This workflow follows the Agent → OpenAI Chat 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 →
{
"name": "Roast My Code API",
"description": null,
"active": true,
"isArchived": false,
"nodes": [
{
"parameters": {
"path": "roast-code-api",
"responseMode": "responseNode",
"httpMethod": "POST",
"options": {
"responseHeaders": {
"entries": [
{
"name": "Access-Control-Allow-Origin",
"value": "*"
},
{
"name": "Access-Control-Allow-Headers",
"value": "Content-Type"
}
]
}
}
},
"type": "n8n-nodes-base.webhook",
"typeVersion": 2,
"position": [
200,
300
],
"id": "webhook-node",
"name": "Webhook"
},
{
"parameters": {
"promptType": "define",
"text": "=Roast the following code (roast level: {{ $json.body.level || \"medium\" }}):\n\nLanguage: {{ $json.body.language || \"auto-detect\" }}\n\nCode:\n```\n{{ $json.body.code || \"// No code provided\" }}\n```",
"options": {
"systemMessage": "You are a hilariously savage code roaster. You're like a combination of a senior developer and a stand-up comedian. Your job is to roast submitted code in the most entertaining way possible while still being somewhat educational.\n\nYour roast should include:\n1. **First Impression** - Your visceral reaction to seeing this code\n2. **The Roast** - Go through the code and roast every questionable decision. Be creative, use metaphors, pop culture references, and programming humor.\n3. **Savage Score** - Rate the code on a scale of \"Gordon Ramsay would cry\" to \"Actually not terrible\"\n4. **One Nice Thing** - Say ONE genuinely nice thing (but make it backhanded if possible)\n5. **What They Should Actually Do** - Brief, real advice hidden in humor\n\nBe funny but not mean-spirited. The goal is entertainment + education. Use emojis sparingly for effect."
}
},
"type": "@n8n/n8n-nodes-langchain.agent",
"typeVersion": 2.2,
"position": [
500,
300
],
"id": "ai-agent-node",
"name": "AI Agent"
},
{
"parameters": {
"model": {
"__rl": true,
"mode": "list",
"value": "gpt-4.1-mini"
},
"options": {}
},
"type": "@n8n/n8n-nodes-langchain.lmChatOpenAi",
"typeVersion": 1.2,
"position": [
500,
500
],
"id": "openai-model-node",
"name": "OpenAI Chat Model",
"credentials": {
"openAiApi": {
"name": "<your credential>"
}
}
},
{
"parameters": {
"respondWith": "json",
"responseBody": "={{ JSON.stringify({ \"roast\": $json.output }) }}",
"options": {
"responseHeaders": {
"entries": [
{
"name": "Access-Control-Allow-Origin",
"value": "*"
},
{
"name": "Access-Control-Allow-Headers",
"value": "Content-Type"
},
{
"name": "Content-Type",
"value": "application/json"
}
]
}
}
},
"type": "n8n-nodes-base.respondToWebhook",
"typeVersion": 1.1,
"position": [
800,
300
],
"id": "respond-node",
"name": "Respond to Webhook"
}
],
"connections": {
"Webhook": {
"main": [
[
{
"node": "AI Agent",
"type": "main",
"index": 0
}
]
]
},
"OpenAI Chat Model": {
"ai_languageModel": [
[
{
"node": "AI Agent",
"type": "ai_languageModel",
"index": 0
}
]
]
},
"AI Agent": {
"main": [
[
{
"node": "Respond to Webhook",
"type": "main",
"index": 0
}
]
]
}
},
"settings": {
"executionOrder": "v1",
"callerPolicy": "workflowsFromSameOwner",
"availableInMCP": false
},
"staticData": null,
"meta": null,
"activeVersionId": "001adbdb-2903-4fbc-bbe9-2854fc840f9d",
"versionCounter": 14,
"triggerCount": 1,
"shared": [
{
"updatedAt": "2026-03-01T23:54:10.255Z",
"createdAt": "2026-03-01T23:54:10.255Z",
"role": "workflow:owner",
"workflowId": "MSNYiwImRsmkc3Ko",
"projectId": "jISBlT19NO0fn5mT",
"project": {
"updatedAt": "2025-11-19T23:58:51.301Z",
"createdAt": "2025-11-19T23:57:07.759Z",
"id": "jISBlT19NO0fn5mT",
"name": "Armani Cunningham <hamstudios101@gmail.com>",
"type": "personal",
"icon": null,
"description": null,
"creatorId": "a8e49b89-e536-45ff-8330-fab9f0943ab1"
}
}
],
"tags": [],
"activeVersion": {
"updatedAt": "2026-03-02T01:03:41.453Z",
"createdAt": "2026-03-02T01:03:41.453Z",
"versionId": "001adbdb-2903-4fbc-bbe9-2854fc840f9d",
"workflowId": "MSNYiwImRsmkc3Ko",
"nodes": [
{
"parameters": {
"path": "roast-code-api",
"responseMode": "responseNode",
"httpMethod": "POST",
"options": {
"responseHeaders": {
"entries": [
{
"name": "Access-Control-Allow-Origin",
"value": "*"
},
{
"name": "Access-Control-Allow-Headers",
"value": "Content-Type"
}
]
}
}
},
"type": "n8n-nodes-base.webhook",
"typeVersion": 2,
"position": [
200,
300
],
"id": "webhook-node",
"name": "Webhook",
"webhookId": "roast-code-api-wh"
},
{
"parameters": {
"promptType": "define",
"text": "=Roast the following code (roast level: {{ $json.body.level || \"medium\" }}):\n\nLanguage: {{ $json.body.language || \"auto-detect\" }}\n\nCode:\n```\n{{ $json.body.code || \"// No code provided\" }}\n```",
"options": {
"systemMessage": "You are a hilariously savage code roaster. You're like a combination of a senior developer and a stand-up comedian. Your job is to roast submitted code in the most entertaining way possible while still being somewhat educational.\n\nYour roast should include:\n1. **First Impression** - Your visceral reaction to seeing this code\n2. **The Roast** - Go through the code and roast every questionable decision. Be creative, use metaphors, pop culture references, and programming humor.\n3. **Savage Score** - Rate the code on a scale of \"Gordon Ramsay would cry\" to \"Actually not terrible\"\n4. **One Nice Thing** - Say ONE genuinely nice thing (but make it backhanded if possible)\n5. **What They Should Actually Do** - Brief, real advice hidden in humor\n\nBe funny but not mean-spirited. The goal is entertainment + education. Use emojis sparingly for effect."
}
},
"type": "@n8n/n8n-nodes-langchain.agent",
"typeVersion": 2.2,
"position": [
500,
300
],
"id": "ai-agent-node",
"name": "AI Agent"
},
{
"parameters": {
"model": {
"__rl": true,
"mode": "list",
"value": "gpt-4.1-mini"
},
"options": {}
},
"type": "@n8n/n8n-nodes-langchain.lmChatOpenAi",
"typeVersion": 1.2,
"position": [
500,
500
],
"id": "openai-model-node",
"name": "OpenAI Chat Model",
"credentials": {
"openAiApi": {
"id": "xVvmBQ0k0B49oB4q",
"name": "n8n free OpenAI API credits"
}
}
},
{
"parameters": {
"respondWith": "json",
"responseBody": "={{ JSON.stringify({ \"roast\": $json.output }) }}",
"options": {
"responseHeaders": {
"entries": [
{
"name": "Access-Control-Allow-Origin",
"value": "*"
},
{
"name": "Access-Control-Allow-Headers",
"value": "Content-Type"
},
{
"name": "Content-Type",
"value": "application/json"
}
]
}
}
},
"type": "n8n-nodes-base.respondToWebhook",
"typeVersion": 1.1,
"position": [
800,
300
],
"id": "respond-node",
"name": "Respond to Webhook"
}
],
"connections": {
"Webhook": {
"main": [
[
{
"node": "AI Agent",
"type": "main",
"index": 0
}
]
]
},
"OpenAI Chat Model": {
"ai_languageModel": [
[
{
"node": "AI Agent",
"type": "ai_languageModel",
"index": 0
}
]
]
},
"AI Agent": {
"main": [
[
{
"node": "Respond to Webhook",
"type": "main",
"index": 0
}
]
]
}
},
"authors": "Armani Cunningham",
"name": null,
"description": null,
"autosaved": false,
"workflowPublishHistory": [
{
"createdAt": "2026-03-02T01:03:41.892Z",
"id": 347,
"workflowId": "MSNYiwImRsmkc3Ko",
"versionId": "001adbdb-2903-4fbc-bbe9-2854fc840f9d",
"event": "activated",
"userId": "a8e49b89-e536-45ff-8330-fab9f0943ab1"
}
]
}
}
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
Pro
For the full experience including quality scoring and batch install features for each workflow upgrade to Pro
About this workflow
Roast My Code API. Uses agent, lmChatOpenAi. Webhook trigger; 4 nodes.
Source: https://github.com/mhmdmnsor292003-arch/free-ai-tools/blob/main/workflows/roast-my-code-api.json — 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.
jarvis. Uses agent, lmChatOpenAi, outputParserStructured, toolWorkflow. Webhook trigger; 13 nodes.
Agent, OpenAI Chat, Output Parser Structured +3
This template is ideal for: Businesses that want to provide 24/7 automated voice-based customer support Service providers needing to schedule appointments via voice interaction Teams looking to handle
Agent, Tool Think, OpenAI Chat +3
Description: This n8n workflow automates a Discord bot to fetch messages from a specified channel and send AI-generated responses in threads. It ensures smooth message processing and interaction, maki
Tool Calculator, Discord, OpenAI Chat +2
AI chatbot for appointment scheduling. Uses memoryBufferWindow, lmChatOpenAi, toolWorkflow, chatTrigger. Webhook trigger; 12 nodes.
Memory Buffer Window, OpenAI Chat, Tool Workflow +4
💥 Build a Customer Support AI Voice Agent with GPT-5 and ElevenLabs _ VIDE. Uses agent, toolThink, lmChatOpenAi, googleSheetsTool. Webhook trigger; 12 nodes.
Agent, Tool Think, OpenAI Chat +3