All Case Studies
Case Study

AI Voice Agent: Automated Appointment Booking via Phone

An AI phone agent that handles inbound calls for a dental practice, books appointments, answers FAQs, and reduces missed calls from 40% to 3%.

Client: Confidential Dental Practice Network

Timeline
14 days
Investment
$7,499
Key Result
Missed calls reduced from 40% to 3%, 120 appointments/month booked by AI

Dashboard showing a call log with AI-handled calls, appointment calendar with AI-booked slots highlighted in blue, and a real-time call in progress with transcript streaming.

The Challenge

The practice received 300+ calls per month across 3 locations. Two receptionists handled calls, but during peak hours (mornings and lunch), 40% of calls went to voicemail. Most callers didn't leave messages — they called the next dentist on Google. Each missed call represented $250-500 in potential revenue. The practice owner estimated $15,000/month in lost revenue from missed calls alone. They tried an answering service, but the agents couldn't book appointments (no system access) and the lag frustrated callers.

Our Approach

We built an AI voice agent using Vapi for voice infrastructure and Claude for conversation intelligence. The agent answered calls in under 2 seconds with a natural, friendly voice. It could handle three primary workflows: appointment booking (checking real-time availability in the practice management system), insurance verification (looking up coverage in a provider database), and FAQ answering (office hours, location, accepted insurance plans, procedure pricing). The agent integrated with the practice's existing Dentrix scheduling system via API. For complex requests (emergency dental issues, insurance disputes, complaints), the agent transferred to a human receptionist with a brief summary on screen. We added a dashboard showing call volume, AI resolution rate, appointments booked, and transfer reasons. The practice could customize the agent's greeting, personality, and escalation rules.

What We Built

AI voice agent with natural speech via Vapi and Claude intelligence.
Real-time appointment booking integrated with Dentrix practice management.
Insurance verification lookup against provider database.
FAQ answering for hours, locations, pricing, and accepted plans.
Call analytics dashboard with resolution rates and transfer reasons.

Delivery Timeline

Day 1-3: Voice Infrastructure

Vapi setup, Claude integration, base conversation flows, voice personality tuning.

Day 4-7: Scheduling Integration

Dentrix API connection, real-time availability check, appointment booking flow.

Day 8-10: FAQ + Insurance

Knowledge base for practice FAQs, insurance verification lookup, multi-location handling.

Day 11-12: Dashboard

Call analytics, transcript viewer, resolution rates, agent configuration panel.

Day 13: Testing

Live call testing, edge case handling, transfer flow validation, latency optimization.

Day 14: Launch

Production deployment, phone number forwarding setup, staff training.

Tech Stack

Vapi
Voice Infrastructure
Claude AI
Conversation Engine
Hono
Backend
Next.js
Dashboard
PostgreSQL
Database
Dentrix API
Practice Management
Railway
Hosting

Architecture

frontend

Next.js admin dashboard for call analytics and agent configuration.

backend

Hono on Railway with Vapi webhook handlers and Dentrix API integration.

auth

Better Auth with practice-level admin access.

data

PostgreSQL for call logs and analytics. Dentrix API for scheduling.

voice

Vapi for voice infrastructure. Claude for conversation intelligence.

Security

hipaa

HIPAA-aware call handling. No PHI stored in plain text. Call recordings encrypted.

rbac

Practice Admin and Location Manager roles.

audit

Every call logged with transcript, actions taken, and outcome.

monitoring

Real-time call quality monitoring. Alert on high transfer rates.

The Results

Missed call rate
40%3%
Appointments booked by AI monthly
0120
Estimated recovered revenue per month
$0$15,000+
We were losing $15K a month to missed calls. The AI answers every call in 2 seconds, books appointments, and sounds better than most humans. Patients don't even realize it's AI until we tell them.
Dr. Emily Nguyen
Practice Owner

Key Takeaways

Voice AI has crossed the uncanny valley for structured conversations. Appointment booking, FAQ answering, and simple workflows sound natural enough that most callers don't notice.

Integration with existing practice management software is the real challenge. The AI agent is only useful if it can actually book appointments in the real schedule.

Sub-2-second answer time is critical for phone agents. Callers expect immediate pickup. Any delay and they hang up.

Deliverables

Full source codeVapi voice agentDentrix integrationCall analytics dashboardStaff training guide

FAQ

Frequently Asked Questions

Related Case Studies

Want similar results?

Book a free 15-min scope review. Your vision, engineered for production in 14 days. Fixed price.

Book Scope Review