Automation library · Content

Generate Gmail reply drafts with OpenAI and Postgres

Started by an arriving email, and works across Gmail and Postgres. It puts OpenAI behind a retrieval step, so answers are drawn from documents you supply rather than from the model alone. 22 steps, 1 branch: large, and worth reading before you trust it with anything live.

LargeCalls a model: OpenAIRetrieval

22 stepsLarge: read it before trusting it with anything live
1Branch: places the flow splits
0Loops or waits
2Services it connects to

The flow

Starts it 1Model 4Logic 8Service 9

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

  1. 1OpenAI Chat ModelLm Chat Open AiModel
  2. 2Simple MemoryMemory Buffer WindowModel
  3. 3Gmail TriggerGmail triggerStarts it
  4. 4AI Agent - ClassifyAgentModel
  5. 5Parse & ValidateCodeLogic
  6. 6MergeMergeLogic
  7. 7IF ValidIfLogic
  8. 8Parse ClassificationCodeLogic
  9. 9DB - Log SkippedPostgresService
  10. 10Generate Email EmbeddingHttp RequestService
  11. 11Extract EmbeddingCodeLogic
  12. 12DB - Fetch KB DataPostgresService
  13. 13DB - Fetch Similar CorrectionsPostgresService
  14. 14DB - Fetch Similar ScenariosPostgresService
  15. 15DB - Fetch Customer TransactionsPostgresService
  16. 16Resolve ScenarioCodeLogic
  17. 17Assemble Draft PromptCodeLogic
  18. 18Generate DraftOpen AiModel
  19. 19Extract Draft TextCodeLogic
  20. 20Create Gmail DraftGmailService
  21. 21DB - Save AI DraftPostgresService
  22. 22DB - Log SuccessPostgresService

How it's built

Starts on
An arriving email
Steps
22, with 1 branch
Size
Large: read it before trusting it with anything live
Connects to
Gmail, Postgres
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 Gmail and Postgres accounts, and a key for OpenAI. You connect your own accounts after importing it; none are included.

What starts it?

It starts on an arriving email.

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?

Take your time. At 22 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 22 steps before you point it at anything that matters.