The flow
Starts it 1Model 2Logic 4Service 6
The steps in the order they run, from what starts it.
- 1Every 4 hoursSchedule triggerStarts it
- 2OpenAI chat modelLm Chat Open AiModel
- 3Optional: email the questions insteadGmailService
- 4Optional: raise a ticket in your helpdeskHttp RequestService
- 5What to watch forSetLogic
- 6Work out what it needsChain LlmModel
- 7Search XApifyService
- 8Send it where it belongsSwitchLogic
- 9Keep mentions worth readingFilterLogic
- 10Questions to the reply queueNotionService
- 11Complaints straight to SlackSlackService
- 12Everything else just gets loggedGoogle SheetsService
- 13Skip ones already handledRemove DuplicatesLogic
How it's built
- Starts on
- A clock
- Steps
- 13, with 1 branch
- Size
- Medium: a working afternoon
- Connects to
- Apify, Gmail, Google Sheets, Notion, Slack
- Model
- OpenAI
Questions
What does it need to run?
An n8n account, plus your own Apify, Gmail, Google Sheets, Notion and Slack accounts, and a key for OpenAI. You connect your own accounts after importing it; none are included.
What starts it?
It starts on a clock.
Does it use AI?
Yes. It calls OpenAI. Model calls are billed by the provider, not by n8n.
How long does it take to set up?
Plan an afternoon. 13 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 itNothing 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 13 steps before you point it at anything that matters.