AI agent for midwifes
Newborn Screening Follow-up Agent
Every baby in the practice has all newborn screens completed and any repeat done on time
What it does
Midwives who attend births outside the hospital are responsible for making sure newborn screens are done and results come back. This agent opens a tracker for every birth. It lists the blood spot, hearing screen and pulse oximetry check with their due windows, then watches the lab portal and the practice record for results. When a result arrives, it reads it and sorts it as normal, needs repeat, or out of range. Repeats get a scheduling draft for the midwife to send. If no result appears five days after collection, it checks the courier and lab records and drafts a lab inquiry. It never tells parents a result. The midwife does that. Edge case: a baby who transferred to hospital care has their screening ownership confirmed with the hospital before the tracker closes.
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
- Birth entered in the practice record
- Open a tracker with each screen and its due window
- Check lab portal and record for results daily
- Has every collected sample returned a result within 5 days?If not: check courier tracking and draft a lab inquiry. Back to step 3.
- Sort each result as normal, repeat needed or out of range
- Midwife reviews results and contacts the familyThe agent waits here for your OK.
- Draft repeat or referral appointments
- Is every repeat screen completed and resulted?If not: send the midwife a reminder and redraft the appointment. Back to step 7.
- Tracker closed with all screens documented
How it decides
It compares each screen's status to its due window and the lab's result categories; anything not normal goes to the midwife with the next step drafted.
- No result after 5 days triggers a courier and lab check
- Hearing screens not done by 4 weeks go to the midwife as overdue
- Any out-of-range result is flagged the same day
- Hospital-transferred babies need written confirmation of who owns follow-up
Make it yours
Every agent is a starting point. You choose these settings for your own situation.
- Days before a missing result is chased (default 5)
- Hearing screen deadline (default 4 weeks)
- Which screens are tracked
- Reminder schedule for the midwife
What keeps you in control
It always asks you first
- Midwife reviews every result before families are told
- Midwife approves appointment and referral messages
Hard limits
- Never shares results with families directly
- Never decides on clinical referral
- Keeps records within the practice system
It stops when
- Done: all screens normal or repeats complete
- Stop: baby care transferred and confirmed with receiving 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.
- 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