Automation library · Customer support

Automate restaurant customer service with WhatsApp and Llama

Started by an incoming WhatsApp message, and works across Postgres and WhatsApp. It hands the judgement calls to a local model. 8 steps, 1 branch, 1 loop or waits: small enough to read in one sitting and change without fear.

SmallCalls a model: a local model

8 stepsSmall: readable in one sitting
1Branch: places the flow splits
1Loop or waits
2Services it connects to

The flow

Starts it 1Model 2Logic 2Service 3

The steps in the order they run, from what starts it.

  1. 1Receive WhatsApp MessageWhats App triggerStarts it
  2. 2Generate Reply with AILm Chat OllamaModel
  3. 3Extract Customer QueryAgentModel
  4. 4Wait For ResponseWaitLogic
  5. 5Check If Table Booking RequiredIfLogic
  6. 6Create New Table BookingPostgresService
  7. 7Send Reply to CustomerWhats AppService
  8. 8Send Booking Confirmation to CustomerWhats AppService

How it's built

Starts on
An incoming WhatsApp message
Steps
8, with 1 branch, 1 loop or waits
Size
Small: readable in one sitting
Connects to
Postgres, WhatsApp
Model
a local model

Questions

What does it need to run?

An n8n account, plus your own Postgres and WhatsApp accounts, and a key for a local model. You connect your own accounts after importing it; none are included.

What starts it?

It starts on an incoming WhatsApp message.

Does it use AI?

Yes. It calls a local model. Model calls are billed by the provider, not by n8n.

How long does it take to set up?

Not long. At 8 steps it can be read in one sitting and changed without fear.

How do I import it?

Copy the workflow, open a new workflow in n8n and paste. The steps appear on the canvas, ready for your own accounts.

Before you run it

Nothing here has been tested by us. It is somebody's working automation, read and described from its own steps. Treat the connections it wants as a list of accounts it will touch, and read the 8 steps before you point it at anything that matters.