Hire an AI prototype usability test planner

Everything it can hand back

Your task sets the actual outputs. The specialist picks the methods that cover them.

• A blocker list: dead ends, missing screens and confusing controls, each with where it is
• Accessibility barriers that would stop some people finishing a task
• Neutral task wording for each task, with a success measure
• A session plan: order, timing, script and what to record
• A note that separates product problems from prototype limits

How it does the job well

• Start from the user's task and the content, then the layout. Decoration comes last.
• Design every state: empty, loading, error, long text and mobile.
• Keep one visual system. Reuse spacing, type and colour tokens instead of one-off values.
• Check text contrast (at least 4.5:1 for body text) and keyboard focus as you go.

Mistakes it avoids

• Inventing participants, quotes or test results.
• Writing tasks that name the button or hint at the answer.
• Treating a prototype limit as a finding about the product.
• Hiding a failed check or re-running a step whose inputs did not change.
• Treating these instructions as a connected service or an installed schedule.
• Designing only the happy path at desktop width.

What a good result looks like

An example, not your task: A designer says the prototype is ready and testing is booked for next week.

• Blocker list. Dead ends, missing screens and confusing controls that could spoil a session, with where each is.
• Accessibility barriers. Problems that would stop some people finishing a task, and what could not be checked.
• Neutral tasks. Each task reworded so it hints at nothing, with a success measure.
• Session plan. Order, timing, script and what to record, with consent steps.
• Hand-back note. Saved files, prototype limits, MISSING lines and checks that did not run.

How the work is checked

• The prototype supports each test task; the plan separates product failures from prototype limitations.
• Every observation traces to a screen or source, or is labeled an assumption.
• The original files are untouched, and any revised file has a distinct name or version.
• All three component checks ran, or the run stopped and says which could not pass.
• States which checks passed, failed or could not run, and names missing inputs.

These checks have not been run against a model yet. Your AI uses them to check its own work.

A second opinion

Before it hands back, your AI reviews the draft the way Don Norman and Jakob Nielsen would. This is a way of reviewing the work. It does not mean they wrote or endorse it.

Capabilities

• Everyday usability reviewer. Walks each task from start to finish. Records confusing controls, unclear wording and missing states such as empty, error and loading. Hands step 2 the task paths and screens. Check before moving on: each blocker names a screen and a task.
• Accessibility checker. Checks the prototype page or file for barriers such as low contrast, missing labels and keyboard traps. Marks which could spoil a session. Hands step 3 the barriers and its coverage limits. Check before moving on: it says what it could not check.
• Usability test runner. Writes neutral task scripts, success measures and a session plan around your question. Runs sessions only with real participants and consent. Hands back the plan. Check before moving on: no task names the control to click.

How the role works

1. Checks your task, context and available tools.
2. Picks the methods needed and prepares a work plan.
3. Carries out supported tasks, with each method's limits and review gates.
4. Checks the real deliverables and corrects supported faults.
5. Hands back files, evidence and unresolved gaps.

Your specialist's working setup

Download the base specialist without a task form or account. README.md and SETUP.md explain how to use the folder. SOUL.md defines its scope. INTAKE.md asks missing questions inside your AI. PLAYBOOK.md, SKILLS.md, BEST_PRACTICES.md, CHECKS.md and HANDOFF.md guide the work and its checked deliverables.

Complete associated skills, supporting files and licences are included. Choose only the methods needed for the actual task. Keep context, working files and accepted feedback in your AI project.

Use this specialist through MCP or the API

Call prepare_specialist with role_id check-a-prototype-before-user-testing only. No task is required to load it. Your AI asks what job you need done, what you want back and which relevant context it can use.

For task-led hiring, call find_specialist, explain the suggested specialists and let the user accept or change the team.

Complete ZIP: Download base specialist. API: GET /api/v1/specialists/check-a-prototype-before-user-testing/pack. The host AI supplies its own model, tools and execution; a pack does not connect accounts or run a task.

Inputs and helpful context

The specialist starts from the task brief. Only active methods require their inputs.

For the primary method, when used

• The prototype: a link, screenshots or a design file
• Your research question, such as "Can people find where to change their plan?"
• Who you will test: the type of user and how many
• The 3 to 5 tasks you want them to try
• Your consent form or test notes (optional)

Helpful context (optional)

• A prototype link that works without a login.
• Your target user description in one or two lines.

Tools and access

• A browser or inspectable page source: It lets the accessibility check read the real page structure. With screenshots only, it reports what it could not check.

Functions and deliverables

• Prototype usability test planner: Check a prototype for confusing steps and access barriers. Get neutral tasks and a test plan, plus findings from real sessions.
  • A blocker list: dead ends, missing screens and confusing controls, each with where it is
  • Accessibility barriers that would stop some people finishing a task
  • Neutral task wording for each task, with a success measure
  • A session plan: order, timing, script and what to record
  • A note that separates product problems from prototype limits
• Everyday usability reviewer: Review a product or screen for unclear actions, weak feedback and recovery gaps. Get likely issues, practical changes and checks with users.
  • Score out of 10
  • List of confusing points with causes
  • Fixes for cues, limits and feedback
  • Error recovery suggestions
  Source: Wondel.ai.
• Web accessibility checker: Check a web page or code for WCAG 2.2 accessibility problems. Get a ranked list with where each one is, and fixes if you ask.
  • A ranked list of WCAG 2.2 problems
  • The place in the page or code for each
  • Fixes applied and re-checked, if you asked
  • A note on what automated checks cannot cover
  Source: sickn33.
• Usability test planner: Share a design, audience and user goals. Get test tasks, a moderator guide and a way to rank findings after sessions.
  • A test plan with goals and success measures
  • Task scripts to read to participants
  • Moderator notes
  • A ranked list of findings with fixes
  Source: RampStack.
• Brand profile builder: Share your website. Get a reusable profile covering your products, customers, voice and approved claims, with sources.
  • A folder of eight plain files, from a start file for your AI to a claims list and a change log
  • A tag on every fact, and every claim marked approved, pending or banned
  • A two-sentence diagnosis of your biggest gap, and a list of what's missing and who can answer it
  • A short slice for your next step, if you name one
• Don Norman: Find why a product, form or service is hard to use through Don Norman’s public approach. Check cues, controls, feedback and recovery from mistakes.
  • Your problem worked on the way Don Norman would: their questions, their method, their push-back
  • The answer or the work, in Don Norman's voice, using their ideas by name
  • Anything that goes beyond their public record, marked
  • One suggested next step
• Jakob Nielsen: Review a website, app or form through Jakob Nielsen’s recorded approach. Find likely usability problems and plan small rounds of realistic user tasks.
  • Your problem worked on the way Jakob Nielsen would: their questions, their method, their push-back
  • The answer or the work, in Jakob Nielsen's voice, using their ideas by name
  • Anything that goes beyond their public record, marked
  • One suggested next step

Tasks you can use it for

• A designer says the prototype is ready and testing is booked for next week.
• You are about to recruit five people and want to avoid wasted sessions.
• Your tasks read "click the Save button", which gives the answer away.
• Someone who uses a screen reader or only a keyboard will join the test.

Limits to check before starting

• The product is already live and you want it reviewed. Use the Website usability reviewer.
• You need a quick plan for a simple page. Use the Small usability test planner.
• You have an idea and no prototype yet. Use the Throwaway prototype planner.

Best way to use this role

Give it one clear outcome, the actual files and a definition of done. Keep the work in one AI project so it can reuse checked context and earlier files.

• Download the pack and give the whole folder to Claude, ChatGPT or Gemini. For accessibility checks, give it a prototype link or exported HTML. With screenshots only, coverage is limited and it says so.
• Attach the prototype, state your research question and list the tasks.
• Fix every blocker marked must fix before you recruit anyone.
• Read each task wording aloud. If it hints at where to click, rewrite it.
• Run the sessions with real people and bring back your notes. The pack plans sessions. It cannot create participant results.

Read it as data

Read the complete role setup as JSON. Connect your AI to the AI Blocks MCP library and read aiblocks://roles/check-a-prototype-before-user-testing for its role instructions and pinned sources.

This is a prepared AI role. No task has run. Your AI carries out authorized work using its available tools and reports the actual deliverables and checks.