Automatisation Slack avec n8n : création de tickets intelligents
Ce workflow n8n a pour objectif d'automatiser la création de tickets dans un système de gestion de projet via Slack. En intégrant des outils comme OpenAI et des notes autocollantes, ce processus permet aux équipes de gagner du temps et d'améliorer leur efficacité. Les cas d'usage incluent la gestion des demandes des clients, le suivi des problèmes techniques, et l'organisation des tâches au sein des équipes. Le workflow débute par un déclencheur planifié qui active le processus à intervalles réguliers. Ensuite, les messages Slack sont récupérés pour identifier les demandes pertinentes. L'OpenAI Chat Model est utilisé pour analyser ces messages et générer des résumés ou des descriptions de tickets. Les informations sont ensuite structurées et vérifiées pour déterminer si un nouveau ticket doit être créé. Si c'est le cas, le ticket est généré automatiquement, ce qui élimine les erreurs humaines et réduit le temps de traitement. En intégrant cette automatisation n8n, les entreprises peuvent améliorer leur réactivité face aux demandes, optimiser leur flux de travail et garantir une meilleure satisfaction client.
Workflow n8n Slack, OpenAI, tickets : vue d'ensemble
Schéma des nœuds et connexions de ce workflow n8n, généré à partir du JSON n8n.
Workflow n8n Slack, OpenAI, tickets : détail des nœuds
Inscris-toi pour voir l'intégralité du workflow
Inscription gratuite
S'inscrire gratuitementBesoin d'aide ?{
"meta": {
"instanceId": "26ba763460b97c249b82942b23b6384876dfeb9327513332e743c5f6219c2b8e"
},
"nodes": [
{
"id": "2b3112a9-046e-4aae-8fcc-95bddf3bb02e",
"name": "Slack",
"type": "n8n-nodes-base.slack",
"position": [
828,
327
],
"parameters": {
"limit": 10,
"query": "in:#n8n-tickets has::ticket:",
"options": {},
"operation": "search"
},
"credentials": {
"slackApi": {
"id": "VfK3js0YdqBdQLGP",
"name": "Slack account"
}
},
"typeVersion": 2.2
},
{
"id": "65fd6821-4d19-436c-81d9-9bdb0f5efddd",
"name": "OpenAI Chat Model",
"type": "@n8n/n8n-nodes-langchain.lmChatOpenAi",
"position": [
1920,
480
],
"parameters": {
"options": {}
},
"credentials": {
"openAiApi": {
"id": "8gccIjcuf3gvaoEr",
"name": "OpenAi account"
}
},
"typeVersion": 1
},
{
"id": "85125704-7363-40de-af84-f267f8c7e919",
"name": "Structured Output Parser",
"type": "@n8n/n8n-nodes-langchain.outputParserStructured",
"position": [
2100,
480
],
"parameters": {
"jsonSchema": "{\n \"type\": \"object\",\n \"properties\": {\n \"title\": { \"type\": \"string\" },\n \"summary\": { \"type\": \"string\" },\n \"ideas\": {\n \"type\": \"array\",\n \"items\": { \"type\": \"string\" }\n },\n \"priority\": { \"type\": \"string\" }\n }\n}"
},
"typeVersion": 1.1
},
{
"id": "eda8851a-1929-4f2f-9149-627c0fe62fbc",
"name": "Schedule Trigger",
"type": "n8n-nodes-base.scheduleTrigger",
"position": [
628,
327
],
"parameters": {
"rule": {
"interval": [
{
"field": "minutes"
}
]
}
},
"typeVersion": 1.2
},
{
"id": "ad0d56b5-5caf-4fc0-bdbb-4e6207e4eb03",
"name": "Sticky Note",
"type": "n8n-nodes-base.stickyNote",
"position": [
580,
112.87898199907983
],
"parameters": {
"color": 7,
"width": 432.4578914269739,
"height": 427.09547550768553,
"content": "## 1. Query Slack for Messages \n[Read more about the Slack Trigger](https://docs.n8n.io/integrations/builtin/app-nodes/n8n-nodes-base.slack)\n\nSlack API search uses the same search syntax found in the app. Here, we'll use it to filter the latest messages with the ticket emoji within our designated channel called #n8n-tickets. "
},
"typeVersion": 1
},
{
"id": "d4ebe5b3-6d9a-4547-8af8-0985206c4ca4",
"name": "Sticky Note1",
"type": "n8n-nodes-base.stickyNote",
"position": [
1040,
180.44851541532478
],
"parameters": {
"color": 7,
"width": 711.6907825442045,
"height": 632.7258798316449,
"content": "## 2. Decide If We Need to Create a New Ticket \n[Read more about using Linear](https://docs.n8n.io/integrations/builtin/app-nodes/n8n-nodes-base.linear)\n\nFor generated issues, we add the message id to the description of the message so that we can check them at this point in the workflow to avoid duplicates."
},
"typeVersion": 1
},
{
"id": "b2920271-6698-47a4-8cac-ea4cec7b47d6",
"name": "Get Values",
"type": "n8n-nodes-base.set",
"position": [
1100,
360
],
"parameters": {
"mode": "raw",
"options": {},
"jsonOutput": "={\n \"id\": \"#{{ $json.permalink.split('/').last() }}\",\n \"type\": \"{{ $json.type }}\",\n \"title\": \"__NOT_SET__\",\n \"channel\": \"{{ $json.channel.name }}\",\n \"user\": \"{{ $json.username }} ({{ $json.user }})\",\n \"ts\": \"{{ $json.ts }}\",\n \"permalink\": \"{{ $json.permalink }}\",\n \"message\": \"{{ $json.text.replaceAll('\"','\\\\\"').replaceAll('\\n', '\\\\n') }}\"\n}"
},
"typeVersion": 3.3
},
{
"id": "c4a4db2a-5d1c-4726-8c98-aef57fdcfaa6",
"name": "Create New Ticket?",
"type": "n8n-nodes-base.if",
"position": [
1600,
360
],
"parameters": {
"options": {},
"conditions": {
"options": {
"leftValue": "",
"caseSensitive": true,
"typeValidation": "strict"
},
"combinator": "and",
"conditions": [
{
"id": "c11109b6-ee45-4b52-adc3-4be5fe420202",
"operator": {
"type": "boolean",
"operation": "false",
"singleValue": true
},
"leftValue": "={{ Boolean(($json.hashes ?? []).includes($json.id)) }}",
"rightValue": "=false"
}
]
}
},
"typeVersion": 2
},
{
"id": "46acb0de-1df1-4116-8aaf-704ec6644d7c",
"name": "Sticky Note2",
"type": "n8n-nodes-base.stickyNote",
"position": [
1780,
80
],
"parameters": {
"color": 7,
"width": 530.6864600881105,
"height": 578.3950618708791,
"content": "## 3. Use AI to Generate Ticket Contents\n[Read more about using Basic LLM Chain](https://docs.n8n.io/integrations/builtin/cluster-nodes/root-nodes/n8n-nodes-langchain.chainllm)\n\nFor this demo, we've instructed the AI to do the following:\n* Generate a descriptive title of the issue\n* Summarise the user message into an actionable request.\n* Determine a prority based on tone and context of the user message. \n* Can offer possible fixes through use of tools or RAG. (not implemented)\n"
},
"typeVersion": 1
},
{
"id": "503d4ae7-9d5b-4dab-94a2-da28bc0e49da",
"name": "Sticky Note6",
"type": "n8n-nodes-base.stickyNote",
"position": [
200,
120
],
"parameters": {
"width": 359.6648027457353,
"height": 400.4748439127683,
"content": "## Try It Out!\n### This workflow does the following:\n* Monitors a Slack channel for new user messages asking for assistance\n* Only user messages which are tagged with the ticket(🎫) emoji are processed.\n* Linear is first checked to see if a ticket was created for the user message.\n* User messages are sent to ChatGPT to generate title, description and priority.\n* Support ticket is created in Linear.\n\n### Need Help?\nJoin the [Discord](https://discord.com/invite/XPKeKXeB7d) or ask in the [Forum](https://community.n8n.io/)!\n\nHappy Hacking!"
},
"typeVersion": 1
},
{
"id": "11e423a4-36b6-4ecd-8bf7-58a7d4a1aa9a",
"name": "Get Existing Issues",
"type": "n8n-nodes-base.linear",
"position": [
1260,
360
],
"parameters": {
"operation": "getAll"
},
"credentials": {
"linearApi": {
"id": "Nn0F7T9FtvRUtEbe",
"name": "Linear account"
}
},
"typeVersion": 1,
"alwaysOutputData": true
},
{
"id": "413fde96-346a-468e-80b7-d465bd8add14",
"name": "Generate Ticket Using ChatGPT",
"type": "@n8n/n8n-nodes-langchain.chainLlm",
"position": [
1920,
320
],
"parameters": {
"text": "=The \"user issue\" is enclosed by 3 backticks:\n```\n{{ $('Get Values').item.json.message }}\n```\nYou will complete the following 4 tasks:\n1. Generate a title intended for a support ticket based on the user issue only. Be descriptive but use no more than 10 words.\n2. Summarise the user issue only by identifying the key expectations and steps that were taken to reach the conclusion.\n3. Offer at most 3 suggestions to debug or resolve the user issue only. ignore the previous issues for this task.\n4. Identify the urgency of the user issue only and denote the priority as one of \"low\", \"medium\", \"high\" or \"urgent\". If you cannot determine the urgency of the issue, then assign the \"low\" priority. Also consider that requests which require action either today or tomorrow should be prioritised as \"high\".",
"promptType": "define",
"hasOutputParser": true
},
"typeVersion": 1.4
},
{
"id": "66aecf53-6e8a-4ee8-88c3-be6b7d8d0527",
"name": "Sticky Note3",
"type": "n8n-nodes-base.stickyNote",
"position": [
2340,
206
],
"parameters": {
"color": 7,
"width": 374.7406065828194,
"height": 352.3865785298774,
"content": "## 4. Create New Ticket in Linear\n[Read more about using Linear](https://docs.n8n.io/integrations/builtin/app-nodes/n8n-nodes-base.linear)\n\nWith our ticket contents generated, we can now create our ticket in Linear for support to handle.\n"
},
"typeVersion": 1
},
{
"id": "f7898b7b-f60a-4315-a870-8c8ec4ad848f",
"name": "Create Ticket",
"type": "n8n-nodes-base.linear",
"position": [
2480,
380
],
"parameters": {
"title": "={{ $json.output.title }}",
"teamId": "1c721608-321d-4132-ac32-6e92d04bb487",
"additionalFields": {
"stateId": "92962324-3d1f-4cf8-993b-0c982cc95245",
"priorityId": "={{ { 'urgent': 1, 'high': 2, 'medium': 3, 'low': 4 }[$json.output.priority.toLowerCase()] ?? 0 }}",
"description": "=## {{ $json.output.summary }}\n\n### Suggestions\n{{ $json.output.ideas.map(idea => '* ' + idea).join('\\n') }}\n\n## Original Message\n{{ $('Get Values').item.json[\"user\"] }} asks:\n> {{ $('Get Values').item.json[\"message\"] }}\n\n### Metadata\nchannel: {{ $('Get Values').item.json.channel }}\nts: {{ $('Get Values').item.json.ts }}\npermalink: {{ $('Get Values').item.json.permalink }}\nhash: {{ $('Get Values').item.json.id }}\n"
}
},
"credentials": {
"linearApi": {
"id": "Nn0F7T9FtvRUtEbe",
"name": "Linear account"
}
},
"typeVersion": 1
},
{
"id": "0b706c12-6ce0-41af-ad4b-9d98d7d03a41",
"name": "Merge",
"type": "n8n-nodes-base.merge",
"position": [
1440,
360
],
"parameters": {
"mode": "combine",
"options": {},
"combinationMode": "multiplex"
},
"typeVersion": 2.1
},
{
"id": "d5b30127-f237-459d-860a-2589e3b54fb8",
"name": "Get Hashes Only",
"type": "n8n-nodes-base.set",
"position": [
1260,
640
],
"parameters": {
"options": {},
"assignments": {
"assignments": [
{
"id": "9b0e8527-ea17-4b1e-ba62-287111f4b37e",
"name": "hashes",
"type": "array",
"value": "={{ $json.descriptions.map(desc => desc.match(/hash\\:\\s([\\w#]+)/i)[1]) }}"
}
]
}
},
"typeVersion": 3.3
},
{
"id": "9de103e1-b6a4-4454-b1b9-73eff730fcb6",
"name": "Collect Descriptions",
"type": "n8n-nodes-base.aggregate",
"position": [
1260,
500
],
"parameters": {
"options": {},
"fieldsToAggregate": {
"fieldToAggregate": [
{
"renameField": true,
"outputFieldName": "descriptions",
"fieldToAggregate": "description"
}
]
}
},
"typeVersion": 1,
"alwaysOutputData": true
},
{
"id": "af34916f-7888-4d41-aee6-752b78e88c0c",
"name": "Sticky Note4",
"type": "n8n-nodes-base.stickyNote",
"position": [
780,
300
],
"parameters": {
"width": 204.96868508214473,
"height": 296.735132421306,
"content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n🚨**Required**\n* Set the Slack channel to monitor here."
},
"typeVersion": 1
},
{
"id": "58ab44f7-5fe5-4804-8bf1-36f351d86528",
"name": "Sticky Note5",
"type": "n8n-nodes-base.stickyNote",
"position": [
2440,
360
],
"parameters": {
"width": 183.49787916474958,
"height": 296.735132421306,
"content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n🚨**Required**\n* Set the Linear Team Name or ID here."
},
"typeVersion": 1
}
],
"pinData": {},
"connections": {
"Merge": {
"main": [
[
{
"node": "Create New Ticket?",
"type": "main",
"index": 0
}
]
]
},
"Slack": {
"main": [
[
{
"node": "Get Values",
"type": "main",
"index": 0
}
]
]
},
"Get Values": {
"main": [
[
{
"node": "Merge",
"type": "main",
"index": 0
},
{
"node": "Get Existing Issues",
"type": "main",
"index": 0
}
]
]
},
"Get Hashes Only": {
"main": [
[
{
"node": "Merge",
"type": "main",
"index": 1
}
]
]
},
"Schedule Trigger": {
"main": [
[
{
"node": "Slack",
"type": "main",
"index": 0
}
]
]
},
"OpenAI Chat Model": {
"ai_languageModel": [
[
{
"node": "Generate Ticket Using ChatGPT",
"type": "ai_languageModel",
"index": 0
}
]
]
},
"Create New Ticket?": {
"main": [
[
{
"node": "Generate Ticket Using ChatGPT",
"type": "main",
"index": 0
}
]
]
},
"Get Existing Issues": {
"main": [
[
{
"node": "Collect Descriptions",
"type": "main",
"index": 0
}
]
]
},
"Collect Descriptions": {
"main": [
[
{
"node": "Get Hashes Only",
"type": "main",
"index": 0
}
]
]
},
"Structured Output Parser": {
"ai_outputParser": [
[
{
"node": "Generate Ticket Using ChatGPT",
"type": "ai_outputParser",
"index": 0
}
]
]
},
"Generate Ticket Using ChatGPT": {
"main": [
[
{
"node": "Create Ticket",
"type": "main",
"index": 0
}
]
]
}
}
}Workflow n8n Slack, OpenAI, tickets : pour qui est ce workflow ?
Ce workflow s'adresse aux équipes de support client, aux responsables de projet et aux entreprises de taille petite à moyenne qui utilisent Slack pour la communication interne. Un niveau technique intermédiaire est recommandé pour la personnalisation de ce flux.
Workflow n8n Slack, OpenAI, tickets : problème résolu
Ce workflow résout le problème de la gestion manuelle des tickets, qui peut être chronophage et sujet à des erreurs. En automatisant la création de tickets à partir de messages Slack, les utilisateurs peuvent se concentrer sur des tâches à plus forte valeur ajoutée. Les entreprises bénéficient d'une réduction des délais de réponse et d'une meilleure organisation des demandes, ce qui améliore la satisfaction client et l'efficacité opérationnelle.
Workflow n8n Slack, OpenAI, tickets : étapes du workflow
Étape 1 : Le workflow est déclenché par un événement planifié.
- Étape 1 : Les messages Slack sont récupérés pour identifier les demandes.
- Étape 2 : L'OpenAI Chat Model analyse ces messages pour générer des résumés.
- Étape 3 : Les informations sont structurées et vérifiées pour décider de la création d'un ticket.
- Étape 4 : Si nécessaire, un ticket est créé automatiquement dans le système de gestion de projet.
Workflow n8n Slack, OpenAI, tickets : guide de personnalisation
Pour personnaliser ce workflow, vous pouvez modifier le déclencheur planifié en ajustant la fréquence d'exécution. Il est également possible de changer les paramètres de l'OpenAI Chat Model pour affiner les résumés générés. Assurez-vous de configurer correctement les connexions avec Slack et le système de gestion de projet utilisé. Pour renforcer la sécurité, pensez à mettre en place des contrôles d'accès sur les données sensibles traitées par le workflow.