Skip to content
NMNikolaos.
Back to projects

Engineering case study / Applied AI · Automation

AI Receptionist

A working voice-based appointment assistant prototype connecting customer conversations to real booking operations.

Prototype · Active developmentUpdated 2026-11-18
View GitHub

Watch the working demonstration

Prototype demonstration. Video playback is provided by YouTube; opening it may involve YouTube cookies and data processing. Watch directly on YouTube.

The video demonstrates the prototype workflow. The management dashboard is still under development and is not presented as a finished product.

Problem and solution

Small businesses spend time answering service questions and coordinating appointments. I built a browser-based voice assistant that connects conversational requests to FastAPI operations instead of merely generating text.

Architecture

AI Receptionist architecture diagram showing browser, FastAPI backend and external services
Original architecture diagram from the AI Receptionist showcase.

Stack: Python, FastAPI, Pydantic, SQLAlchemy, Supabase Auth, PostgreSQL-compatible persistence, Vite/JavaScript and OpenAI API.

Voice-to-booking workflow

  1. A customer starts a browser voice session and asks for a service and appointment.
  2. The assistant interprets the request and invokes structured tools such as check_availability and book_appointment.
  3. Scheduling logic checks service duration, opening hours, closures, existing bookings and past-time restrictions.
  4. The booking path rechecks availability and uses a PostgreSQL advisory lock to reduce competing-booking conflicts.
  5. The assistant communicates the result through synthesized speech.

Engineering highlights

Known limitations

Next steps

Reduce latency, strengthen automated integration tests, complete privacy controls and improve the dashboard without overstating readiness.

Contact about this projectDownload CV (PDF)