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

Device Complaint Trend Agent

Possible reportable events and trends found within days

MonitoringAnalysisRisk managementScience and research
See how it worksGet access
Device Complaint Trend Agent: what goes in, what the agent does and what you get

What it does

Device complaints must be assessed for trends and for events that may need reporting to regulators within strict timelines. Each day this agent reads new complaints and codes them by failure mode, device part and severity. It checks that each complaint has enough detail to assess, such as lot number, what happened and patient outcome. Incomplete ones go back to the complaint handler with specific questions, and the agent recodes them when answers arrive. Any complaint that mentions injury, death or a malfunction that could cause harm is flagged the same day for reportability review. It then compares failure rates with past periods and with the rates assumed in the risk file, and flags trends above thresholds. The engineer and regulatory staff make every reportability decision. Edge case: unclear wording that might describe a burn is flagged rather than coded as cosmetic.

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, continueApprovedNo 1 STARTS WHEN Daily complaint review 2 USES A TOOL Read new complaints 3 DOES Code failure mode, part and severity 4 CHECKS THE RESULT Is each complaint detailed enough to assess? If not: send specific questions to the complainthandler. Back to step 3. 5 DOES Flag harm-related complaints for reportabilityreview 6 USES A TOOL Compare failure rates with history and risk file 7 YOU APPROVE Engineer and regulatory decide reportability andactions 8 RESULT Daily trend report
Read the steps as a list
  1. Daily complaint review
  2. Read new complaints
  3. Code failure mode, part and severity
  4. Is each complaint detailed enough to assess?If not: send specific questions to the complaint handler. Back to step 3.
  5. Flag harm-related complaints for reportability review
  6. Compare failure rates with history and risk file
  7. Engineer and regulatory decide reportability and actionsThe agent waits here for your OK.
  8. Daily trend report

How it decides

It flags complaints with harm-related content immediately and flags failure modes whose rate is above the threshold or the risk file assumption.

  • Flag any mention of injury or harm the same day
  • Flag rates above the risk file assumption
  • Treat unclear harm descriptions as possible harm

Make it yours

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

  • Trend thresholds by failure mode
  • Harm keyword list
  • Report time
  • Comparison periods

What keeps you in control

It always asks you first

  • Reportability decisions
  • Opening a corrective action

Hard limits

  • Never decides reportability
  • Never contacts patients or users

It stops when

  • Done: daily report filed
  • Stop: complaint system unavailable; alert the team

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 happensOn the morning of June 3, 27 new complaints arrived. The detail check failed on four with no lot number, so the agent sent questions to the handler and recoded them after replies. One complaint mentioned skin redness and was flagged at once. Battery complaints had risen from 0.2% to 0.5% of units over two months, above the 0.3% in the risk file. Regulatory reviewed both that day.

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
Risk management · Quality control

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.

11 steps2 checks2 jobs