# Customer Support with Gemini: n8n workflow template

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

Source: https://millionrounds.com/workflow/customer-support-with-gemini (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)

# Customer Support with Gemini

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. 23 steps, 1 branch: large, and worth reading before you trust it with anything live.

Large Calls a model: Gemini Retrieval

[Download free](https://millionrounds.com/login?next=%2Fapp%2Fworkflow%2Fcustomer-support-with-gemini)

**23 steps** Large: read it before trusting it with anything live

**1** Branch: places the flow splits

**0** Loops or waits

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

## The flow

Starts it 4 Model 15 Logic 4

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

- 1 **Smart Gemini** Lm Chat Google Gemini *Model*
- 2 **Gemini Evaluator** Lm Chat Google Gemini *Model*
- 3 **find_relevant_image** Agent Brains Rag Tool *Model*
- 4 **search_knowledge_base** Agent Brains Rag Tool *Model*
- 5 **Webhook** Integration trigger *Starts it*
- 6 **Stub "Webhook"** Webhook *Starts it*
- 7 **Gemini mini** Lm Chat Google Gemini *Model*
- 8 **Chat Memory** Memory Mongo Db Chat *Model*
- 9 **General Expert** Agent *Model*
- 10 **Greeting Expert** Agent *Model*
- 11 **Product Expert** Agent *Model*
- 12 **Structured Output Parser for Eval** Output Parser Structured *Model*
- 13 **Evaluator** Chain Llm *Model*
- 14 **Guardrails** Guardrails *Model*
- 15 **Response** Respond To Webhook *Starts it*
- 16 **Selecting an expert who will answer the question** Switch *Logic*
- 17 **Main variables** Set *Logic*
- 18 **Error Response (guardrails)** Respond To Webhook *Starts it*
- 19 **GET All Products** Knowledge Base *Model*
- 20 **GET Customer Profile** Knowledge Base *Model*
- 21 **Product Identifier Flow** Execute Workflow *Logic*
- 22 **Setup Agent Vars** Set *Logic*
- 23 **GET Product Manual** Knowledge Base *Model*

## How it's built

- **Starts on:** Another system calling it
- **Steps:** 23, with 1 branch
- **Size:** Large: read it before trusting it with anything live
- **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?

Take your time. At 23 steps it is large: read it before trusting it with anything live.

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 23 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%2Fcustomer-support-with-gemini)
- **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.

- [**AI email support system: Gmail, Gemini, GPT-4, Slack & Google** 23 steps · calls a model · Gmail, Google Drive](https://millionrounds.com/workflow/ai-email-support-system-gmail-gemini-gpt-4-slack-and-google)
- [**Build RAG-powered support agent for Jira issues with Pinecone** 23 steps · calls a model · Pinecone](https://millionrounds.com/workflow/build-rag-powered-support-agent-for-jira-issues-with-pinecon)
- [**Create a WhatsApp customer support bot with OpenAI** 23 steps · calls a model · Gmail, Google Calendar](https://millionrounds.com/workflow/create-a-whatsapp-customer-support-bot-with-openai)
- [**Draft grounded Gmail support replies from a Notion KB** 23 steps · calls a model · Gmail, Notion](https://millionrounds.com/workflow/draft-grounded-gmail-support-replies-from-a-notion-kb)
- [**Facebook Messenger chatbot with OpenAI** 23 steps · calls a model](https://millionrounds.com/workflow/facebook-messenger-chatbot-with-openai)
- [**Generate multiple language blogpost with OpenAI** 23 steps · calls a model · WordPress](https://millionrounds.com/workflow/generate-multiple-language-blogpost-with-openai)