Dealer AI receptionist pulls customer data mid-call through Make (20,000 calls a month)

Source-checked Oct 11, 2026Case study

Stellantis &You UK built a virtual receptionist on ElevenLabs and connected it to Make so it can pull real customer data during the call.

Source: Make, Make case study, 2026-09-22

1What it does

Stellantis &You UK built a virtual receptionist on ElevenLabs and connected it to Make so it can pull real customer data during the call.

2Who it is for

Industry: Automotive dealership
Platform: Make
Category: Voice AI
Tools used: MakeElevenLabs

3How it works

Every step, in order, is in Workflow at a glance, pinned on the right as you scroll.

Workflow at a glanceMake scenario

01 Trigger
Unanswered dealership call routed to the AI agent.
02 Action
ElevenLabs agent answers.
03 Action
Mid-call tool calls hit Make scenarios.
04 Action
Make looks up customer data and returns it to the agent.

Trigger: Unanswered dealership call routed to the AI agent.
AI step: Unknown.

4How it went

Per Make: the agent handles 20,000 calls a month and saves about £200,000 a year on this use case.

Only what the source reports. Numbers above come from the source.

5Worth knowing

The human reception team only worked business hours, so after-hours calls were the gap.

6Recipe

Adapted from source Reworded or reconstructed from what the source shows.

Pattern: voice agent tool -> Make webhook -> lookup (CRM/DMS) -> Webhook response with only the fields the agent needs.

7Source

Open the original Make case study by Make →

Source opened and read on 2026-10-11.

More Voice AI builds

All builds →

HighLevel Voice AI

Voice AI agent that transfers live, updates fields and texts mid-call

A HighLevel Voice AI agent set up with in-call actions: live call transfer, trigger a workflow, update custom fields and send a text during the call. A call summary workflow runs when the call ends.

Any local business Written by Builds That Work

HighLevel Voice AI

The voice AI call summary text that owners actually read

The owner never hears the call. He reads the text 30 seconds later. This build makes that summary the product: decision first, five lines, the caller's own words, what was promised and what is unclear.

Home services Adapted from source

HighLevel Voice AI

AI receptionist in HighLevel built from three prompts

Build the knowledge base first with two prompts (business info extraction and FAQ expansion), then write custom agent instructions. Connect a calendar, assign a number, and try to break it for 20 minutes before going live.

Home services Adapted from source