Automation library · Chat assistants

Edit Google Sheets by chat with OpenAI

Started by someone opening a chat with it, and works across Google Sheets and Telegram. It puts OpenAI behind a retrieval step, so answers are drawn from documents you supply rather than from the model alone. 18 steps, 3 branches: a working afternoon to understand properly.

MediumCalls a model: OpenAIRetrieval

18 stepsMedium: a working afternoon
3Branches: places the flow splits
0Loops or waits
2Services it connects to

The flow

Starts it 1Model 3Logic 9Service 5

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

  1. 1When You Ask About the SheetChat triggerStarts it
  2. 2Assistant ModelLm Chat Open AiModel
  3. 3Conversation MemoryMemory Buffer WindowModel
  4. 4Read the Sheet for AnswersGoogle Sheets ToolService
  5. 5Spreadsheet AssistantAgentModel
  6. 6Check the Proposed Change Is SafeCodeLogic
  7. 7Is It a Change Request?IfLogic
  8. 8Read the Row as It Is NowGoogle SheetsService
  9. 9Answer the Question in ChatNo OpLogic
  10. 10Build the Before-and-After PreviewCodeLogic
  11. 11Is There Anything Left to Change?IfLogic
  12. 12Ask You to Confirm the ChangeTelegramService
  13. 13Explain Why Nothing ChangedNo OpLogic
  14. 14Did You Approve It?IfLogic
  15. 15Prepare the Row UpdateCodeLogic
  16. 16Discard the Proposed ChangeNo OpLogic
  17. 17Apply the Approved ChangeGoogle SheetsService
  18. 18Log the Change to the Audit TrailGoogle SheetsService

How it's built

Starts on
Someone opening a chat with it
Steps
18, with 3 branches
Size
Medium: a working afternoon
Connects to
Google Sheets, Telegram
Model
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 Sheets and Telegram accounts, and a key for 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 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.