All 141 tools / Research and usability testing
Build a usability test plan from your goal, participants and tasks, and flag tasks that lead the user
Usability test planFreeFor researchers, product teams and designers
25/day
free runs a day, no sign-in.
Before: what you give it
The example input, as typed in. You give it structured JSON.
goal: Find out whether new customers can book a table without help.
participants: {"count":5,"profile":["Eats out at least twice a month","Has booked a restaurant online in the last 3 months"]}
tasks: ["Click the Reserve button and book a table",{"name":"Change a booking","scenario":"Your plans changed and you need to move Friday's dinner to Saturday.","success":"Confirmation shows the new date."}]
product: Larder booking flow
After: what comes back
The first lines of a real run on that input. Nothing here is edited by hand.
# Usability test plan: Larder booking flow ## Goal Find out whether new customers can book a table without help. ## Format Moderated sessions, about 45 minutes each, 5 participants. Tasks: 2. ## Screener - Screen on: Eats out at least twice a month. Ask for the behaviour behind it (what they did, how often, when last) with a multiple-choice question that lists the target answer among several plausible ones, so the right answer is not obvious. - Screen on: Has booked a restaurant online in the last 3 months. Ask for the behaviour behind it (what they did, how often, when last) with a multiple-choice question that lists the target answer among several plausible ones, so the right answer is not obvious. - Exclude people who work in design, UX research or marketing, or for the company or a direct competitor (convention). - Exclude anyone who took part in a study with you in the last 6 months (convention, to limit practised participants). - Confirm the device, browser and connection needed for the session, and that they can share a screen and talk aloud if the session is remote. ... full output on the tool page
What you get
Screener, session outline, task scenarios with success and stop rules, metrics, and a note-taking sheet
What it cannot do
Fixed template logic with no model call; the leading-wording check is a keyword heuristic.
Who it is for
- Researchers
- Product teams
- Designers
Free and Pro
| Free | 25 runs a day per IP address, up to 20,000 characters a run. |
|---|---|
| Pro | No daily limit, 300 requests a minute, up to 200,000 characters a run. |
Use it from your assistant
The tool is called plan_usability_test. Connect the server once, then ask for it by name or just describe the job. Install steps for each app.
claude mcp add --transport http designers https://designers.allthepossibles.com/mcp
curl -X POST https://designers.allthepossibles.com/api/usability-test-plan -H 'content-type: application/json' -d '{"goal":"Find out whether new customers can book a table without help.","participants":{"count":5,"profile":["Eats out at least twice a month","Has booked a restaurant online in the last 3 months"]},"tasks":["Click the Reserve button and book a table",{"name":"Change a booking","scenario":"Your plans changed and you need to move Friday'\''s dinner to Saturday.","success":"Confirmation shows the new date."}],"product":"Larder booking flow"}'
Try it here
The form starts with the same example input, so you can run it first and then swap in your own.
More in research and usability testing
- Usability numbers
Score SUS results and work out sample sizes for usability tests, A/B tests and surveys.
- Heuristic review
Get a Nielsen heuristic worksheet for a screen or flow, with signals showing where to look first.
- Critique plan
Plan a design critique for the stage the work is in, with timed rounds, roles and feedback to hold back.
- Research questions
Find leading, double-barrelled and hypothetical questions in an interview or survey script and rewrite them.
- Trunk test
Check whether a page answers Krug's six trunk-test questions: site, page, sections, options, location, search
- Form check
Check a form's markup against Wroblewski's Web Form Design rules and get a fix for each finding