The flow
Starts it 2Model 6Logic 1Service 5
The steps in the order they run, from what starts it.
- 1LLM for message normalizationLm Chat Open AiModel
- 2LLM for triage agentLm Chat Open AiModel
- 3LLM for structured parsingLm Chat Open AiModel
- 4Run every minuteSchedule triggerStarts it
- 5Watch inbound Gmail messagesGmail triggerStarts it
- 6Universal intake normalizerInformation ExtractorModel
- 7Triage and prioritize requestAgentModel
- 8Parse triage JSONOutput Parser StructuredModel
- 9Fetch recent Slack messagesSlackService
- 10Skip already processed itemsData TableService
- 11Only high importance itemsFilterLogic
- 12Create Notion ticketNotionService
- 13Store processed IDsData TableService
- 14Notify in SlackSlackService
How it's built
- Starts on
- A clock
- Steps
- 14
- Size
- Medium: a working afternoon
- Connects to
- Gmail, Notion, Slack, n8n data table
- Model
- OpenAI
Questions
What does it need to run?
An n8n account, plus your own Gmail, 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. 14 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.
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 14 steps before you point it at anything that matters.