Complete AI Training

AI agent for physiotherapists

Home Exercise Adherence Agent

Raise home program completion and catch problems before the next visit

Home Exercise Adherence Agent: what goes in, what the agent does and what you get

What it does

A home exercise program only works if the patient does it, and clinicians often learn too late that they did not. When a clinician assigns a program, this agent sends it to the patient with a reminder schedule. It collects simple daily check-ins on what they did and how it felt, including pain and difficulty ratings. It first screens each check-in for red-flag symptoms, such as new numbness or severe pain; those stop reminders, tell the patient to contact the clinic and alert the clinician as urgent. It then checks completion and pain against targets. When completion drops under 50% in a week or pain rises 3 points, it sends a gentle follow-up and alerts the clinician. Before each visit it summarizes adherence and ratings. The clinician approves any program change. Edge case: red-flag symptoms always override the normal reminder flow.

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, continueYes, continueApprovedNoNo 1 STARTS WHEN Clinician assigns a home program 2 USES A TOOL Send program and reminder schedule to the patient 3 USES A TOOL Collect daily check-ins 4 CHECKS THE RESULT Is the check-in free of red-flag symptoms? If not: stop reminders, tell the patient to call theclinic and alert the clinician. Back to step 3. 5 CHECKS THE RESULT Is completion above target and pain stable? If not: send a follow-up or alert the clinician if painrises. Back to step 3. 6 DOES Summarize adherence and ratings before the visit 7 YOU APPROVE Clinician approves changes to the program 8 RESULT Updated program sent to patient
Read the steps as a list
  1. Clinician assigns a home program
  2. Send program and reminder schedule to the patient
  3. Collect daily check-ins
  4. Is the check-in free of red-flag symptoms?If not: stop reminders, tell the patient to call the clinic and alert the clinician. Back to step 3.
  5. Is completion above target and pain stable?If not: send a follow-up or alert the clinician if pain rises. Back to step 3.
  6. Summarize adherence and ratings before the visit
  7. Clinician approves changes to the programThe agent waits here for your OK.
  8. Updated program sent to patient

How it decides

It tracks completion and pain ratings. Low completion triggers coaching messages; rising pain or red-flag words trigger a clinician alert.

  • Completion under 50% in a week triggers a check-in message
  • Pain up 3 or more points alerts the clinician
  • Red-flag symptoms stop reminders and alert the clinic

Make it yours

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

  • Reminder times and channel
  • Completion target
  • Pain change that triggers an alert
  • Summary format before visits

What keeps you in control

It always asks you first

  • Any change to the exercise program
  • Advice beyond the prescribed program

Hard limits

  • No new exercises are given without the clinician
  • Red-flag replies always reach a person

It stops when

  • Done: episode of care ends
  • Stop: patient opts out of messages

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 happensA knee patient completed 2 of 7 sessions in week 2 and rated step-ups at 6 out of 10 pain, up from 3. The adherence check failed, so the agent sent a follow-up and alerted the physiotherapist. She swapped step-ups for a lower box and approved the change. The next week, completion rose to 6 of 7 with pain at 3, and the check passed.

More agents for physiotherapists