Paul Karrmann This workflow corresponds to n8n.io template #13180 — we link there as the canonical source.
This workflow follows the Agent → Datatable recipe pattern — see all workflows that pair these two integrations.
The workflow JSON
Copy or download the full n8n JSON below. Paste it into a new n8n workflow, add your credentials, activate. Full import guide →
{
"id": "d56BKcKZud3ENFsPn3BYS",
"name": "Triage requests from Slack and Gmail with a plug and play intake layer",
"tags": [],
"nodes": [
{
"id": "a47f4fcc-9504-4f2d-8a43-2fdb6580d1df",
"name": "LLM for message normalization",
"type": "@n8n/n8n-nodes-langchain.lmChatOpenAi",
"position": [
1008,
448
],
"parameters": {
"model": {
"__rl": true,
"mode": "list",
"value": "gpt-4.1-mini"
},
"options": {},
"builtInTools": {}
},
"typeVersion": 1.3
},
{
"id": "c45714d0-0805-49ab-af7f-57befcc7d38a",
"name": "LLM for triage agent",
"type": "@n8n/n8n-nodes-langchain.lmChatOpenAi",
"position": [
1760,
480
],
"parameters": {
"model": {
"__rl": true,
"mode": "list",
"value": "gpt-5.2",
"cachedResultName": "gpt-5.2"
},
"options": {},
"builtInTools": {}
},
"typeVersion": 1.3
},
{
"id": "c05ed7f5-fc0e-45e0-978f-d05cca2fc949",
"name": "Parse triage JSON",
"type": "@n8n/n8n-nodes-langchain.outputParserStructured",
"position": [
1888,
480
],
"parameters": {
"autoFix": true,
"schemaType": "manual",
"inputSchema": "{\n \"$schema\": \"https://json-schema.org/draft/2020-12/schema\",\n \"$id\": \"https://example.com/hr-triage.schema.json\",\n \"title\": \"HR Triage Classification Output\",\n \"type\": \"object\",\n \"additionalProperties\": false,\n \"required\": [\n \"ticket_title\",\n \"summary\",\n \"category\",\n \"eisenhower_quadrant\",\n \"urgency\",\n \"importance\",\n \"effort\",\n \"risk\",\n \"confidence\",\n \"should_create_ticket\",\n \"suggested_assignee_role\",\n \"suggested_due_date\",\n \"draft_reply\"\n ],\n \"properties\": {\n \"ticket_title\": {\n \"type\": \"string\",\n \"minLength\": 1,\n \"maxLength\": 90,\n \"description\": \"Short ticket title, ideally 6 to 10 words.\"\n },\n \"summary\": {\n \"type\": \"string\",\n \"minLength\": 1,\n \"maxLength\": 140,\n \"description\": \"Short summary, max about 20 words.\"\n },\n \"category\": {\n \"type\": \"string\",\n \"enum\": [\"Payroll\", \"Time off\", \"Contract\", \"Hiring\", \"IT\", \"Facilities\", \"Finance\", \"Other\"]\n },\n \"eisenhower_quadrant\": {\n \"type\": \"string\",\n \"enum\": [\"DoNow\", \"Plan\", \"Delegate\", \"Defer\"]\n },\n \"urgency\": {\n \"type\": \"integer\",\n \"minimum\": 0,\n \"maximum\": 10\n },\n \"importance\": {\n \"type\": \"integer\",\n \"minimum\": 0,\n \"maximum\": 10\n },\n \"effort\": {\n \"type\": \"integer\",\n \"minimum\": 0,\n \"maximum\": 10\n },\n \"risk\": {\n \"type\": \"integer\",\n \"minimum\": 0,\n \"maximum\": 10,\n \"description\": \"Risk includes legal, compliance, reputation, escalation potential.\"\n },\n \"confidence\": {\n \"type\": \"number\",\n \"minimum\": 0,\n \"maximum\": 1\n },\n \"should_create_ticket\": {\n \"type\": \"boolean\"\n },\n \"suggested_assignee_role\": {\n \"type\": \"string\",\n \"enum\": [\"HR Ops\", \"Recruiter\", \"People Lead\", \"IT\", \"Finance\"]\n },\n \"suggested_due_date\": {\n \"type\": \"string\",\n \"format\": \"date\",\n \"description\": \"ISO 8601 date, for example 2026-01-25.\"\n },\n \"draft_reply\": {\n \"type\": \"string\",\n \"minLength\": 1,\n \"maxLength\": 600,\n \"description\": \"One short reply suitable for Slack or email.\"\n }\n }\n}\n"
},
"typeVersion": 1.3
},
{
"id": "3f36efad-c273-406f-b14b-dcef692a84d2",
"name": "LLM for structured parsing",
"type": "@n8n/n8n-nodes-langchain.lmChatOpenAi",
"position": [
1888,
656
],
"parameters": {
"model": {
"__rl": true,
"mode": "list",
"value": "gpt-5.2",
"cachedResultName": "gpt-5.2"
},
"options": {},
"builtInTools": {}
},
"typeVersion": 1.3
},
{
"id": "9e078e3d-3947-4063-a819-bd9d1919843e",
"name": "Notify in Slack",
"type": "n8n-nodes-base.slack",
"position": [
2480,
160
],
"parameters": {
"text": "={{ $('Triage and prioritize request').item.json.output.summary }}",
"user": {
"__rl": true,
"mode": "list",
"value": "REPLACE_WITH_SLACK_USER_ID"
},
"select": "user",
"otherOptions": {},
"authentication": "oAuth2"
},
"typeVersion": 2.4
},
{
"id": "bd0bd87f-ffaf-477f-a695-ae2c5acfb18c",
"name": "Run every minute",
"type": "n8n-nodes-base.scheduleTrigger",
"position": [
320,
176
],
"parameters": {
"rule": {
"interval": [
{
"field": "minutes"
}
]
}
},
"typeVersion": 1.3
},
{
"id": "896e927d-47b1-408c-a32b-622bd8791678",
"name": "Fetch recent Slack messages",
"type": "n8n-nodes-base.slack",
"position": [
544,
176
],
"parameters": {
"options": {},
"resource": "channel",
"channelId": {
"__rl": true,
"mode": "list",
"value": ""
},
"operation": "get",
"authentication": "oAuth2"
},
"typeVersion": 2.4
},
{
"id": "221a8952-07aa-4c9a-91ab-110a0390bfad",
"name": "Watch inbound Gmail messages",
"type": "n8n-nodes-base.gmailTrigger",
"position": [
544,
368
],
"parameters": {
"simple": false,
"filters": {
"sender": ""
},
"options": {},
"pollTimes": {
"item": [
{
"mode": "everyMinute"
}
]
}
},
"typeVersion": 1.3
},
{
"id": "ac6b1a3c-221a-48f7-b653-3f01a013407e",
"name": "Skip already processed items",
"type": "n8n-nodes-base.dataTable",
"position": [
1312,
256
],
"parameters": {
"filters": {
"conditions": [
{
"keyName": "uniqueID",
"keyValue": "={{ $json.output.source_id + $json.output.source }}"
}
]
},
"operation": "rowNotExists",
"dataTableId": {
"__rl": true,
"mode": "list",
"value": ""
}
},
"typeVersion": 1.1
},
{
"id": "c34eef0e-60f9-4b90-8d3d-f078dde3a1b3",
"name": "Store processed IDs",
"type": "n8n-nodes-base.dataTable",
"position": [
1536,
256
],
"parameters": {
"columns": {
"value": {
"uniqueID": "={{ $json.output.source + $json.output.source_id }}"
},
"schema": [
{
"id": "uniqueID",
"type": "string",
"display": true,
"removed": false,
"readOnly": false,
"required": false,
"displayName": "uniqueID",
"defaultMatch": false
}
],
"mappingMode": "defineBelow",
"matchingColumns": [
"uniqueID"
],
"attemptToConvertTypes": false,
"convertFieldsToString": false
},
"options": {},
"dataTableId": {
"__rl": true,
"mode": "list",
"value": ""
}
},
"typeVersion": 1.1
},
{
"id": "f0cd3b01-eeb4-45f0-aefa-49e0e83183f5",
"name": "Triage and prioritize request",
"type": "@n8n/n8n-nodes-langchain.agent",
"position": [
1792,
256
],
"parameters": {
"text": "=Input item JSON: {{ JSON.stringify($('Universal intake normalizer').item.json.output) }}\n\nClassify it and return:\n\nsummary (max 20 words)\n\ncategory (Payroll, Time off, Contract, Hiring, IT, Facilities, Finance, Other)\n\neisenhower_quadrant (DoNow, Plan, Delegate, Defer)\n\nurgency 0-10\n\nimportance 0-10\n\neffort 0-10\n\nrisk 0-10\n\nconfidence 0-1\n\nshould_create_ticket true or false\n\nsuggested_assignee_role (HR Ops, Recruiter, People Lead, IT, Finance)\n\nsuggested_due_date (ISO date)\n\ndraft_reply (one short reply for Slack or email)\n\ntoday is {{ $now }}",
"options": {
"systemMessage": "System message\n\nYou are an HR operations triage assistant.\n\nYour job is to read a single inbound item and return structured JSON only.\n\nIf you are not confident, set confidence low and recommend human review.\n\nNever invent facts. Use only the given text."
},
"promptType": "define",
"hasOutputParser": true
},
"typeVersion": 3.1
},
{
"id": "117965c8-6d91-4366-bd5b-b5f30d275b06",
"name": "Create Notion ticket",
"type": "n8n-nodes-base.notion",
"position": [
2256,
352
],
"parameters": {
"simple": false,
"options": {},
"resource": "databasePage",
"databaseId": {
"__rl": true,
"mode": "list",
"value": "REPLACE_WITH_NOTION_DATABASE_ID"
},
"propertiesUi": {
"propertyValues": [
{
"key": "Description|rich_text",
"textContent": "={{ $json.output.summary }}"
},
{
"key": "Assignee Role|rich_text",
"textContent": "={{ $json.output.suggested_assignee_role }}"
},
{
"key": "confidence_score|number",
"numberValue": "={{ $json.output.confidence }}"
},
{
"key": "Due Date|date",
"date": "={{ $json.output.suggested_due_date }}"
},
{
"key": "effort|number",
"numberValue": "={{ $json.output.effort }}"
},
{
"key": "Helpful other things|rich_text",
"textContent": "={{ $json.output.draft_reply }}"
},
{
"key": "importance|number",
"numberValue": "={{ $json.output.importance }}"
},
{
"key": "risk|number",
"numberValue": "={{ $json.output.risk }}"
},
{
"key": "Status|status",
"statusValue": "Backlog"
},
{
"key": "urgency|number",
"numberValue": "={{ $json.output.urgency }}"
},
{
"key": "Priority|select",
"selectValue": "={{ $json.output.eisenhower_quadrant }}"
},
{
"key": "Name|title",
"title": "={{ $json.output.ticket_title }}"
}
]
}
},
"typeVersion": 2.2
},
{
"id": "80284d99-b8b0-4dba-abbd-943a7efa63e7",
"name": "Only high importance items",
"type": "n8n-nodes-base.filter",
"position": [
2256,
160
],
"parameters": {
"options": {},
"conditions": {
"options": {
"version": 3,
"leftValue": "",
"caseSensitive": true,
"typeValidation": "strict"
},
"combinator": "and",
"conditions": [
{
"id": "7620c1d1-cf9a-47ca-b451-c98154644b0e",
"operator": {
"type": "number",
"operation": "gt"
},
"leftValue": "={{ $json.output.importance }}",
"rightValue": 9
}
]
}
},
"typeVersion": 2.3
},
{
"id": "f6a969ab-16ba-4348-835d-2f5e78fb9828",
"name": "Main sticky note",
"type": "n8n-nodes-base.stickyNote",
"position": [
-352,
32
],
"parameters": {
"width": 528,
"height": 592,
"content": "## How it works\n* This workflow collects inbound requests from Slack and Gmail.\n* Each item is normalized into a consistent JSON structure.\n* A data table is used to dedupe items so the same request is not processed twice.\n* An AI agent classifies the request, scores urgency and importance, and suggests a reply.\n* A Notion ticket is created for tracking, and very important items can trigger a Slack alert.\n\nSafety note: This workflow sends content to LLMs. Keep third party terms in mind and avoid processing restricted or sensitive data.\n\n## Setup steps\n* Connect Slack, Gmail, Notion, and OpenAI credentials in n8n.\n* Select a Slack channel to read from and a Slack user to notify.\n* Point the Notion node to your own database and confirm the property names match.\n* Create or select a data table and map the uniqueID column.\n* Tune the filter threshold and consider truncating message text to control cost.\n\n## Extending\n* Just connect a trigger from any source at the beginning and connect to normalize node"
},
"typeVersion": 1
},
{
"id": "9b78ff76-f0b6-45c6-801d-02bbd336df26",
"name": "Group sticky note: Collect items",
"type": "n8n-nodes-base.stickyNote",
"position": [
240,
32
],
"parameters": {
"color": 7,
"width": 528,
"height": 560,
"content": "### Collect items\n* Schedule trigger polls a Slack channel.\n* Gmail trigger watches for new messages.\n* Configure the Slack channel and Gmail sender filter before enabling."
},
"typeVersion": 1
},
{
"id": "4a383452-73df-4d85-a7aa-113aa976ca4e",
"name": "Group sticky note: Extract content",
"type": "n8n-nodes-base.stickyNote",
"position": [
960,
64
],
"parameters": {
"color": 7,
"width": 704,
"height": 544,
"content": "### Normalize and dedupe\n* Normalizes sources into one schema.\n* Uses a data table to skip repeats.\n* Ensure the data table exists and has a uniqueID column.\n* Makes it possible to add a new source as plug-and-play"
},
"typeVersion": 1
},
{
"id": "255cabc3-d456-4e95-b312-cdab31ff4f1b",
"name": "Group sticky note: Analyze and send",
"type": "n8n-nodes-base.stickyNote",
"position": [
1696,
64
],
"parameters": {
"color": 7,
"width": 976,
"height": 736,
"content": "### Analyze and send\n* AI agent outputs structured fields.\n* Notion ticket is created for tracking.\n* Slack notification is sent only when the filter matches.\n* Adjust the importance threshold as needed."
},
"typeVersion": 1
},
{
"id": "1a8c48ce-65b9-4a00-a11e-6ffc9459072a",
"name": "Universal intake normalizer",
"type": "@n8n/n8n-nodes-langchain.informationExtractor",
"position": [
1008,
256
],
"parameters": {
"text": "={{ JSON.stringify($json) }}",
"options": {},
"schemaType": "fromJson",
"jsonSchemaExample": "{\n \"source\": \"gmail|slack|form|other\",\n \"source_id\": \"unique-id-from-source\",\n \"timestamp\": \"2026-01-25T10:15:00Z\",\n \"author\": {\n \"name\": \"\u2026\",\n \"handle\": \"\u2026\",\n \"email\": \"\u2026\"\n },\n \"context\": {\n \"channel\": \"\u2026\",\n \"thread_ts\": \"\u2026\",\n \"email_subject\": \"\u2026\"\n },\n \"text\": \"raw message text\",\n \"links\": [\"permalink or gmail thread url\"],\n \"attachments\": [\n {\"type\": \"file|image|pdf\", \"name\": \"\u2026\", \"url\": \"\u2026\"}\n ]\n}\n"
},
"typeVersion": 1.2
}
],
"active": false,
"settings": {
"availableInMCP": false,
"executionOrder": "v1"
},
"versionId": "52058187-82fd-4d8d-8c5b-51f9e99232bb",
"connections": {
"Run every minute": {
"main": [
[
{
"node": "Fetch recent Slack messages",
"type": "main",
"index": 0
}
]
]
},
"Parse triage JSON": {
"ai_outputParser": [
[
{
"node": "Triage and prioritize request",
"type": "ai_outputParser",
"index": 0
}
]
]
},
"Store processed IDs": {
"main": [
[
{
"node": "Triage and prioritize request",
"type": "main",
"index": 0
}
]
]
},
"LLM for triage agent": {
"ai_languageModel": [
[
{
"node": "Triage and prioritize request",
"type": "ai_languageModel",
"index": 0
}
]
]
},
"LLM for structured parsing": {
"ai_languageModel": [
[
{
"node": "Parse triage JSON",
"type": "ai_languageModel",
"index": 0
}
]
]
},
"Only high importance items": {
"main": [
[
{
"node": "Notify in Slack",
"type": "main",
"index": 0
}
]
]
},
"Fetch recent Slack messages": {
"main": [
[
{
"node": "Universal intake normalizer",
"type": "main",
"index": 0
}
]
]
},
"Universal intake normalizer": {
"main": [
[
{
"node": "Skip already processed items",
"type": "main",
"index": 0
}
]
]
},
"Skip already processed items": {
"main": [
[
{
"node": "Store processed IDs",
"type": "main",
"index": 0
}
]
]
},
"Watch inbound Gmail messages": {
"main": [
[
{
"node": "Universal intake normalizer",
"type": "main",
"index": 0
}
]
]
},
"LLM for message normalization": {
"ai_languageModel": [
[
{
"node": "Universal intake normalizer",
"type": "ai_languageModel",
"index": 0
}
]
]
},
"Triage and prioritize request": {
"main": [
[
{
"node": "Only high importance items",
"type": "main",
"index": 0
},
{
"node": "Create Notion ticket",
"type": "main",
"index": 0
}
]
]
}
}
}
Pro
For the full experience including quality scoring and batch install features for each workflow upgrade to Pro
About this workflow
This n8n template helps you turn inbound messages into a clean, deduped queue of actionable tickets.
Source: https://n8n.io/workflows/13180/ — original creator credit. Request a take-down →
Related workflows
Workflows that share integrations, category, or trigger type with this one. All free to copy and import.
This workflow automates end-to-end sustainability lifecycle management for corporate sustainability teams, ESG governance officers, and circular economy programme leads. It addresses the challenge of
Form Trigger, Agent, OpenAI Chat +11
This workflow automates end-to-end ESG (Environmental, Social, and Governance) sustainability reporting for enterprise sustainability teams, compliance officers, and green governance leads. It solves
Agent, OpenAI Chat, Output Parser Structured +12
This workflow automates semiconductor board-level reliability monitoring using AI agents. It targets reliability engineers, manufacturing teams, and quality analysts. The system collects capacity, his
Google Sheets, Agent, OpenAI Chat +10
This workflow automates procurement fraud detection and supplier compliance monitoring for organizations managing complex purchasing operations. Designed for procurement teams, audit departments, and
OpenAI Chat, Output Parser Structured, Agent +6
This workflow automates end-to-end recruitment operations for HR teams, talent acquisition specialists, and hiring managers facing high-volume candidate processing challenges. It solves the critical p
Agent, OpenAI Chat, Output Parser Structured +4