Eduard This workflow corresponds to n8n.io template #1938 — we link there as the canonical source.
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": "180",
"name": "Discord AI bot",
"tags": [],
"nodes": [
{
"id": "6f188270-2c08-491f-bf52-c4a152b33aa0",
"name": "When clicking \"Execute Workflow\"",
"type": "n8n-nodes-base.manualTrigger",
"position": [
1220,
780
],
"parameters": {},
"typeVersion": 1
},
{
"id": "e4839de2-fc04-40b0-b6bc-596455ad93fe",
"name": "Webhook",
"type": "n8n-nodes-base.webhook",
"position": [
1220,
580
],
"parameters": {
"path": "d0cdd428-be96-4821-85bc-65342cf928d0",
"options": {},
"httpMethod": "POST"
},
"typeVersion": 1
},
{
"id": "15dcafe1-6361-4775-ace0-e34fd2a143b4",
"name": "No Operation, do nothing",
"type": "n8n-nodes-base.noOp",
"position": [
2120,
940
],
"parameters": {},
"typeVersion": 1
},
{
"id": "0d28fe8e-da80-458b-9a75-d316019cb3ae",
"name": "Analyze user request",
"type": "n8n-nodes-base.openAi",
"position": [
1420,
680
],
"parameters": {
"model": "gpt-4",
"prompt": {
"messages": [
{
"role": "system",
"content": "Act as a service desk agent and help to categorize user messages. Return back only JSON without quotations. Do not return anything else."
},
{
"content": "=Here is a user feedback: \"{{ $json.body.feedback }}\". Please analyse it and put into one of the categories:\n1. \"success-story\" for user appraisal or success story. this will be processed by customer success department\n2. \"urgent-issue\" for extreme dissatisfaction or an urgent problem. this will be escalated to the IT team. Please assess if the request is really urgent and whether it has an immediate impact on the client. If the ticket doesn't look like an immediate problem or an extreme dissatisfaction then proceed as a normal ticket.\n3. \"ticket\" for everything else. This will be processed as normal by customer support team.\n\nPlease return back a JSON with the following structure: category (string), feedback (string), instruction (string).\nCategory must match the analysed category. feedback must match the original text. instruction should contain a text for a department according to the category with a one sentense summary of the feedback. Please be polite and friendly to the colleagues."
}
]
},
"options": {
"maxTokens": 500,
"temperature": 0.5
},
"resource": "chat"
},
"credentials": {
"openAiApi": {
"name": "<your credential>"
}
},
"typeVersion": 1
},
{
"id": "ce1c4198-ce21-4436-9ccb-4a2a078cd06e",
"name": "Select category",
"type": "n8n-nodes-base.switch",
"position": [
1840,
680
],
"parameters": {
"rules": {
"rules": [
{
"value2": "success-story"
},
{
"output": 1,
"value2": "urgent-issue"
},
{
"output": 2,
"value2": "ticket"
}
]
},
"value1": "={{ $json.gpt_reply.category.toLowerCase() }}",
"dataType": "string",
"fallbackOutput": 3
},
"typeVersion": 1
},
{
"id": "839cc38d-b393-4fc1-a068-47a8fcf55e3f",
"name": "Parse JSON",
"type": "n8n-nodes-base.set",
"position": [
1640,
680
],
"parameters": {
"values": {
"string": [
{
"name": "gpt_reply",
"value": "={{ JSON.parse( $json.message.content.replace(/\\n(?=[^\"]*\"(?:[^\"]*\"[^\"]*\")*[^\"]*$)/g, '\\\\n')) }}"
}
]
},
"options": {}
},
"typeVersion": 2
},
{
"id": "4c150439-89af-42bd-bbdc-905d13ada76b",
"name": "User Success Dept",
"type": "n8n-nodes-base.discord",
"position": [
2120,
460
],
"parameters": {
"text": "={{ $json.gpt_reply.instruction }}",
"options": {},
"webhookUri": "https://discord.com/api/webhooks/<YOUR WEBHOOK HERE>"
},
"typeVersion": 1
},
{
"id": "9a5e5335-9e6c-4f1f-a0f0-b1b022956549",
"name": "IT Dept",
"type": "n8n-nodes-base.discord",
"position": [
2120,
620
],
"parameters": {
"text": "={{ $json.gpt_reply.instruction }}",
"options": {},
"webhookUri": "https://discord.com/api/webhooks/<YOUR WEBHOOK HERE>"
},
"typeVersion": 1
},
{
"id": "d6d6250a-3a24-49f1-a597-47ebc179949c",
"name": "Helpdesk",
"type": "n8n-nodes-base.discord",
"position": [
2120,
780
],
"parameters": {
"text": "={{ $json.gpt_reply.instruction }}",
"options": {},
"webhookUri": "https://discord.com/api/webhooks/<YOUR WEBHOOK HERE>"
},
"typeVersion": 1
}
],
"active": false,
"settings": {
"callerPolicy": "workflowsFromSameOwner",
"saveManualExecutions": true,
"saveDataSuccessExecution": "all"
},
"versionId": "8871171e-7e18-49ee-a570-facbe97afb79",
"connections": {
"Webhook": {
"main": [
[
{
"node": "Analyze user request",
"type": "main",
"index": 0
}
]
]
},
"Parse JSON": {
"main": [
[
{
"node": "Select category",
"type": "main",
"index": 0
}
]
]
},
"Select category": {
"main": [
[
{
"node": "User Success Dept",
"type": "main",
"index": 0
}
],
[
{
"node": "IT Dept",
"type": "main",
"index": 0
}
],
[
{
"node": "Helpdesk",
"type": "main",
"index": 0
}
],
[
{
"node": "No Operation, do nothing",
"type": "main",
"index": 0
}
]
]
},
"Analyze user request": {
"main": [
[
{
"node": "Parse JSON",
"type": "main",
"index": 0
}
]
]
},
"When clicking \"Execute Workflow\"": {
"main": [
[
{
"node": "Analyze user request",
"type": "main",
"index": 0
}
]
]
}
}
}
Credentials you'll need
Each integration node will prompt for credentials when you import. We strip credential IDs before publishing — you'll add your own.
openAiApi
For the full experience including quality scoring and batch install features for each workflow upgrade to Pro
About this workflow
This workflow is a template example for making Discord GPT-powered bots. Incoming user requests are analysed and categorised via OpenAI node with the help of a hand-crafted prompt. The response message is then routed to a different Discord channel.
Source: https://n8n.io/workflows/1938/ — 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.
The Problem That it Solves
2322. Uses formTrigger, httpRequest, bannerbear, discord. Event-driven trigger; 16 nodes.
This n8n workflow shows an easy way to automate the creation of social media assets using AI and a service like BannerBear.
This workflow listens for new products in Shopify and transforms the product data into polished social media content. It generates captions and hashtags using an AI model, then posts the product to In
This workflow captures new form submissions, cleans the data, and stores it securely before applying AI-based lead qualification. It analyzes each message to assign category, score, and priority. Base