AI agent for nurse practitioners
Measurement-Based Care Agent
Use symptom scores to catch non-response and safety risk early
What it does
Measurement-based care means giving short questionnaires like the PHQ-9 or GAD-7 at regular points and acting on the trend. Two days before each session, this agent sends the right questionnaire. If it is not completed, it sends one reminder, then marks the score as missing. Missing scores are never treated as stable. It scores completed questionnaires and checks safety items first: any positive answer on the self-harm question alerts the clinician the same day. It then adds the score to the trend and compares it with baseline. Patients with less than 25% improvement after 8 weeks are flagged for a treatment review, with a list of what has been tried. The clinician reviews flagged patients and decides any change. Edge case: a patient who skips the questionnaire twice is noted as a gap, not as no change.
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.
Read the steps as a list
- Session is 2 days away
- Send the questionnaire
- Was the questionnaire completed?If not: send one reminder, then mark as missing. Back to step 2.
- Score responses and add to the trend
- Are all safety items negative?If not: alert the clinician the same day. Back to step 4.
- Compare response with baseline and flag low improvement
- Clinician reviews flagged patientsThe agent waits here for your OK.
- Score trend in the chart before session
How it decides
Scores are compared with baseline. Less than the set improvement after the review window triggers a flag; any positive safety item triggers an immediate alert.
- Any positive self-harm item alerts the clinician the same day
- Less than 25% improvement after 8 weeks flags for review
- Missing scores are never treated as stable
Make it yours
Every agent is a starting point. You choose these settings for your own situation.
- Questionnaires per diagnosis
- Review window and improvement target
- Reminder timing
- Alert channel
What keeps you in control
It always asks you first
- Any change to treatment
- Contacting a patient after a safety alert
Hard limits
- Safety alerts always reach a person
- The agent never contacts patients about scores on its own
It stops when
- Done: scores in chart before session
- Stop: patient declines questionnaires, document
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.
- 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
An example run
More agents for nurse practitioners
Communication · Healthcare
Appointment Preparation Coordination Agent
Every patient receives the correct, current preparation instructions.
Compliance · Quality control
Documentation Audit Agent for Medical Necessity
Notes show medical necessity and the pass rate rises month by month.
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.
Monitoring · Risk management
Risk Flag Escalation Agent
Warning signs are caught early, escalated to the professional and followed to a response.