Skip to content

CASE STUDY · Healthcare

AI Voice Agent for a US Healthcare Provider

Published November 2026

The Problem

A US healthcare provider wanted an AI voice agent to handle its appointment scheduling, insurance verification and patient triage calls.

Architecture & Approach

We deployed a Twilio-powered voice AI agent that handles appointment scheduling, insurance verification and patient triage calls.

Outcome: 2,000+ calls handled per week, with a 92% resolution rate.

How we would build it in 2026

If we built this today, we would run the agent on the OpenAI Realtime API over Twilio, and connect the scheduling and insurance verification systems as tools through the Model Context Protocol (MCP). This is our current stack, not the one this project used. Typical delivery: a 2-6 week pilot, then 6-12 weeks to production.

See how we deliver AI voice agents.

Want Results Like These?

Book a free 30-minute architecture review and we'll scope a production AI build for your problem.