Automation library · Scheduling

Automated multi-platform sales agent with Gemini

Started by an incoming WhatsApp message, and works across Google Calendar, Postgres and WhatsApp. It puts Gemini and OpenAI behind a retrieval step, so answers are drawn from documents you supply rather than from the model alone. 75 steps, 4 branches: large, and worth reading before you trust it with anything live.

LargeCalls a model: Gemini, OpenAIRetrieval

Download free
75 stepsLarge: read it before trusting it with anything live
4Branches: places the flow splits
0Loops or waits
3Services it connects to

The flow

Starts it 8Model 21Logic 5Service 26

The steps in the order they run, from what starts it. The first 60 of 75.

  1. 1Calendar AgentTool WorkflowModel
  2. 2CRM AgentTool WorkflowModel
  3. 3Postgres Chat MemoryMemory Postgres ChatModel
  4. 4Reply To User1Whats AppService
  5. 5Reply To UserWhats AppService
  6. 6WhatsAppWhats App triggerStarts it
  7. 7WhatsApp Business CloudWhats AppService
  8. 8Output - chatSetLogic
  9. 9When chat message receivedChat triggerStarts it
  10. 10Google Gemini Chat ModelLm Chat Google GeminiModel
  11. 11Google Gemini Chat Model1Lm Chat Google GeminiModel
  12. 12Embeddings Google Gemini1Embeddings Google GeminiModel
  13. 13Simple MemoryMemory Buffer WindowModel
  14. 14Create ChargeStripe ToolService
  15. 15Create Discount CouponStripe ToolService
  16. 16Get Customer CardStripe ToolService
  17. 17Get CustomerStripe ToolService
  18. 18Create CustomerStripe ToolService
  19. 19Update CustomerStripe ToolService
  20. 20Delete CustomerStripe ToolService
  21. 21Google Gemini Chat Model4Lm Chat Google GeminiModel
  22. 22Billing AgentTool WorkflowModel
  23. 23Facebook TriggerWebhookStarts it
  24. 24Instagram TriggerWebhookStarts it
  25. 25Instagram Graph API - smb.sales.agent.demoHttp RequestService
  26. 26GeminiLm Chat Google GeminiModel
  27. 27Contact FormForm triggerStarts it
  28. 28When Executed by Another WorkflowExecute Workflow triggerStarts it
  29. 29Window Buffer MemoryMemory Buffer WindowModel
  30. 30Create Event with AttendeeGoogle Calendar ToolService
  31. 31Create EventGoogle Calendar ToolService
  32. 32Get EventsGoogle Calendar ToolService
  33. 33Delete EventGoogle Calendar ToolService
  34. 34Update EventGoogle Calendar ToolService
  35. 35Google Gemini Chat Model2Lm Chat Google GeminiModel
  36. 36Create OpportunityPostgres ToolService
  37. 37List RecordsPostgres ToolService
  38. 38Update ContactPostgres ToolService
  39. 39Delete ContactPostgres ToolService
  40. 40Delete OpportunityPostgres ToolService
  41. 41Update OpportunityPostgres ToolService
  42. 42Google Gemini Chat Model3Lm Chat Google GeminiModel
  43. 43Create ContactPostgres ToolService
  44. 44AI AgentAgentModel
  45. 45Get LeadPostgresService
  46. 46HTTP RequestHttp RequestService
  47. 47Edit Fields - chatSetLogic
  48. 48technical_and_sales_knowledgeTool Vector StoreModel
  49. 49Postgres PGVector StoreVector Store PGVectorModel
  50. 50Billing Agent1AgentModel
  51. 51Respond to Webhook - facebook postRespond To WebhookStarts it
  52. 52Respond to Webhook - instagram postRespond To WebhookStarts it
  53. 53Personalised First MessageAgentModel
  54. 54Create Contact1PostgresService
  55. 55CRM Agent2AgentModel
  56. 56Calendar Agent1AgentModel
  57. 57Switch1SwitchLogic
  58. 58Handle Message TypesSwitchLogic
  59. 59OpenAIOpen AiModel
  60. 60No Operation, do nothingNo OpLogic

How it's built

Starts on
An incoming WhatsApp message
Steps
75, with 4 branches
Size
Large: read it before trusting it with anything live
Connects to
Google Calendar, Postgres, WhatsApp
Model
Gemini, OpenAI
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 Google Calendar, Postgres and WhatsApp accounts, and a key for Gemini and OpenAI. 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 and OpenAI. 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 75 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 75 steps before you point it at anything that matters.