Empathetic Appointment Scheduling Assistant

See a live demo of an AI agent booking medical appointments, ensuring no double-bookings through atomic database updates and secure identity management.

OpenAI Agents SDK PostgreSQL FastAPI Deepgram Cartesia

Overview

A voice AI agent that books, reschedules, and cancels medical appointments over a phone-style call, the LLM handles the conversation while a Postgres-backed service owns all the truth (availability, identity, concurrency). Live I’ll show a real voice call (Deepgram, OpenAI Agents SDK, Cartesia over a WebSocket) booking end-to-end, the 50-racer concurrency test proving no double-booking, and the repo.

Links

https://github.com/asking28/voice_agent
Python-based voice agent scheduling appointments using PostgreSQL concurrency controls.

Tech stack

OpenAI Agents SDK

The production-ready SDK for building complex, multi-agent AI workflows with robust orchestration, guardrails, and built-in observability.

The OpenAI Agents SDK is a lightweight, powerful framework for developing agentic AI applications, serving as a production-ready evolution of the previous Swarm experimentation. It’s a Python-first, provider-agnostic tool, supporting the OpenAI Responses API and 100+ other LLMs. Core primitives—Agents, Handoffs, Guardrails, and Sessions—enable sophisticated coordination: Agents use tools, Handoffs delegate tasks between specialized agents, Guardrails validate inputs and outputs, and Sessions manage conversation history automatically. The SDK includes built-in tracing, crucial for visualizing, debugging, and monitoring complex agent flows, ensuring you build reliable, real-world applications efficiently.

https://openai.github.io/openai-agents-python/

View projects
PostgreSQL

PostgreSQL (Postgres): The world's most advanced, open-source object-relational database (ORDBMS), built for reliability and extensibility.

PostgreSQL is the premier open-source ORDBMS, proven over 35+ years of active development. It adheres strictly to ACID properties (Atomicity, Consistency, Isolation, Durability), ensuring data integrity for mission-critical workloads. Key features include robust SQL compliance, Multi-Version Concurrency Control (MVCC), and superior extensibility (e.g., custom data types, functions in multiple languages). Advanced capabilities like native JSON/JSONB support and the PostGIS extension (geospatial data) make it a powerful, flexible choice for complex enterprise applications.

https://www.postgresql.org/

View projects
FastAPI

FastAPI is a modern, high-performance Python web framework for building APIs with automatic OpenAPI documentation.

FastAPI is a robust, high-speed Python web framework: it is built on Starlette (for async capabilities) and Pydantic (for data validation and serialization). Leveraging standard Python 3.8+ type hints, the framework automatically generates interactive API documentation (Swagger UI/ReDoc) and enforces data validation, effectively reducing developer-induced errors by an estimated 40%. This architecture delivers performance on par with Node.js and Go, significantly increasing feature development speed (up to 300% faster). It is production-ready, fully supporting OpenAPI and JSON Schema standards for all API specifications.

https://fastapi.tiangolo.com

View projects
Deepgram

Deepgram is the end-to-end Voice AI platform: delivering real-time, highly accurate Speech-to-Text (STT), Text-to-Speech (TTS), and conversational Voice Agents via a developer-first API.

Deepgram is your enterprise-grade Voice AI platform, built on a proprietary end-to-end deep learning network for unmatched speed and accuracy. Our core APIs (STT, TTS, and the unified Voice Agent API) handle everything from real-time transcription to synthesizing natural speech. Specifically, models like Nova-3 and Flux deliver 2-4x better accuracy on alphanumeric data than competitors, and batch transcription processes one hour of audio in less than 30 seconds (120x real-time). We support flexible deployment (public cloud, private cloud, or self-hosted) and offer advanced features like diarization (up to 10 speakers) and custom model training, ensuring your voice applications—from contact centers to conversational AI—are fast, precise, and scalable.

https://deepgram.com

View projects
Cartesia

Cartesia develops Sonic: a generative AI model delivering high-fidelity text-to-speech with sub-100ms latency for real-time voice applications.

Cartesia specializes in real-time multimodal intelligence, led by its flagship Sonic model. The system achieves industry-leading speeds (under 100 milliseconds of latency) to provide natural, expressive voice synthesis across dozens of languages. Developers use the Cartesia API to power interactive agents, gaming NPCs, and accessibility tools with lifelike audio quality. By prioritizing performance and scale, the platform eliminates the lag found in traditional speech synthesis.

https://cartesia.ai

View projects

Empathetic Appointment Scheduling Assistant

Related talks