Inbound and outbound

On-premises AI agent for clinics and labs: appointment booking

Health data is a special category under GDPR (Art. 9). Recordings and transcripts should stay with you: AI Fortis recognises speech and synthesises the voice on your server.

What it solves

  • Reception can't keep up with the phone.
  • Missed appointments.
  • Sensitive data that must not leave the premises.

How it works

  1. Booking with a specific doctor through your hospital/booking system.
  2. Reminder the day before with confirm or cancel.
  3. Information: opening hours, test preparation, whether results are ready (no medical advice).
  4. Emergencies: the agent points to 112 and transfers to a person.

Get a free sample agent

Example call

AgentI can book you with Dr Ivanova on Thursday at ten or Friday at two. Which suits you better?

Illustration with invented names and data. Script, tone and rules are yours. The agent speaks Bulgarian; the lines are translated here.

Integrations

  • Hospital information system or calendar through an HTTP tool
  • Webhook when booked or cancelled
  • Transfer to reception

All integrations →

Compliance

  • The agent gives no medical advice; that is a prompt rule and a transfer topic.
  • The agent says at the start that it is an AI assistant (EU AI Act, Art. 50) and announces that the call is recorded.
  • Recordings and transcripts stay on your server; retention is set per client.

Security & GDPR →

What we measure in the pilot

  • Appointments booked without staff
  • No-shows
  • Calls handled after hours

We will publish results from real deployments with the customers' permission.

Frequently asked questions

Does everything really run on our servers?

Yes: our own speech recognition and voice models, conversation control, the telephony gateway, campaigns and recordings. The language model is your choice: your existing provider via API (then only the text of the turns is sent) or a fully local model with no internet.

How fast does the agent answer?

In our test calls with a cloud language model the median time from the end of the caller's sentence to the first sound of the answer was 1.4 s; the voice itself starts 136 ms after the answer text is ready. The language model is the largest part, so we measure it with your choice in the pilot.

Which telephony does it work with?

Any standard SIP trunk or PBX: your existing numbers and carrier stay in place.

Does the agent say it is an AI?

Yes. At the start of the call the agent introduces itself as an AI assistant and announces the recording (EU AI Act, Art. 50). The wording is configurable.

Get a free sample agent for "Healthcare"

Tell us your call type and language; we build a sample agent you can call and judge yourself.

  • GDPR by design
  • Runs on your own servers
  • 24/7 operation and support
  • A team of 5 in Sofia, EU

Already running in production at organisations in Bulgaria — names under NDA.

How we prove it →