The Voice Receptionist — CxD Case Study

~90%

Of inbound calls answered, including after hours

~40%

Of bookings handled without staff involvement

Seconds

For distressed or urgent callers to reach a human

The challenge

Every missed call was a missed booking.

Who they are

A multi-practitioner clinic missing a high share of inbound calls during peak hours and after close.

The problem

After-hours callers went to voicemail and rarely called back. The team didn't want a robotic phone tree — and they needed upset or urgent callers to reach a human fast, not get stuck talking to a bot.

What we built

A receptionist that answers — and knows its limits.

An AI voice agent that answers every call, books against live availability, and escalates to a human the moment a caller sounds distressed or the request falls outside its scope.

The system

See it work, end to end.

How it works

Handle the routine, hand off the rest.

The agent answers in a natural voice, identifies why the caller is ringing, and checks live availability.

For routine requests — book, reschedule, cancel, hours, directions — it completes the task and confirms by SMS.

Tone and sentiment are monitored throughout. If a caller sounds frustrated, anxious, or urgent, the call is warm-transferred to a human with the context already captured.

Anything outside the agent's scope is escalated rather than guessed at.

The result

Every call answered. The right ones reach a person.

~90%

Of calls answered, after hours included

~40%

Of bookings handled without staff

Seconds

For urgent callers to reach a human, with full context

The pattern: a workflow backbone, a reasoning layer, a system of record, and a channel. The system handles volume and routine; people handle judgment and exceptions. That's what makes it an automation the business can trust — not AI running unsupervised.