Workflow n8n
Automatisation n8n : conversation multi-agent en temps réel
- Ce workflow n8n permet d'automatiser des conversations multi-agents en temps réel, offrant ainsi une solution innovante pour les entreprises cherchant à améliorer leur interaction avec les clients. Dans un contexte où la communication instantanée est cruciale, ce workflow s'avère particulièrement utile pour les équipes de support client, les plateformes de chat en ligne, ou toute entreprise souhaitant intégrer une intelligence artificielle dans ses échanges. L'automatisation n8n permet de gérer les messages entrants, d'extraire des mentions et de formuler des réponses adaptées grâce à des agents intelligents.
- Le processus débute avec le déclencheur 'When chat message received', qui active le workflow dès qu'un message est reçu. Ensuite, l'agent AI est chargé d'analyser le message et de générer une réponse appropriée. Les messages sont ensuite traités en lots grâce au noeud 'Loop Over Items', permettant une gestion efficace des conversations. Des étapes intermédiaires, telles que l'extraction des mentions et la définition des paramètres globaux et de l'agent, garantissent que chaque interaction est personnalisée et pertinente. Enfin, les réponses sont combinées et formatées avant d'être renvoyées à l'utilisateur.
- En intégrant ce workflow, les entreprises peuvent réduire le temps de réponse, améliorer la satisfaction client et optimiser l'efficacité de leurs équipes. La valeur ajoutée réside dans la capacité à offrir une expérience utilisateur fluide et réactive, tout en allégeant la charge de travail des agents humains.
Tags clés :automatisationchatbotn8nintelligence artificiellesupport client
Catégorie: Webhook · Tags: automatisation, chatbot, n8n, intelligence artificielle, support client❤ 0
Workflow n8n chatbot, intelligence artificielle, support client : vue d'ensemble
Schéma des nœuds et connexions de ce workflow n8n, généré à partir du JSON n8n.
Workflow n8n chatbot, intelligence artificielle, support client : détail des nœuds
Inscris-toi pour voir l'intégralité du workflow
Inscription gratuite
S'inscrire gratuitementBesoin d'aide ?{
"id": "0QQxgdQABUbbDJ0G",
"meta": {
"instanceId": "c98909b50b05c4069bd93ee5a4753d07322c9680e81da8568e96de2c713adb5c"
},
"name": "Multi-Agent Conversation",
"tags": [],
"nodes": [
{
"id": "218308e2-dc68-43ee-ae84-d931ad7a4ac5",
"name": "When chat message received",
"type": "@n8n/n8n-nodes-langchain.chatTrigger",
"position": [
-1880,
-3280
],
"webhookId": "a74752f3-419a-4510-856f-3efeaceec019",
"parameters": {
"options": {}
},
"typeVersion": 1.1
},
{
"id": "a519fe1e-8739-46e0-9770-deb256ab96cf",
"name": "AI Agent",
"type": "@n8n/n8n-nodes-langchain.agent",
"position": [
-340,
-3280
],
"parameters": {
"text": "={{ $json.chatInput }}",
"options": {
"systemMessage": "=Current date is {{ $now.format('yyyy-MM-dd') }}. The current time is {{ $now.format('HH:MM:ss') }}.\n\nThe user is {{ $('Define Global Settings').item.json.user.name }}, based in {{ $('Define Global Settings').item.json.user.location }}. {{ $('Define Global Settings').item.json.user.notes }}\n\nYou are part of a conversation with a user and multiple AI Assistants: {{ $('Define Agent Settings').item.json.keys() }}\n\nYou are {{ $('First loop?').item.json.name }}.\n\n{{ $('Loop Over Items').item.json.systemMessage }}\n\n{{ $('Define Global Settings').item.json.global.systemMessage }}"
},
"promptType": "define"
},
"typeVersion": 1.8
},
{
"id": "2e00f0ff-e7af-45d5-99bc-23031b5d7892",
"name": "Loop Over Items",
"type": "n8n-nodes-base.splitInBatches",
"position": [
-1000,
-3280
],
"parameters": {
"options": {}
},
"typeVersion": 3
},
{
"id": "1c979a20-46a5-4591-92da-82c1c96277c6",
"name": "Extract mentions",
"type": "n8n-nodes-base.code",
"position": [
-1220,
-3280
],
"parameters": {
"jsCode": "// Analyzes the user message and extracts @mentions in the order they appear. If there are none, all Assistants will be called in random order.\n// --- Configuration: Adjust these lines ---\nconst chatMessageNodeName = 'When chat message received'; // <-- Replace with your Chat Message node name\nconst agentSetupNodeName = 'Define Agent Settings'; // <-- Replace with your Agent Setup node name\nconst chatTextPath = 'json.chatInput'; // <-- Replace with path to text in Chat node output (e.g., 'json.message')\n// --- End Configuration ---\n\n// Helper function for safe nested property access (alternative to _.get)\nfunction getSafe(obj, path, defaultValue = undefined) {\n const pathParts = path.split('.');\n let current = obj;\n for (const part of pathParts) {\n if (current === null || current === undefined || typeof current !== 'object' || !Object.prototype.hasOwnProperty.call(current, part)) {\n return defaultValue;\n }\n current = current[part];\n }\n return current ?? defaultValue;\n}\n\n// 1. Get Chat Text\nconst chatMessageNode = $(chatMessageNodeName);\nconst chatText = getSafe(chatMessageNode.item, chatTextPath, '');\n\n// 2. Get Agent Data and Names\nconst agentSetupNode = $(agentSetupNodeName);\nconst agentData = getSafe(agentSetupNode.item, 'json', {}); // e.g., { Chad: {...}, Gemma: {...}, Claude: {...} }\nconst agentNames = Object.keys(agentData);\n\n// 3. Find all mentions, their names, and their positions in the text\nconst foundMentions = [];\nif (chatText && agentNames.length > 0) {\n const escapeRegex = (s) => s.replace(/[-\\/\\\\^$*+?.()|[\\]{}]/g, '\\\\$&');\n const agentPatternPart = agentNames.map(escapeRegex).join('|');\n\n if (agentPatternPart) {\n const mentionPattern = new RegExp(`\\\\B@(${agentPatternPart})\\\\b`, 'gi');\n const matches = chatText.matchAll(mentionPattern);\n\n for (const match of matches) {\n const matchedNameCaseInsensitive = match[1];\n const matchIndex = match.index;\n const canonicalName = agentNames.find(name => name.toLowerCase() === matchedNameCaseInsensitive.toLowerCase());\n if (canonicalName) {\n foundMentions.push({ name: canonicalName, index: matchIndex });\n }\n }\n }\n}\n\n// 4. Sort the found mentions by their index (order of appearance)\nfoundMentions.sort((a, b) => a.index - b.index);\n\n// 5. Map the sorted mentions to the desired output format (array of agent detail objects)\nlet outputArray = foundMentions.map(mention => {\n const agentDetails = agentData[mention.name];\n if (!agentDetails) {\n console.warn(`Could not find details for agent: ${mention.name}`);\n return null;\n }\n return {\n name: agentDetails.name,\n model: agentDetails.model,\n systemMessage: agentDetails.systemMessage\n };\n}).filter(item => item !== null);\n\n// 6. Check if any mentions were specifically found. If not, populate outputArray with ALL agents in RANDOM order.\nif (outputArray.length === 0 && foundMentions.length === 0) { // Check if NO mentions were found initially\n // --- NO MENTIONS FOUND ---\n // Populate outputArray with ALL agents from agentData\n const allAgentDetailsArray = Object.values(agentData);\n\n // --- Simple Randomization ---\n // Shuffle the array in place using sort with a random comparator\n allAgentDetailsArray.sort(() => 0.5 - Math.random());\n // --- End Randomization ---\n\n // Map all agents (now in random order) to the output structure\n outputArray = allAgentDetailsArray.map(agentObject => ({\n name: agentObject.name,\n model: agentObject.model,\n systemMessage: agentObject.systemMessage\n }));\n} // Intentionally no 'else' here, if outputArray already had items from mentions, we use that.\n\n// 7. Final Output Formatting (Handles both cases: specific mentions OR all agents)\n// Check if, after everything, the outputArray is *still* empty (e.g., if agentData was empty initially)\nif (outputArray.length === 0) {\n // If still empty, return a status or error as a fallback\n return [{ json: { status: \"no_agents_available\", message: \"No mentions found and no agents defined.\" } }];\n} else {\n // Return the array of agent objects formatted for n8n (multiple items)\n return outputArray.map(agentObject => ({ json: agentObject }));\n}"
},
"typeVersion": 2
},
{
"id": "45f635ca-f4fa-4f6c-a32a-9722906255fd",
"name": "Simple Memory",
"type": "@n8n/n8n-nodes-langchain.memoryBufferWindow",
"position": [
-192,
-3060
],
"parameters": {
"sessionKey": "={{ $('When chat message received').first().json.sessionId }}",
"sessionIdType": "customKey",
"contextWindowLength": 99
},
"typeVersion": 1.3
},
{
"id": "5c903044-bce2-4aa8-b168-a460a4999c54",
"name": "Set last Assistant message as input",
"type": "n8n-nodes-base.set",
"position": [
-560,
-3180
],
"parameters": {
"options": {},
"assignments": {
"assignments": [
{
"id": "38aa959a-e1e5-4c84-a7bd-ff5e0f61b62d",
"name": "=chatInput",
"type": "string",
"value": "={{ $('Set lastAssistantMessage').first().json.lastAssistantMessage }}"
}
]
}
},
"typeVersion": 3.4
},
{
"id": "7b389b9f-1751-4bc1-9c6f-bf6a04a1e09f",
"name": "Set user message as input",
"type": "n8n-nodes-base.set",
"position": [
-560,
-3380
],
"parameters": {
"options": {},
"assignments": {
"assignments": [
{
"id": "75b61275-7526-4431-b624-f8e098aa812d",
"name": "chatInput",
"type": "string",
"value": "={{ $('When chat message received').item.json.chatInput }}"
}
]
}
},
"typeVersion": 3.4
},
{
"id": "a238817f-0d10-4cd4-9760-53f69bb179f7",
"name": "First loop?",
"type": "n8n-nodes-base.if",
"position": [
-780,
-3280
],
"parameters": {
"options": {},
"conditions": {
"options": {
"version": 2,
"leftValue": "",
"caseSensitive": true,
"typeValidation": "strict"
},
"combinator": "and",
"conditions": [
{
"id": "51c41fdf-f4d3-4c7a-ac18-06815a59a958",
"operator": {
"type": "number",
"operation": "equals"
},
"leftValue": "={{ $runIndex}}",
"rightValue": 0
}
]
}
},
"typeVersion": 2.2
},
{
"id": "415927d7-b1a4-42b2-9607-c6ff707a528b",
"name": "Set lastAssistantMessage",
"type": "n8n-nodes-base.set",
"position": [
36,
-3155
],
"parameters": {
"options": {},
"assignments": {
"assignments": [
{
"id": "b93025b2-f5a7-476b-bd09-b5b4af050e73",
"name": "lastAssistantMessage",
"type": "string",
"value": "=**{{ $('Loop Over Items').item.json.name }}**:\n\n{{ $json.output }}"
}
]
}
},
"typeVersion": 3.4
},
{
"id": "77861e4b-a1d2-4c35-bf50-15914602a8b5",
"name": "Combine and format responses",
"type": "n8n-nodes-base.code",
"position": [
-780,
-3480
],
"parameters": {
"jsCode": "// Get the array of items from the input (output of the loop)\nconst inputItems = items;\n\n// Extract the 'lastAssistantMessage' from each item's JSON data.\n// If the field is missing or not a string, use an empty string to avoid errors.\nconst messages = inputItems.map(item => {\n const message = item.json.lastAssistantMessage;\n return typeof message === 'string' ? message : '';\n});\n\n// Join the extracted messages together with a horizontal rule separator\nconst combinedText = messages.join('\\n\\n---\\n\\n');\n\n// Return a new single item containing the combined text.\n// You can rename 'output' if you like.\nreturn [{ json: { output: combinedText } }];"
},
"typeVersion": 2
},
{
"id": "4da2f95d-bce4-4844-a23c-63ca777efbfd",
"name": "Define Global Settings",
"type": "n8n-nodes-base.code",
"position": [
-1660,
-3280
],
"parameters": {
"jsCode": "// Configure Global settings. This includes information about you - the user - and a section of the System Message that all Assistants will see. (Assistant-specific System Message sections can be set in the 'Define Agent Settings' node.)\nreturn [\n {\n json: {\n \"user\": {\n \"name\": \"Jon\",\n \"location\": \"Melbourne, Australia\",\n \"notes\": \"Jon likes a casual, informal conversation style.\"\n },\n \"global\": {\n \"systemMessage\": \"Don't overdo the helpful, agreeable approach.\"\n }\n }\n }\n];\n"
},
"typeVersion": 2
},
{
"id": "6639a554-9e5f-40ac-b68e-b8eaa777252d",
"name": "Define Agent Settings",
"type": "n8n-nodes-base.code",
"position": [
-1440,
-3280
],
"parameters": {
"jsCode": "// Configure Assistants. The number of Assistants can be changed by adding or removing JSON objects. Use the OpenRouter model naming convention.\nreturn [\n {\n json: {\n \"Chad\": {\n \"name\": \"Chad\",\n \"model\": \"openai/gpt-4o\",\n \"systemMessage\": \"You are a helpful Assistant. You are eccentric and creative, and try to take discussions into unexpected territory.\"\n },\n \"Claude\": {\n \"name\": \"Claude\",\n \"model\": \"anthropic/claude-3.7-sonnet\",\n \"systemMessage\": \"You are logical and practical.\"\n },\n \"Gemma\": {\n \"name\": \"Gemma\",\n \"model\": \"google/gemini-2.0-flash-lite-001\",\n \"systemMessage\": \"You are super friendly and love to debate.\"\n }\n }\n }\n];\n"
},
"typeVersion": 2
},
{
"id": "d55a7e02-3574-4d78-a141-db8d3657857b",
"name": "Sticky Note",
"type": "n8n-nodes-base.stickyNote",
"position": [
-1750,
-3620
],
"parameters": {
"color": 4,
"width": 500,
"height": 500,
"content": "## Step 1: Configure Settings Nodes\n\nEdit the JSON in these nodes to:\n\n- Configure details about you (the user)\n- Define content that will appear in all system messages\n- Define Agents.\n\nFor Agents, you can configure:\n- How many you create\n- Their names\n- The LLM model they use (choose any that are available via OpenRouter)\n- Agent-specific system prompt content"
},
"typeVersion": 1
},
{
"id": "d3eb2797-4008-4bdb-a588-b2412ed5ffa7",
"name": "Sticky Note1",
"type": "n8n-nodes-base.stickyNote",
"position": [
-400,
-3620
],
"parameters": {
"color": 4,
"width": 360,
"height": 720,
"content": "## Step 2: Connect Agent to OpenRouter\n\nSet your OpenRouter credentials, and all other parameters including system messages and model selection are dynamically populated."
},
"typeVersion": 1
},
{
"id": "a6085a55-db36-42d8-8c57-c9123490581f",
"name": "Sticky Note2",
"type": "n8n-nodes-base.stickyNote",
"position": [
-1940,
-3900
],
"parameters": {
"color": 5,
"width": 2180,
"height": 1100,
"content": "# Scalable Multi-Agent Conversations\n\n"
},
"typeVersion": 1
},
{
"id": "d2ee6317-3a9c-4df8-8fce-87daa3530233",
"name": "Sticky Note3",
"type": "n8n-nodes-base.stickyNote",
"position": [
-1200,
-3860
],
"parameters": {
"width": 380,
"height": 360,
"content": "## About this workflow\n\n**What does this workflow do?**\nEnables you to initiate a conversation with multiple AI agents at once. Each agent can be configured with a unique name, system instructions, a different model.\n\n**How do I use it?**\n1. Configure the settings nodes to create the Agents you need.\n2. Call one or more individual agents using @Name mentions in your messages. If your message does not have @mentions, all agents will be called, in random order."
},
"typeVersion": 1
},
{
"id": "a190a268-7f90-4c4e-aceb-482545d0b72b",
"name": "Sticky Note4",
"type": "n8n-nodes-base.stickyNote",
"position": [
-820,
-3860
],
"parameters": {
"width": 380,
"height": 360,
"content": "**How does it work?**\nSettings are configured in the first two nodes after the chat trigger. Then @mentions in your message are extracted and fed into a loop. With each loop, the agent's system message and model are dynamically populated, avoiding the need to create multiple agent nodes and complex routing logic.\n\nWhen all agents have had their say, their responses are combined and formatted. The use of a shared memory node enables multi-round conversations.\n\n**What are the limitations?**\nAgents cannot call each other or respond in parallel. Agents' responses are not visible to the user until all agents have responded.\n\n"
},
"typeVersion": 1
},
{
"id": "30d8c207-9a7a-46c5-be89-0deafc6c183f",
"name": "OpenRouter Chat Model",
"type": "@n8n/n8n-nodes-langchain.lmChatOpenRouter",
"position": [
-312,
-3060
],
"parameters": {
"model": "={{ $('Extract mentions').item.json.model }}",
"options": {}
},
"credentials": {
"openRouterApi": {
"id": "jB56IT6KRdHSBbkw",
"name": "OpenRouter account"
}
},
"typeVersion": 1
}
],
"active": false,
"pinData": {},
"settings": {
"executionOrder": "v1"
},
"versionId": "6c0312e7-7a81-41cd-9403-8ad947100b80",
"connections": {
"AI Agent": {
"main": [
[
{
"node": "Set lastAssistantMessage",
"type": "main",
"index": 0
}
]
]
},
"First loop?": {
"main": [
[
{
"node": "Set user message as input",
"type": "main",
"index": 0
}
],
[
{
"node": "Set last Assistant message as input",
"type": "main",
"index": 0
}
]
]
},
"Simple Memory": {
"ai_memory": [
[
{
"node": "AI Agent",
"type": "ai_memory",
"index": 0
}
]
]
},
"Loop Over Items": {
"main": [
[
{
"node": "Combine and format responses",
"type": "main",
"index": 0
}
],
[
{
"node": "First loop?",
"type": "main",
"index": 0
}
]
]
},
"Extract mentions": {
"main": [
[
{
"node": "Loop Over Items",
"type": "main",
"index": 0
}
]
]
},
"Define Agent Settings": {
"main": [
[
{
"node": "Extract mentions",
"type": "main",
"index": 0
}
]
]
},
"OpenRouter Chat Model": {
"ai_languageModel": [
[
{
"node": "AI Agent",
"type": "ai_languageModel",
"index": 0
}
]
]
},
"Define Global Settings": {
"main": [
[
{
"node": "Define Agent Settings",
"type": "main",
"index": 0
}
]
]
},
"Set lastAssistantMessage": {
"main": [
[
{
"node": "Loop Over Items",
"type": "main",
"index": 0
}
]
]
},
"Set user message as input": {
"main": [
[
{
"node": "AI Agent",
"type": "main",
"index": 0
}
]
]
},
"When chat message received": {
"main": [
[
{
"node": "Define Global Settings",
"type": "main",
"index": 0
}
]
]
},
"Combine and format responses": {
"main": [
[]
]
},
"Set last Assistant message as input": {
"main": [
[
{
"node": "AI Agent",
"type": "main",
"index": 0
}
]
]
}
}
}Workflow n8n chatbot, intelligence artificielle, support client : pour qui est ce workflow ?
Ce workflow s'adresse aux entreprises de toutes tailles souhaitant intégrer des solutions d'intelligence artificielle dans leur service client. Il est particulièrement adapté pour les équipes techniques et les responsables de l'expérience client, qui recherchent des moyens d'améliorer l'efficacité de leurs interactions avec les utilisateurs.
Workflow n8n chatbot, intelligence artificielle, support client : problème résolu
Ce workflow résout le problème de la lenteur et de l'inefficacité des réponses aux demandes des clients. En automatisant le processus de réponse, il élimine les frustrations liées aux temps d'attente et réduit le risque d'erreurs humaines. Les utilisateurs bénéficient ainsi d'une interaction instantanée et personnalisée, ce qui améliore leur satisfaction et fidélité.
Workflow n8n chatbot, intelligence artificielle, support client : étapes du workflow
Étape 1 : Le workflow est déclenché par la réception d'un message via le noeud 'When chat message received'.
- Étape 1 : L'agent AI analyse le message et génère une réponse.
- Étape 2 : Les messages sont traités en lots grâce au noeud 'Loop Over Items'.
- Étape 3 : Les mentions sont extraites pour personnaliser les réponses.
- Étape 4 : Les paramètres globaux et de l'agent sont définis pour garantir la pertinence des réponses.
- Étape 5 : Les réponses sont combinées et formatées avant d'être envoyées à l'utilisateur.
Workflow n8n chatbot, intelligence artificielle, support client : guide de personnalisation
Pour personnaliser ce workflow, vous pouvez modifier les paramètres du noeud 'When chat message received' pour l'adapter à votre plateforme de chat. Il est également possible de personnaliser les réponses générées par l'agent AI en ajustant les paramètres dans le noeud 'AI Agent'. Pensez à adapter les conditions dans le noeud 'First loop?' pour gérer les différentes situations de conversation. Enfin, vous pouvez ajouter ou retirer des noeuds selon vos besoins spécifiques, tout en veillant à tester le flux pour garantir son bon fonctionnement.