Slack - Travail automatisé par IA
Ceci est unInternal Wiki, Multimodal AIworkflow d'automatisation du domainecontenant 10 nœuds.Utilise principalement des nœuds comme Slack, SlackTrigger, GoogleDocsTool, Agent, LmChatOpenAi. Répondre automatiquement aux messages Slack en utilisant GPT et RAG sur Google Docs
- •Token Bot Slack ou URL Webhook
- •Clé API OpenAI
Nœuds utilisés (10)
Catégorie
{
"id": "7MQLIwQsFOmnQV4n",
"meta": {
"instanceId": "16d5a69b6a4f4733c8f669903729902650204c895b060993271b9227d7b0b3e8",
"templateCredsSetupCompleted": true
},
"name": "Slack - Let AI Do Your Job",
"tags": [],
"nodes": [
{
"id": "c724b8ae-462f-4bb5-8e23-09dfe66e783b",
"name": "Déclencheur Slack",
"type": "n8n-nodes-base.slackTrigger",
"position": [
-96,
0
],
"parameters": {
"options": {
"userIds": "==[\"User_ID\"]"
},
"trigger": [
"any_event",
"app_mention"
],
"watchWorkspace": true
},
"typeVersion": 1
},
{
"id": "a15d59e3-4ada-418b-9cde-7dc8f713ecc9",
"name": "Modèle de chat OpenAI",
"type": "@n8n/n8n-nodes-langchain.lmChatOpenAi",
"position": [
112,
208
],
"parameters": {
"model": {
"__rl": true,
"mode": "list",
"value": "gpt-5",
"cachedResultName": "gpt-5"
},
"options": {}
},
"typeVersion": 1.2
},
{
"id": "0d87970d-9887-4ec4-ab10-3564310919cc",
"name": "Simple Mémoire",
"type": "@n8n/n8n-nodes-langchain.memoryBufferWindow",
"position": [
304,
208
],
"parameters": {
"sessionKey": "={{ $json.channel }}",
"sessionIdType": "customKey"
},
"typeVersion": 1.3
},
{
"id": "5ed06900-d13c-44f6-b763-5d9cd176db01",
"name": "Send a message",
"type": "n8n-nodes-base.slack",
"position": [
656,
0
],
"parameters": {
"text": "={{ $json.output }}",
"select": "channel",
"channelId": {
"__rl": true,
"mode": "id",
"value": "={{ $('Slack Trigger').item.json.channel }}"
},
"otherOptions": {
"sendAsUser": "Jacob",
"includeLinkToWorkflow": false
}
},
"typeVersion": 2.3
},
{
"id": "ff806d9b-f9bf-4071-aebc-be85b6bcf2d4",
"name": "Get a document in Google Docs",
"type": "n8n-nodes-base.googleDocsTool",
"position": [
480,
208
],
"parameters": {
"operation": "get",
"documentURL": "GOOGLE DOC ID OR URL"
},
"typeVersion": 2
},
{
"id": "9cce7ec0-c157-47a9-81df-0ebc08114287",
"name": "Note adhésive",
"type": "n8n-nodes-base.stickyNote",
"position": [
608,
-160
],
"parameters": {
"color": 3,
"width": 304,
"height": 624,
"content": "Slack Respond as a User"
},
"typeVersion": 1
},
{
"id": "bd66fe12-5532-4183-b641-71f6cadcc204",
"name": "Note adhésive1",
"type": "n8n-nodes-base.stickyNote",
"position": [
48,
-160
],
"parameters": {
"color": 4,
"width": 544,
"height": 624,
"content": "GPT-5 Agent"
},
"typeVersion": 1
},
{
"id": "cdd11d82-b9bf-435e-8bb1-208737b8c74b",
"name": "GPT 5 Slack Agent",
"type": "@n8n/n8n-nodes-langchain.agent",
"position": [
224,
0
],
"parameters": {
"text": "={{ $json.text }}",
"options": {
"systemMessage": "You are Jacob, a social media manager at Purple Unicorn Marketing Agency. Respond to your members' message on Jacob's behalf on Slack. Sound friendly and natural in a typical tech working environment. \n\n##Tool\nUse the Google Doc Tool when asked about Project Updates"
},
"promptType": "define"
},
"typeVersion": 2
},
{
"id": "faa86c34-10a7-47bd-b258-250e24bb6b9a",
"name": "Note adhésive2",
"type": "n8n-nodes-base.stickyNote",
"position": [
-208,
-160
],
"parameters": {
"color": 5,
"height": 624,
"content": "Slack Trigger"
},
"typeVersion": 1
},
{
"id": "44ae482d-d65a-4f05-be10-9948733394b8",
"name": "Note adhésive3",
"type": "n8n-nodes-base.stickyNote",
"position": [
-1024,
-160
],
"parameters": {
"width": 768,
"height": 1008,
"content": "💬 GPT-5 Slack Impersonation Agent with RAG – Auto-Respond to Messages Using Live Project Docs\n\nLet AI handle your Slack conversations — and always have the right answer.\nThis n8n workflow transforms GPT-5 into your on-brand Slack assistant, capable of responding as you in real-time while referencing a Google Docs RAG (Retrieval-Augmented Generation) document for accurate project updates.\n\nWatch step-by-step build like these on:\nhttps://www.youtube.com/@automatewithmarc\n\nHere’s how it works:\n\nListens for Slack mentions or messages — triggered instantly when someone talks to you.\n\nUnderstands the conversation context using GPT-5 and conversation memory.\n\nRetrieves the latest project updates from your linked Google Doc via RAG.\n\nResponds in Slack as you — maintaining your tone, style, and workplace personality.\n\nKey Features & Benefits:\n\n🧠 RAG-powered accuracy – Always pulls the latest info from your project docs.\n\n🤖 GPT-5 natural conversation – Replies feel human, friendly, and context-aware.\n\n⚡ Instant responses – No more message backlog or missed updates.\n\n🎯 Impersonation mode – Sends replies under your Slack name for seamless collaboration.\n\n🔄 Continuous conversation memory – Keeps track of what was said before.\n\nIdeal Use Cases:\n\nActing as a stand-in during busy periods so no message goes unanswered.\n\nProject managers who want instant, document-backed answers.\n\nCustomer support or client-facing roles needing quick, accurate replies.\n\nIncluded Integrations:\n\nSlack Trigger & Send Message – Listen and reply in real-time.\n\nGPT-5 Agent – Craft context-aware, on-brand responses.\n\nGoogle Docs Tool – Pull live data from your RAG document.\n\nConversation Memory – Maintain context across messages.\n\n💡 Pro Tip: Customize the system prompt to mimic your exact tone and integrate with multiple docs for broader knowledge coverage."
},
"typeVersion": 1
}
],
"active": false,
"pinData": {},
"settings": {
"executionOrder": "v1"
},
"versionId": "e58b3b27-0453-409e-91ce-61639cb188a7",
"connections": {
"Simple Memory": {
"ai_memory": [
[
{
"node": "cdd11d82-b9bf-435e-8bb1-208737b8c74b",
"type": "ai_memory",
"index": 0
}
]
]
},
"Slack Trigger": {
"main": [
[
{
"node": "cdd11d82-b9bf-435e-8bb1-208737b8c74b",
"type": "main",
"index": 0
}
]
]
},
"cdd11d82-b9bf-435e-8bb1-208737b8c74b": {
"main": [
[
{
"node": "5ed06900-d13c-44f6-b763-5d9cd176db01",
"type": "main",
"index": 0
}
]
]
},
"OpenAI Chat Model": {
"ai_languageModel": [
[
{
"node": "cdd11d82-b9bf-435e-8bb1-208737b8c74b",
"type": "ai_languageModel",
"index": 0
}
]
]
},
"ff806d9b-f9bf-4071-aebc-be85b6bcf2d4": {
"ai_tool": [
[
{
"node": "cdd11d82-b9bf-435e-8bb1-208737b8c74b",
"type": "ai_tool",
"index": 0
}
]
]
}
}
}Comment utiliser ce workflow ?
Copiez le code de configuration JSON ci-dessus, créez un nouveau workflow dans votre instance n8n et sélectionnez "Importer depuis le JSON", collez la configuration et modifiez les paramètres d'authentification selon vos besoins.
Dans quelles scénarios ce workflow est-il adapté ?
Intermédiaire - Wiki interne, IA Multimodale
Est-ce payant ?
Ce workflow est entièrement gratuit et peut être utilisé directement. Veuillez noter que les services tiers utilisés dans le workflow (comme l'API OpenAI) peuvent nécessiter un paiement de votre part.
Workflows recommandés
Automate With Marc
@marconiAutomating Start-Up and Business processes. Helping non-techies understand and leverage Agentic AI with easy to understand step-by-step tutorials. Check out my educational content: https://www.youtube.com/@Automatewithmarc
Partager ce workflow