Triage Slack and Gmail requests with an AI-powered intake layer
Ready for 3.0What this workflow does
This AI workflow has 14 nodes and runs on a schedule (every minute) (plus 1 other trigger). Along the way it connects OpenAI Chat Model, Slack, Gmail and Notion.
How it runs
Trigger: On a schedule (every minute) (plus 1 other trigger).
- Fetch recent Slack messages (Slack): get (channel)
- Universal intake normalizer (Information Extractor): extracts structured fields from text with AI, with model: LLM for message normalization
- Skip already processed items (Data table): row not exists
- Store processed IDs (Data table): uses Data table
- Triage and prioritize request (AI Agent): runs an AI agent, with model: LLM for triage agent; output parser: Parse triage JSON
- Only high importance items (Filter): keeps only the items that match a condition
- Create Notion ticket (Notion): work with database page
- Notify in Slack (Slack): uses Slack
Services it uses
Before you upgrade to n8n 3.0
Nothing in this workflow is removed in n8n 3.0, so it should import and run after the upgrade.
- Still check Gmail Trigger below v1.4 runs as v1.4 (drafts skipped, max emails per poll) (Watch inbound Gmail messages).
Nodes used (10)
- OpenAI Chat Model
@n8n/n8n-nodes-langchain.lmChatOpenAi - Structured Output Parser
@n8n/n8n-nodes-langchain.outputParserStructured - Slack
n8n-nodes-base.slack - Schedule Trigger
n8n-nodes-base.scheduleTrigger - Gmail Trigger
n8n-nodes-base.gmailTrigger - Data table
n8n-nodes-base.dataTable - AI Agent
@n8n/n8n-nodes-langchain.agent - Notion
n8n-nodes-base.notion - Filter
n8n-nodes-base.filter - Information Extractor
@n8n/n8n-nodes-langchain.informationExtractor
From the author
This n8n template helps you turn inbound messages into a clean, deduped queue of actionable tickets. It includes Slack and Gmail as ready to use examples, but the key idea is the universal intake normalizer: you can plug in other sources later (forms,…