Patient Scheduling Agent · Use case
How can a hospital use an AI agent to handle booking and rescheduling requests on its own infrastructure?
A patient scheduling agent takes booking and rescheduling requests by voice and chat, offers the slots your rules allow and books the one the patient chooses. It reminds patients who are due for care. Anything clinical, urgent or outside the rules goes to a member of staff. The agent runs on the hospital's own infrastructure.
Phones ring unanswered.
Cancelled slots go unused.
- ✗ 01Booking lines are busiest at the times patients can call, and cancelled slots go unfilled.
- ✗ 02A booking conversation holds patient information and cannot run on a public AI service.
Where it stops for a person
Clinical questions and exceptions go to staff.Questions about symptoms, urgency or which service a patient needs go to a member of staff. So does any request the rules do not cover.
It handles routine bookings.
Staff take the rest.
Step · 01
The scheduling system and your booking rules are connected.
Step · 02
A patient asks to book or change an appointment.
Step · 03
The agent offers the slots the rules allow.
Step · 04
It books the slot the patient chooses and confirms it.
Step · 05
Requests outside the rules go to staff with the conversation.
Reads from · connectors
Your own APIs
The agent connects to your scheduling system through your own APIs. Calls reach it through your telephony platform, and speech is turned into text by a model you serve.
Acts through · MCP servers
It books, changes and cancels appointments through your scheduling system, within the rules you set. It sends only the reminders you have approved.
What you set up
- Connect the scheduling system.
- Write the booking rules for each clinic.
- Test with booking requests, including ones it should hand over.
Where it runs
The agent, its knowledge store and the model run on infrastructure you own or control. You choose the model and serve it yourself, so questions, documents and answers are not sent to a public AI service.
How you get it today
This page is labelled Use case: the agent is built in Katonic Studio. You describe the job, connect what is named above, add test questions and release the agent once it passes them. When the Catalog holds a tested template for this job, this page will carry the Template label and show how to take it.
Does the agent give medical advice?
No. Clinical questions go to a member of staff.
Can it book any slot?
Only the slots your rules allow for that patient and clinic.
Where are booking conversations processed?
On your own infrastructure, with a model you serve. Nothing is sent to a public AI service.