Automation library · Scheduling

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.

LargeCalls a model: Gemini, GroqRetrieval

Download free
63 stepsLarge: read it before trusting it with anything live
2Branches: places the flow splits
0Loops or waits
4Services it connects to

The flow

Starts it 3Model 30Logic 5Service 22

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

  1. 1WhatsApp TriggerWhats App triggerStarts it
  2. 2WeatherMapOpen Weather Map ToolService
  3. 3ThinkTool ThinkModel
  4. 4Simple MemoryMemory Buffer WindowModel
  5. 5Get many eventsGoogle Calendar ToolService
  6. 6Create an eventGoogle Calendar ToolService
  7. 7Update an eventGoogle Calendar ToolService
  8. 8Delete an eventGoogle Calendar ToolService
  9. 9Get an eventGoogle Calendar ToolService
  10. 10gemini-2.5-flashLm Chat Google GeminiModel
  11. 11gpt-5-nanoLm Chat Open RouterModel
  12. 12Get many messagesGmail ToolService
  13. 13Get a messageGmail ToolService
  14. 14Create a task in Google TasksGoogle Tasks ToolService
  15. 15Delete a task in Google TasksGoogle Tasks ToolService
  16. 16Get many tasks in Google TasksGoogle Tasks ToolService
  17. 17image creationHttp Request ToolService
  18. 18Brave SearchBrave Search ToolService
  19. 19Brave Search1Brave Search ToolService
  20. 20gpt-4.1-nanoChat Model1Lm Chat Open RouterModel
  21. 21perprlexciaHttp Request ToolService
  22. 22WikipediaTool WikipediaModel
  23. 23Default Data LoaderDocument Default Data LoaderModel
  24. 24Google Gemini Chat ModelLm Chat Google GeminiModel
  25. 25Webhook2WebhookStarts it
  26. 26Webhook3WebhookStarts it
  27. 27Google Gemini Chat Model5Lm Chat Google GeminiModel
  28. 28gpt-4.1-nanoLm Chat Vercel Ai GatewayModel
  29. 29codestral-embed-2505Embeddings Mistral CloudModel
  30. 30codestral-embed-Embeddings Mistral CloudModel
  31. 31codestral-embed-2506Embeddings Mistral CloudModel
  32. 32openai LLMLm Chat Vercel Ai GatewayModel
  33. 33openai LLM1Lm Chat GroqModel
  34. 34openai/gpt-oss-120bLm Chat Vercel Ai GatewayModel
  35. 35Tavily web searchHttp Request ToolService
  36. 36openai/gpt-5-miniLm Chat Vercel Ai GatewayModel
  37. 37openai/gpt-5-mini1Lm Chat Vercel Ai GatewayModel
  38. 38SwitchSwitchLogic
  39. 39AI Agent1AgentModel
  40. 40Calendar AgentAgent ToolModel
  41. 41Gmail toolAgent ToolModel
  42. 42Task agentAgent ToolModel
  43. 43Research agentAgent ToolModel
  44. 44MongoDB Atlas Vector StoreVector Store Mongo DBAtlasModel
  45. 45Extract Memory InfoChain LlmModel
  46. 46AI AgentAgentModel
  47. 47Summarize ChatChain LlmModel
  48. 48MongoDB Atlas Vector Store2Vector Store Mongo DBAtlasModel
  49. 49MongoDB Atlas Vector Store1Vector Store Mongo DBAtlasModel
  50. 50Download mediaWhats AppService
  51. 51Typing....Http RequestService
  52. 52Send messageWhats AppService
  53. 53Check If Worth RememberingIfLogic
  54. 54Clean Prompt Text1CodeLogic
  55. 55HTTP Request5Http RequestService
  56. 56Code1CodeLogic
  57. 57send chat history to MongoDBHttp RequestService
  58. 58Edit Fields1SetLogic
  59. 59HTTP RequestHttp RequestService
  60. 60Analyze imageGoogle GeminiModel

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.