Agentic Intake Coordinator

Conversational Data Assistant

This project involved designing and deploying a sophisticated, voice-based intake coordinator system for a major digital health platform. The system acts as a comprehensive virtual assistant, capable of handling appointment bookings, updates, cancellations, answering user questions, and providing information in a professional, empathetic manner.

Key Achievement: The system reduced form abandonment by 60–80% through a guided, conversational flow, offering 24/7 availability and enhanced accessibility across multi‑channels (web audio and phone calls via Twilio).

Core Innovation: The Real-Time Voice Pipeline

The architecture is centered around maintaining sub‑second latency and absolute reliability, critical standards for a healthcare application.

• Real-time Voice Foundation: Direct integration with the OpenAI Realtime API provides low-latency Speech‑to‑Text and Text‑to‑Speech processing, enabling fluid voice interactions necessary for high‑quality user experience.
• Function Calling & Tool Integration: The LLM uses native function calling to seamlessly interact with external utilities, allowing it to maintain conversation flow while performing complex tasks (e.g., checking appointment availability or validating collected data).

Layered Architecture for Security and Reliability

The system operates on a four‑layered, modular architecture built for scalability and strict separation of concerns, ensuring maintainability and easy auditing for compliance.

Enterprise-Grade Technical Highlights

• Professional Guardrails Framework: Implements strict, healthcare‑specific conversation boundaries enforced by the Conversation Manager. This includes real‑time crisis detection, professional tone enforcement, and a strict boundary against providing medical advice.
• Dynamic State Management: The Intake Request Manager uses sophisticated state machine logic for AI‑driven adaptive questioning. It intelligently tracks booking progress and handles information provided by the user in any non‑linear order.
• HIPAA‑Compliant Memory Architecture:
  • Redis Cluster provides sub‑50ms access for active session state.
  • DynamoDB/RDS provides HIPAA‑compliant, persistent storage for audit trails and conversation history.
  • Vector Database (Pinecone/Weaviate) is used for RAG‑powered intelligence, enabling context‑aware semantic search of policy documents and professional profiles.
• Comprehensive Analytics & Optimization: A dedicated Analytics API powers real‑time conversation monitoring, tracks booking completion funnels, and generates automated summaries within 30 seconds of conversation completion for operational review.