loud | Completion, difficulty 1-7 |
| T3 | "Book that court and pay." | Reaches the confirmation | Completion, time, errors |
Neutral follow-ups: "What did you expect to happen?" · "How would you describe that in your own words?"
4. Moderator script (45 min)
- 0-5 min · Welcome and consent: "Thanks for joining. We're testing the design, not you; there are no wrong answers. Is it OK if we record your screen and audio?"
- 5-8 min · Think-aloud: "As you work on each task, tell me what you're thinking and looking for."
- 8-12 min · Warm-up: "How do you usually book a court today?"
- 12-37 min · Tasks T1-T5
- 37-45 min · Wrap-up and optional SUS questionnaire…
Key facts
- Category
- UI/UX design · Prototypes
- Output type
- Text
- Level
- Intermediate
- Designed for
- ChatGPT, Claude, Gemini and Microsoft Copilot
- Verified in
- Pending editorial verification
- Variables
- Product, Prototype and fidelity, Research goals, Participant profile, Format and Session length
- Language
- English
- Price
- Free, no sign-up
- Updated
- Nov 7, 2026
Frequently asked questions
How many participants do I need for a usability test?
For a qualitative test, about five participants per profile usually surface the most common problems. If your profiles are very different, test each group separately.
Why should tasks avoid interface wording?
Because participants would just scan for the matching word instead of thinking as they would in real life, so the test would stop measuring whether the interface is understood.
Does it work for unmoderated tests?
Yes. If you choose the unmoderated format, the prompt makes the instructions self-explanatory and replaces live follow-ups with written questions.
What is this prompt for?
Prepare a complete usability test: research questions, participant screener, neutral tasks with success criteria, a moderator script, a note-taking template and an analysis plan.
Which AI tools does it work with?
It is designed for ChatGPT, Claude, Gemini and Microsoft Copilot. We have not verified it in these tools yet, so results may vary between them.
How do I customize the prompt?
Click “Customize” and fill in the variables (Product, Prototype and fidelity, Research goals, Participant profile, Format and Session length). The text updates instantly and you can then copy it in one click. Values are stored only in your browser.
Do I need experience to use it?
It is intermediate: it helps to know the topic so you can provide good context and review the result critically.
Is this prompt free?
Yes. Every HomeCasa Prompts prompt is free, with no sign-up or subscription. You can also use them in professional projects.
Can I trust the AI output?
Treat it as a high-quality draft: always check data, figures and important claims before publishing or making decisions.