← Back to Directory
Customer ServicePlumbingFreelance/Agency

A Plumbing AI Receptionist That Books Emergency Calls and Logs Everything to a CRM

An AI voice receptionist for a plumbing company that books emergency service calls, checks real time calendar availability, and logs every conversation to Airtable automatically.

The Strategy

Plumbing emergencies do not happen during business hours. Burst pipes, backed up sewage, and water heater failures hit at 11 PM on a Sunday, and the homeowner is calling every plumber in their area until someone picks up. Mason Anderson built an AI voice receptionist for a plumbing company that handles exactly this scenario. The agent picks up every call, identifies the problem, collects the customer's name, phone number, and address, checks Cal.com for the next available technician slot, and books an emergency service call on the spot. The system runs on Vapi for the voice agent with ElevenLabs providing the voice and Deepgram handling transcription. The backend automation lives in Make.com with four scenarios handling calendar context injection, availability checking, appointment booking, and post call data processing. A matching chatbot widget runs on the company website using the same backend automations, keeping a single source of truth for all customer interactions regardless of channel.

How It Works

1

Set up a Vapi AI agent with ElevenLabs voice and Deepgram Nova 3 transcription.

2

Build a Make.com scenario that generates 31 days of calendar context from Cal.com.

3

Create four Cal.com event types for different service levels.

4

Build a second Make.com scenario that checks Cal.com availability in real time.

5

Build a third Make.com scenario that executes bookings and updates Airtable CRM.

6

Configure Airtable with AI Agent Conversations and Opportunities tables.

7

Build a post call webhook in Vapi for transcript processing and CRM insertion.

8

Embed the Vapi chat widget on the company website using the same backend.

9

Build a periodic check scenario for pending chat conversations older than 30 minutes.

Results

No revenue metrics shared. The system was demonstrated working end to end with a live emergency plumbing call booked and logged without errors.

Our Take

We think the Cal.com calendar context injection separates this from most voice agent demos. Best suited for AI agency builders who want a proven plumbing receptionist template.

Related Strategies

More AI agent strategies you might find useful

Want more strategies like this?

Get weekly AI agent case studies in your inbox.