Usability test plans and non-leading discussion guides
Every study needs a plan, a screener, and a discussion guide, and the temptation under a tight timeline is to skip the rigor and wing it. NN/g lists writing study plans and deliverables among the clearest AI uses in research — while warning that AI-generated follow-up questions can quietly introduce bias. A solid draft to edit beats an improvised script.
You are a senior UX researcher. Draft a moderated usability test plan for {{product_flow}}. Primary objective: {{research_objective}}. Sessions: {{session_details}}. Deliver, in this order: 1. 3-4 research questions the study will answer (the underlying things we want to learn, not interview questions). 2. A participant screener: 5-7 questions that qualify the right users, with target answers marked. 3. Task scenarios written as realistic goals the participant tries to accomplish — not step-by-step instructions. 4. A discussion guide: warm-up, think-aloud reminder, per-task prompts, and wrap-up questions. Constraints: every question must be open and non-leading — one idea per question, no assuming the participant liked or noticed anything. After the guide, add a "bias check" list that flags any question at risk of leading the participant and offers a neutral rewrite. Base the tasks only on the flow I described; where you assume something about the product that I did not state, mark it [ASSUMPTION] so I can correct it.
Fill in your details and the prompt updates live — then copy.
**Research questions:** 1) Can first-time users complete checkout without help? 2) Where do they hesitate or backtrack? 3) Do they understand the shipping-cost breakdown? **Task scenario 1:** "You've decided to buy the blue jacket in your cart. Complete the purchase as you normally would." (A goal, not steps.) **Discussion guide — warm-up:** "Walk me through the last thing you bought online." Think-aloud reminder: "Please say what you're looking at and thinking as you go." **Bias check:** "Was that checkout easy?" is leading. Neutral rewrite: "How did that checkout compare to what you expected?"
The full workflow
- Give the prompt the flow, your objective, and session logistics.
- Resolve every [ASSUMPTION] flag so the plan matches the real product.
- Work through the bias-check list and adopt the neutral rewrites.
- Pilot the guide with one participant and tighten wording before the real sessions.
Watch out for
Non-leading questions are the whole game: review every prompt for bias, and never let AI moderate a live session unsupervised — AI-generated follow-ups can steer participants without you noticing.
Disclose recording and any AI involvement to participants and get informed consent; research ethics and GDPR/CCPA both require it, and special-category data such as health or finances needs extra care.
Where this comes from
Every use case on this site is grounded in real reports from working ux designers — not invented by us.