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 product managers

Usability Test Coordination Agent

Completed test sessions with a findings summary ranked by severity

Usability Test Coordination Agent: what goes in, what the agent does and what you get

What it does

Usability testing slips because recruiting, scheduling and note synthesis take too long. This agent takes the test plan, screens a pool of users against the criteria, drafts invitations and books sessions in open calendar slots. After sessions, it reads notes or transcripts and lists issues per task with how many participants hit each. It checks that enough participants matched the target profile, and recruits more if not. A participant who works for a customer partner is excluded from results. It rates issues by severity and drafts findings. The product manager approves invitations, incentives and the findings.

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
ApprovedYes, continueNo 1 STARTS WHEN Test plan approved 2 USES A TOOL Screen user pool against criteria 3 YOU APPROVE Product manager approves invitations and incentives 4 USES A TOOL Send invites and book sessions 5 CHECKS THE RESULT Do completed sessions meet the target profile count? If not: screen and invite more participants. Back tostep 2. 6 DOES List issues per task with counts and severity 7 USES A TOOL Draft findings summary 8 RESULT Findings shared with the team
Read the steps as a list
  1. Test plan approved
  2. Screen user pool against criteria
  3. Product manager approves invitations and incentivesThe agent waits here for your OK.
  4. Send invites and book sessions
  5. Do completed sessions meet the target profile count?If not: screen and invite more participants. Back to step 2.
  6. List issues per task with counts and severity
  7. Draft findings summary
  8. Findings shared with the team

How it decides

It ranks issues by how many participants hit them and how badly they blocked the task.

  • Five matching participants per segment minimum
  • Severity based on task failure, not opinion
  • Excluded participants noted with reason

Make it yours

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

  • Screening criteria
  • Participants per segment
  • Incentive rules
  • Summary format

What keeps you in control

It always asks you first

  • Sending invites
  • Paying incentives

Hard limits

  • Recordings stored only where consented
  • No personal data in the summary

It stops when

  • Done: findings shared
  • Stop: no matching participants after two recruiting rounds

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 happensEight sessions were booked, but three no-shows and one profile mismatch left four valid. The count check failed against a minimum of six, so the agent invited six more people and booked two. Four of six participants failed to find the export button, rated high severity. The product manager approved the findings and a redesign ticket.

More agents for product managers