Waleed Ali

Real-time AI receptionist with full observability

LiveKit Doctor Receptionist

LiveKitGeminiElevenLabsDeepgramLangfuse

Live demo / source links coming soon.

Problem

Medical front desks need a receptionist that can hold a natural phone conversation, manage appointments, and stay reliable — with every interaction traceable for debugging and quality review.

Solution

Built a real-time AI receptionist using LiveKit agents, Google Gemini for reasoning, ElevenLabs for TTS, and Deepgram for STT. Integrated Langfuse for tracing, logging, and prompt evaluation. The agent manages appointments, refreshes patient data, responds conversationally, and handles fallback logic with full traceability.

Tech Stack

  • LiveKitReal-time audio transport and agent orchestration for the call.
  • Google GeminiConversational reasoning and appointment-handling logic.
  • ElevenLabsNatural-sounding text-to-speech for the receptionist's voice.
  • DeepgramLow-latency speech-to-text for caller input.
  • LangfuseTracing, logging, and prompt evaluation for production observability.
Screenshots and a demo walkthrough are coming soon.

Challenges

Write-up coming soon.

Impact

Metrics coming soon.

Lessons Learned

Write-up coming soon.