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 nurse practitioners

Abnormal Result Follow-up Agent

Every abnormal result ends with a documented plan, patient contact and completed next step

Risk managementMonitoringHealthcare
See how it worksGet access
Abnormal Result Follow-up Agent: what goes in, what the agent does and what you get

What it does

Results land in the inbox all day, and an abnormal one can be missed or acknowledged without action. This agent watches incoming results and classifies each as critical, abnormal or normal. Critical values are never left in a queue; they go to the on-call clinician right away. For abnormal results, it checks whether the clinician has reviewed them and placed a follow-up plan within 3 business days. If not, it sends a reminder and checks again the next day. It drafts a plain-language patient message for the clinician to approve. It then tracks that the patient was contacted and that any repeat test or referral was booked. Three failed contact attempts trigger a letter. Edge case: a critical value posted overnight pages the on-call clinician, not the ordering clinician's inbox.

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, continueNoNo 1 STARTS WHEN Result posts to the chart 2 DOES Classify as critical, abnormal or normal 3 USES A TOOL Check clinician review and plan in the chart 4 CHECKS THE RESULT Is there a plan within the deadline? If not: remind the clinician and recheck the next day.Back to step 3. 5 DOES Draft a plain-language patient message 6 YOU APPROVE Clinician approves the patient message 7 USES A TOOL Track contact and booking of repeat test or referral 8 CHECKS THE RESULT Was the patient reached and the follow-up booked? If not: remind the responsible person, send a letterafter three attempts. Back to step 7. 9 RESULT Result closed with full follow-up trail
Read the steps as a list
  1. Result posts to the chart
  2. Classify as critical, abnormal or normal
  3. Check clinician review and plan in the chart
  4. Is there a plan within the deadline?If not: remind the clinician and recheck the next day. Back to step 3.
  5. Draft a plain-language patient message
  6. Clinician approves the patient messageThe agent waits here for your OK.
  7. Track contact and booking of repeat test or referral
  8. Was the patient reached and the follow-up booked?If not: remind the responsible person, send a letter after three attempts. Back to step 7.
  9. Result closed with full follow-up trail

How it decides

Results are sorted into critical, abnormal and normal. Abnormal results are tracked through review, patient contact and next step, each with a deadline.

  • Critical values page the on-call clinician right away
  • Abnormal results need a plan within 3 business days
  • Three failed contact attempts trigger a letter

Make it yours

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

  • Days allowed per step
  • Which result types are tracked
  • Contact attempts before a letter
  • Who gets reminders

What keeps you in control

It always asks you first

  • Patient messages about results
  • Any change to the follow-up plan

Hard limits

  • The agent never interprets results for patients
  • Critical values are never batched

It stops when

  • Done: next step completed
  • Stop: patient declines follow-up, document and notify clinician

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 a Tuesday, a potassium of 5.9 was flagged critical and sent to the on-call physician within minutes. A mildly high A1c of 7.4 sat unreviewed for 4 days, so the plan check failed and the agent reminded the nurse practitioner. She added a plan and approved the patient message. The contact check then showed two missed calls; the medical assistant reached the patient and booked a recheck.

More agents for nurse practitioners

Communication · Healthcare

Appointment Preparation Coordination Agent

Every patient receives the correct, current preparation instructions.

7 steps1 check6 jobs
Compliance · Quality control

Documentation Audit Agent for Medical Necessity

Notes show medical necessity and the pass rate rises month by month.

11 steps2 checks11 jobs
Risk management · Healthcare

Supplement and Medication Interaction Screening Agent

Every client's combinations are checked and any risk is passed to a prescriber before the client continues.

10 steps1 check5 jobs
Monitoring · Risk management

Risk Flag Escalation Agent

Warning signs are caught early, escalated to the professional and followed to a response.

11 steps2 checks12 jobs