# Build a Facebook Messenger customer service AI chatbot: n8n workflow

> Started by another system calling it. It calls services over plain HTTP rather than through connectors.

Source: https://millionrounds.com/workflow/build-a-facebook-messenger-customer-service-ai-chatbot (Millionrounds; every figure on the page links to its filing or article)

[Automation library](https://millionrounds.com/workflows) · [Customer support](https://millionrounds.com/workflows?category=Customer+support#library)

# Build a Facebook Messenger customer service AI chatbot

Started by another system calling it. It calls services over plain HTTP rather than through connectors. It puts Gemini behind a retrieval step, so answers are drawn from documents you supply rather than from the model alone. 16 steps, 3 branches: a working afternoon to understand properly.

Medium Calls a model: Gemini Retrieval

[Download free](https://millionrounds.com/login?next=%2Fapp%2Fworkflow%2Fbuild-a-facebook-messenger-customer-service-ai-chatbot)

**16 steps** Medium: a working afternoon

**3** Branches: places the flow splits

**0** Loops or waits

**0** Services by connector: it calls them over plain HTTP

## The flow

Starts it 2 Model 4 Logic 5 Service 5

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

- 1 **Facebook Webhook** Webhook *Starts it*
- 2 **Conversation Memory** Memory Buffer Window *Model*
- 3 **Gemini Flash** Lm Chat Google Gemini *Model*
- 4 **Confirm Webhook** Respond To Webhook *Starts it*
- 5 **Is message** If *Logic*
- 6 **Process Merged Message** Agent *Model*
- 7 **Structured Output Parser** Output Parser Structured *Model*
- 8 **From user?** If *Logic*
- 9 **Cut if reply more than 2000 characters** Code *Logic*
- 10 **Set Context** Set *Logic*
- 11 **Send Text** Http Request *Service*
- 12 **Seen** Http Request *Service*
- 13 **Switch** Switch *Logic*
- 14 **Typing** Http Request *Service*
- 15 **Send image** Http Request *Service*
- 16 **Send video** Http Request *Service*

## How it's built

- **Starts on:** Another system calling it
- **Steps:** 16, with 3 branches
- **Size:** Medium: a working afternoon
- **Connects to:** Nothing by connector; it calls services over plain HTTP
- **Model:** Gemini
- **Retrieval:** Answers are drawn from documents you supply, not from the model alone

## Questions

What does it need to run?

An n8n account, and a key for Gemini. You connect your own accounts after importing it; none are included.

What starts it?

It starts on another system calling it.

Does it use AI?

Yes. It calls Gemini. Its answers draw on documents you give it, not on the model alone. Model calls are billed by the provider, not by n8n.

How long does it take to set up?

Plan an afternoon. 16 steps is enough that you should read each one before running it.

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 16 steps before you point it at anything that matters.

## Run it in n8n

- **Create your n8n account** Free to start. n8n is where the workflow runs. [Create an n8n account ↗](https://millionrounds.com/n8n)
- **Download the workflow** Free with a Millionrounds account. [Download free](https://millionrounds.com/login?next=%2Fapp%2Fworkflow%2Fbuild-a-facebook-messenger-customer-service-ai-chatbot)
- **Paste it into n8n** Open a new workflow in n8n and paste. Then connect your own accounts.

Stored with the author's traces removed: canvas notes, instance identifiers, saved credential names and any live document they had left behind.

## Workflows like it

Also customer support, with the same services where possible, closest in size first.

- [**Answer customer questions and book jobs with OpenAI RAG** 16 steps · calls a model · Gmail, Google Calendar](https://millionrounds.com/workflow/answer-customer-questions-and-book-jobs-with-openai-rag)
- [**Answer customer questions and book jobs with OpenAI RAG** 16 steps · calls a model · Gmail, Google Calendar](https://millionrounds.com/workflow/answer-customer-questions-and-book-jobs-with-openai-rag-2)
- [**Answer electronics questions with Gemini and SerpAPI** 16 steps · calls a model · Supabase vectors](https://millionrounds.com/workflow/answer-electronics-questions-with-gemini-and-serpapi)
- [**Answer infrastructure questions in Slack with OpenAI** 16 steps · calls a model · Qdrant, Slack](https://millionrounds.com/workflow/answer-infrastructure-questions-in-slack-with-openai)
- [**Answer support FAQs with Gemini and Supabase** 16 steps · calls a model · Google Sheets, Supabase vectors](https://millionrounds.com/workflow/answer-support-faqs-with-gemini-and-supabase)
- [**Automate IT support: Convert emails to Jira tickets** 16 steps · calls a model · Gmail, Jira](https://millionrounds.com/workflow/automate-it-support-convert-emails-to-jira-tickets)