Automation library · Customer support

Personalized AI assistant with Claude and OpenAI

Started by someone opening a chat with it, and works across Airtable, Gmail, Google Calendar and Telegram. It puts Claude and OpenAI behind a retrieval step, so answers are drawn from documents you supply rather than from the model alone. 18 steps, 1 branch: a working afternoon to understand properly.

MediumCalls a model: Claude, OpenAIRetrieval

18 stepsMedium: a working afternoon
1Branch: places the flow splits
0Loops or waits
4Services it connects to

The flow

Starts it 1Model 9Logic 2Service 6

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

  1. 1OpenAI Chat ModelLm Chat Open AiModel
  2. 2SerpAPITool Serp ApiModel
  3. 3ContactsAirtable ToolService
  4. 4CalculatorTool CalculatorModel
  5. 5Anthropic Chat ModelLm Chat AnthropicModel
  6. 6Get CalendarGoogle Calendar ToolService
  7. 7Hacker NewsHacker News ToolService
  8. 8When chat message receivedChat triggerStarts it
  9. 9Simple MemoryMemory Buffer WindowModel
  10. 10Get many messages in GmailGmail ToolService
  11. 11Search files and folders in Google DriveGoogle Drive ToolService
  12. 12WikipediaTool WikipediaModel
  13. 13AI Agent - NovaAgentModel
  14. 14Basic LLM ChainChain LlmModel
  15. 15SwitchSwitchLogic
  16. 16Get a fileTelegramService
  17. 17Edit FieldsSetLogic
  18. 18Transcribe a recordingOpen AiModel

How it's built

Starts on
Someone opening a chat with it
Steps
18, with 1 branch
Size
Medium: a working afternoon
Connects to
Airtable, Gmail, Google Calendar, Telegram
Model
Claude, 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 Airtable, Gmail, Google Calendar and Telegram accounts, and a key for Claude and OpenAI. You connect your own accounts after importing it; none are included.

What starts it?

It starts on someone opening a chat with it.

Does it use AI?

Yes. It calls Claude 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?

Plan an afternoon. 18 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 18 steps before you point it at anything that matters.