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 biomedical engineers

Usability Study Use Error Tracking Agent

Every observed use error, close call and difficulty is traced to a hazard and a mitigation before the report.

Risk managementQuality controlScience and researchProduct development
See how it worksGet access
Usability Study Use Error Tracking Agent: what goes in, what the agent does and what you get

What it does

A usability test produces hours of notes, and a use error buried in session 6 never reaches the risk file. This agent reads the session notes and classifies each use error by task, type and severity of possible harm. It links each to the matching hazard and hazardous situation in the risk file and checks that every error has a mitigation, such as a design change, a label or training. Missing links go back to you as a list with suggested matches. After you update the risk file, it rechecks. It then drafts the use error summary for the usability report. You approve the report. Edge case: a close call or difficulty is tracked even when no error occurred.

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, continueApprovedYes, continueApprovedNoNo 1 STARTS WHEN Session notes received 2 USES A TOOL Read notes and list use errors, close calls anddifficulties by task 3 DOES Classify each by type, cause and potential harm 4 USES A TOOL Match each to hazards and hazardous situations inthe risk file 5 CHECKS THE RESULT Does each event have a matching hazard? If not: propose a new hazard entry or a better match forthe engineer. Back to step 4. 6 YOU APPROVE Engineer approves new hazards and links 7 CHECKS THE RESULT Does each linked hazard have a mitigation withevidence? If not: list the gaps and suggest a mitigation type foreach. Back to step 4. 8 DOES Recheck the risk file after the engineer updates it 9 DOES Draft the use error summary table for the report 10 YOU APPROVE Engineer approves the usability report 11 RESULT Use error trace table
Read the steps as a list
  1. Session notes received
  2. Read notes and list use errors, close calls and difficulties by task
  3. Classify each by type, cause and potential harm
  4. Match each to hazards and hazardous situations in the risk file
  5. Does each event have a matching hazard?If not: propose a new hazard entry or a better match for the engineer. Back to step 4.
  6. Engineer approves new hazards and linksThe agent waits here for your OK.
  7. Does each linked hazard have a mitigation with evidence?If not: list the gaps and suggest a mitigation type for each. Back to step 4.
  8. Recheck the risk file after the engineer updates it
  9. Draft the use error summary table for the report
  10. Engineer approves the usability reportThe agent waits here for your OK.
  11. Use error trace table

How it decides

An event is complete when it has a classification, a linked hazard and at least one mitigation with verification evidence.

  • Error with possible serious harm: mark as critical and require a mitigation
  • Same error in 2 or more participants: flag as a pattern
  • Participant needed help from the moderator: count as a use error
  • Close call with no harm path: record as an observation, not a hazard

Make it yours

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

  • Event categories and severity scale
  • Task list
  • Pattern threshold in participants (default 2)
  • Report template
  • Risk file format

What keeps you in control

It always asks you first

  • New hazards added to the risk file
  • The final usability report

Hard limits

  • Never change the risk file itself
  • Never drop an event because it looks minor

It stops when

  • Done: all events traced and report approved
  • Stop: risk file not accessible

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 happensAcross 15 sessions, the agent logged 23 events. Nine were not linked to any hazard, so the check failed. It proposed matches for six and drafted new hazard entries for three, including a mix-up of two similar vial labels seen in 4 participants. The engineer approved them. After mitigation updates, all 23 events had a mitigation, and the report went forward.

More agents for biomedical engineers

Communication · Automation

Product Requirement Change Impact Agent

Every requirement change reaches all linked tests, docs and teams.

7 steps1 check3 jobs
Analysis · Decisions

User Test Prototype Iteration Agent

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

11 steps2 checks8 jobs
Project tracking · Administration

Lab Meeting Action Follow-up Agent

Make sure every action item from a meeting has an owner, a date and a recorded outcome.

10 steps2 checks7 jobs
Compliance · Decisions

Device Software Change Assessment Agent

A documented impact assessment and test plan for each software change, with no requirement left untested.

11 steps2 checks2 jobs