# Build a WhatsApp assistant with Google Suite: n8n workflow

> Started by an incoming WhatsApp message, and works across Gmail, Google Calendar, Google Tasks and WhatsApp.

Source: https://millionrounds.com/workflow/build-a-whatsapp-assistant-with-google-suite (Millionrounds; every figure on the page links to its filing or article)

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

# Build a WhatsApp assistant with Google Suite

Started by an incoming WhatsApp message, and works across Gmail, Google Calendar, Google Tasks and WhatsApp. It puts Gemini, Groq and one other behind a retrieval step, so answers are drawn from documents you supply rather than from the model alone. 63 steps, 2 branches: large, and worth reading before you trust it with anything live.

Large Calls a model: Gemini, Groq Retrieval

[Download free](https://millionrounds.com/login?next=%2Fapp%2Fworkflow%2Fbuild-a-whatsapp-assistant-with-google-suite)

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

**2** Branches: places the flow splits

**0** Loops or waits

**4** Services it connects to

## The flow

Starts it 3 Model 30 Logic 5 Service 22

The steps in the order they run, from what starts it. The first 60 of 63.

- 1 **WhatsApp Trigger** Whats App trigger *Starts it*
- 2 **WeatherMap** Open Weather Map Tool *Service*
- 3 **Think** Tool Think *Model*
- 4 **Simple Memory** Memory Buffer Window *Model*
- 5 **Get many events** Google Calendar Tool *Service*
- 6 **Create an event** Google Calendar Tool *Service*
- 7 **Update an event** Google Calendar Tool *Service*
- 8 **Delete an event** Google Calendar Tool *Service*
- 9 **Get an event** Google Calendar Tool *Service*
- 10 **gemini-2.5-flash** Lm Chat Google Gemini *Model*
- 11 **gpt-5-nano** Lm Chat Open Router *Model*
- 12 **Get many messages** Gmail Tool *Service*
- 13 **Get a message** Gmail Tool *Service*
- 14 **Create a task in Google Tasks** Google Tasks Tool *Service*
- 15 **Delete a task in Google Tasks** Google Tasks Tool *Service*
- 16 **Get many tasks in Google Tasks** Google Tasks Tool *Service*
- 17 **image creation** Http Request Tool *Service*
- 18 **Brave Search** Brave Search Tool *Service*
- 19 **Brave Search1** Brave Search Tool *Service*
- 20 **gpt-4.1-nanoChat Model1** Lm Chat Open Router *Model*
- 21 **perprlexcia** Http Request Tool *Service*
- 22 **Wikipedia** Tool Wikipedia *Model*
- 23 **Default Data Loader** Document Default Data Loader *Model*
- 24 **Google Gemini Chat Model** Lm Chat Google Gemini *Model*
- 25 **Webhook2** Webhook *Starts it*
- 26 **Webhook3** Webhook *Starts it*
- 27 **Google Gemini Chat Model5** Lm Chat Google Gemini *Model*
- 28 **gpt-4.1-nano** Lm Chat Vercel Ai Gateway *Model*
- 29 **codestral-embed-2505** Embeddings Mistral Cloud *Model*
- 30 **codestral-embed-** Embeddings Mistral Cloud *Model*
- 31 **codestral-embed-2506** Embeddings Mistral Cloud *Model*
- 32 **openai LLM** Lm Chat Vercel Ai Gateway *Model*
- 33 **openai LLM1** Lm Chat Groq *Model*
- 34 **openai/gpt-oss-120b** Lm Chat Vercel Ai Gateway *Model*
- 35 **Tavily web search** Http Request Tool *Service*
- 36 **openai/gpt-5-mini** Lm Chat Vercel Ai Gateway *Model*
- 37 **openai/gpt-5-mini1** Lm Chat Vercel Ai Gateway *Model*
- 38 **Switch** Switch *Logic*
- 39 **AI Agent1** Agent *Model*
- 40 **Calendar Agent** Agent Tool *Model*
- 41 **Gmail tool** Agent Tool *Model*
- 42 **Task agent** Agent Tool *Model*
- 43 **Research agent** Agent Tool *Model*
- 44 **MongoDB Atlas Vector Store** Vector Store Mongo DBAtlas *Model*
- 45 **Extract Memory Info** Chain Llm *Model*
- 46 **AI Agent** Agent *Model*
- 47 **Summarize Chat** Chain Llm *Model*
- 48 **MongoDB Atlas Vector Store2** Vector Store Mongo DBAtlas *Model*
- 49 **MongoDB Atlas Vector Store1** Vector Store Mongo DBAtlas *Model*
- 50 **Download media** Whats App *Service*
- 51 **Typing....** Http Request *Service*
- 52 **Send message** Whats App *Service*
- 53 **Check If Worth Remembering** If *Logic*
- 54 **Clean Prompt Text1** Code *Logic*
- 55 **HTTP Request5** Http Request *Service*
- 56 **Code1** Code *Logic*
- 57 **send chat history to MongoDB** Http Request *Service*
- 58 **Edit Fields1** Set *Logic*
- 59 **HTTP Request** Http Request *Service*
- 60 **Analyze image** Google Gemini *Model*

## How it's built

- **Starts on:** An incoming WhatsApp message
- **Steps:** 63, with 2 branches
- **Size:** Large: read it before trusting it with anything live
- **Connects to:** Gmail, Google Calendar, Google Tasks, WhatsApp
- **Model:** Gemini, Groq, OpenRouter
- **Retrieval:** Answers are drawn from documents you supply, not from the model alone

## Questions

What does it need to run?

An n8n account, plus your own Gmail, Google Calendar, Google Tasks and WhatsApp accounts, and a key for Gemini and Groq. 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 Gemini, Groq and OpenRouter. 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 63 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 63 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-whatsapp-assistant-with-google-suite)
- **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.

## Connects to

Each opens the other workflows that use it.

[Gmail](https://millionrounds.com/workflows?service=Gmail#library)[Google Calendar](https://millionrounds.com/workflows?service=Google+Calendar#library)[Google Tasks](https://millionrounds.com/workflows?service=Google+Tasks#library)[WhatsApp](https://millionrounds.com/workflows?service=WhatsApp#library)

## Workflows like it

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

- [**Build a multi-functional Telegram bot with Gemini** 65 steps · calls a model · Google Calendar, Google Docs](https://millionrounds.com/workflow/build-a-multi-functional-telegram-bot-with-gemini)
- [**Automated HR Service System with WhatsApp and OpenAI** 57 steps · calls a model · Gmail, Google Calendar](https://millionrounds.com/workflow/automated-hr-service-system-with-whatsapp-and-openai)
- [**Automate salon appointment management with WhatsApp and OpenAI** 56 steps · calls a model · Gmail, Google Calendar](https://millionrounds.com/workflow/automate-salon-appointment-management-with-whatsapp-and-open)
- [**Multi-platform AI sales agent with RAG and CRM** 71 steps · calls a model · Airtable, Google Calendar](https://millionrounds.com/workflow/multi-platform-ai-sales-agent-with-rag-and-crm)
- [**Multi-agent salon appointment management with Telegram** 52 steps · calls a model · Google Calendar, Redis](https://millionrounds.com/workflow/multi-agent-salon-appointment-management-with-telegram)
- [**Automated multi-platform sales agent with Gemini** 75 steps · calls a model · Google Calendar, Postgres](https://millionrounds.com/workflow/agente-de-ventas-automatizado-multiplataforma-with-gemini)