Complete AI Training
Sign inGet my AI kit

Your job's AI kit

Get your AI kit

Tell us who you are and what you do. We show you your kit right away and email you the link: skills, prompts, AI agents, MCP servers and courses for your job.

500+ jobs ready, and we make a kit for any other job. No payment needed to look.

Share

AI agent for ux researchers

Accessibility Test Session Prep Agent

Make sure the prototype works with each participant's tools before the session.

Quality controlProduct development
See how it worksGet access
Accessibility Test Session Prep Agent: what goes in, what the agent does and what you get

What it does

Sessions with assistive technology users often hit surprises, like a prototype that a screen reader cannot read. This agent collects each participant's tools and needs, such as the screen reader, browser, zoom level or switch device. It then checks the prototype against those tools, using automated checks and a manual review list. It lists blockers and drafts adjustments, such as adding alt text or reordering focus. It retests after each fix. It also drafts a session guide that fits the participant's pace and tools. You approve all messages to participants. Edge case: a participant uses a screen reader that your prototype tool does not support, and the agent proposes an exported version.

How it works

Follow the arrows from top to bottom. The orange dashed arrow is the loop: when a check fails, the agent goes back and tries again.

Start and resultWhat it doesA check on its own workWaits for your OKGoes back and retries
Yes, continueYes, continueApprovedNoNo 1 STARTS WHEN Accessibility sessions are scheduled 2 USES A TOOL Collect each participant's tools and needs 3 USES A TOOL Run automated accessibility checks on the prototype 4 DOES Review the checklist for each tool combination 5 CHECKS THE RESULT Does the prototype work for each participant'stools? If not: List the blockers by participant and task. Backto step 4. 6 DOES Draft adjustments and workarounds 7 USES A TOOL Retest the prototype for each tool 8 CHECKS THE RESULT Are the task blockers cleared? If not: Return the remaining blockers to the designerwith details. Back to step 6. 9 USES A TOOL Draft the session guide and participant messages 10 YOU APPROVE Researcher approves participant messages 11 RESULT Prepared session package
Read the steps as a list
  1. Accessibility sessions are scheduled
  2. Collect each participant's tools and needs
  3. Run automated accessibility checks on the prototype
  4. Review the checklist for each tool combination
  5. Does the prototype work for each participant's tools?If not: List the blockers by participant and task. Back to step 4.
  6. Draft adjustments and workarounds
  7. Retest the prototype for each tool
  8. Are the task blockers cleared?If not: Return the remaining blockers to the designer with details. Back to step 6.
  9. Draft the session guide and participant messages
  10. Researcher approves participant messagesThe agent waits here for your OK.
  11. Prepared session package

How it decides

It tests the prototype for each tool combination and marks blockers that stop the task. Task blockers are fixed before cosmetic issues.

  • Task-blocking issues are fixed first
  • Each tool combination is tested separately
  • Do not ask participants to work around a blocker
  • Session length is adjusted to the participant's needs

Make it yours

Every agent is a starting point. You choose these settings for your own situation.

  • Tools and browsers tested
  • Session length
  • Checklist version
  • Lead time (default 1 week)
  • Fallback if a blocker remains

What keeps you in control

It always asks you first

  • Messages to participants
  • Any prototype change request

Hard limits

  • Never shares health details
  • Never sends without approval
  • Never tests without consent

It stops when

  • Done: no task blockers remain
  • Stop: blocker cannot be fixed; propose an alternative task

Set it up

We guide you through the set-up, step by step

Members get the full set-up guide for this agent. No technical skills needed: you copy, paste and upload.

10 minto set it up in your AI
5 AIsChatGPT, Claude, Copilot, Gemini, Grok
  • One set of instructions to paste into your AI, with the clicks for ChatGPT, Claude, Microsoft 365 Copilot, Gemini and Grok
  • The agent then walks you through connecting your own data, one source at a time
  • A downloadable copy with the flow chart, the rules and the full guide
Get access to this agent

An example run

What happensThree participants used JAWS, VoiceOver and a zoom tool. Automated checks passed, but manual review showed the checkout dialog trapped focus for JAWS. The agent flagged it and the designer fixed it. The retest then found VoiceOver read the price twice, so the check failed. A second fix passed all three. The researcher approved the messages.

More agents for ux researchers

Compliance · Automation

Prototype Usability Session Agent

Consistent, consent-respecting usability session records.

9 steps2 checks3 jobs
Compliance · Product development

Product Research Consent Tracker Agent

Research artifacts used only within consent.

7 steps1 check1 job
Analysis · Decisions

User Test Prototype Iteration Agent

Turn test observations into ranked problems and verified changes for the next prototype.

11 steps2 checks8 jobs
Risk management · Quality control

Research Session Scheduling and Readiness Agent

Make every session ready, with consent, working prototype and recording, before it starts.

11 steps2 checks1 job