AI agent for paramedics
Obstetric Emergency Drill Agent
Teams practice regularly and missed steps are corrected and verified.
What it does
Obstetric emergencies such as shoulder dystocia or postpartum hemorrhage are rare, so teams rarely practice them. The agent schedules drills on the practice calendar and builds a scenario that fits the team's recent cases and protocols. After each drill, it takes the record of what happened, such as time to call for help and steps missed, and scores performance against the protocol. It assigns repeat practice for the missed steps and builds the next drill to target them. At the next drill it checks that those steps are now done. The lead approves the schedule and the scenarios. Edge case: a drill that exposes an equipment fault creates a task for the lead to fix it before the next shift.
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
- Drill month starts
- Read the calendar, roster and protocols
- Build a scenario with the checklist
- Lead approves the schedule and scenarioThe agent waits here for your OK.
- Send invitations and the scenario to the facilitator
- Read the drill record after the session
- Score each step against the protocol
- List missed steps and assign repeat practice
- Were the previously missed steps done correctly in this drill?If not: Keep them in the next scenario and add a targeted skills session. Back to step 3.
- Create tasks for any equipment faults
- Drill report and next scenario
How it decides
It compares each drill with the protocol checklist and builds the next scenario around the steps missed.
- Time to call for help over the target is flagged
- Missed critical steps are repeated until correct
- Equipment faults become tasks
- Rotate scenarios across emergencies
Make it yours
Every agent is a starting point. You choose these settings for your own situation.
- Drill frequency
- Scenarios list
- Timing targets
- Facilitator
- Repeat rule
What keeps you in control
It always asks you first
- Lead approves the schedule and scenarios
- Lead approves any protocol change
Hard limits
- Never change a protocol
- Never use drill records to judge individuals publicly
- Never skip a missed critical step
It stops when
- Done: all critical steps are done correctly in two consecutive drills
- Stop: the team cannot meet because of service demand
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