Elvis Sarvia This workflow corresponds to n8n.io template #13847 — we link there as the canonical source.
This workflow follows the Agent → Chat Trigger 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 →
{
"meta": {
"templateCredsSetupCompleted": true
},
"nodes": [
{
"id": "f5350dfb-7df6-4f5b-a0a3-c4262477ee8e",
"name": "When chat message received",
"type": "@n8n/n8n-nodes-langchain.chatTrigger",
"position": [
256,
480
],
"parameters": {
"options": {
"responseMode": "responseNodes"
}
},
"typeVersion": 1.4
},
{
"id": "77f32376-29e1-4d45-8ef9-6526b3924781",
"name": "AI Agent",
"type": "@n8n/n8n-nodes-langchain.agent",
"position": [
480,
480
],
"parameters": {
"options": {
"systemMessage": "You are a customer support assistant. When a user shares a customer email or inquiry, draft a professional, helpful response. Be concise, empathetic, and accurate. Never promise features that don't exist or offer discounts unless explicitly authorized. If the inquiry is unclear, ask the user for clarification before drafting a response."
}
},
"typeVersion": 3.1
},
{
"id": "37c546d1-e7ab-4f8b-aa5e-e5e04de1670e",
"name": "OpenRouter Chat Model",
"type": "@n8n/n8n-nodes-langchain.lmChatOpenRouter",
"position": [
560,
704
],
"parameters": {
"options": {}
},
"credentials": {
"openRouterApi": {
"name": "<your credential>"
}
},
"typeVersion": 1
},
{
"id": "45dd0c5e-78ce-4538-af77-a56fea41275a",
"name": "If",
"type": "n8n-nodes-base.if",
"position": [
1056,
480
],
"parameters": {
"options": {},
"conditions": {
"options": {
"version": 3,
"leftValue": "",
"caseSensitive": true,
"typeValidation": "loose"
},
"combinator": "and",
"conditions": [
{
"id": "b57dcf1c-6baa-4241-b7e1-6ae5048ef7a9",
"operator": {
"type": "boolean",
"operation": "true",
"singleValue": true
},
"leftValue": "={{ $json.data.approved }}",
"rightValue": "true"
}
]
},
"looseTypeValidation": true
},
"typeVersion": 2.3
},
{
"id": "04626316-5bac-4924-b65e-e521a9394d83",
"name": "Gmail - Send Reply",
"type": "n8n-nodes-base.gmail",
"position": [
1280,
384
],
"parameters": {
"sendTo": "={{ $json.email || \"customer@example.com\" }}",
"message": "={{ $(\"AI Agent\").first().json.output }}",
"options": {},
"subject": "Re: Your Support Request",
"emailType": "text"
},
"credentials": {
"gmailOAuth2": {
"name": "<your credential>"
}
},
"typeVersion": 2
},
{
"id": "a46cc0e1-8e67-4a07-ab24-585e81a231b2",
"name": "Rejected Response",
"type": "@n8n/n8n-nodes-langchain.chat",
"position": [
1280,
576
],
"parameters": {
"message": "Response was rejected. Please provide revision feedback and resubmit.",
"options": {}
},
"typeVersion": 1.2
},
{
"id": "f9d0c2ec-c7bf-4bdf-9479-bb48391575f7",
"name": "Approved Response",
"type": "@n8n/n8n-nodes-langchain.chat",
"position": [
1504,
384
],
"parameters": {
"message": "Response approved and sent to the customer.",
"options": {}
},
"typeVersion": 1.2
},
{
"id": "9b4ba9ab-feb1-4d09-a574-d75af19fd382",
"name": "Human Approval",
"type": "@n8n/n8n-nodes-langchain.chat",
"position": [
832,
480
],
"parameters": {
"message": "=**Draft Response for Review**\n\n{{ $json.output }}\n\nPlease review the AI-generated response above and approve to send to the customer, or reject to revise.",
"options": {
"limitWaitTime": {
"values": {
"resumeAmount": 4
}
}
},
"operation": "sendAndWait",
"responseType": "approval",
"approvalOptions": {
"values": {
"approvalType": "double",
"approveLabel": "Send to Customer",
"disapproveLabel": "Revise"
}
}
},
"typeVersion": 1.2
},
{
"id": "5f0cca1b-e43d-44d2-820d-02931dd9f782",
"name": "Sticky Note",
"type": "n8n-nodes-base.stickyNote",
"position": [
-400,
256
],
"parameters": {
"width": 560,
"height": 720,
"content": "## Customer Support Email Review with Chat Approval\n\n### How it works\n1. **Chat Trigger** receives a customer support scenario via the built-in chat interface.\n2. **AI Agent** drafts a professional email response using the connected LLM.\n3. **Human Approval** node presents the draft in chat with Approve/Reject buttons. The workflow pauses here.\n4. **IF node** routes based on the decision: approved drafts are sent via Gmail, rejected drafts are flagged for manual revision.\n\n### Setup\n- Connect your **LLM credentials** (e.g., OpenRouter, OpenAI) to the Chat Model node\n- Connect your **Gmail credentials** to the Gmail - Send Reply node\n- Set the Chat Trigger's Response Mode to \"Using Response Nodes\"\n- (Optional) Enable \"Limit Wait Time\" on the Human Approval node to prevent indefinite waits\n\n### Customization\n- Swap Gmail for another email provider (Outlook, SMTP)\n- Adjust the AI Agent's system prompt to match your company's tone and policies\n\n\nThis template is a learning companion to the Production AI Playbook, a series that explores strategies, shares best practices, and provides practical examples for building reliable AI systems in n8n. \n\n[Link to blog](https://go.n8n.io/PAP-HO-Blog)\n"
},
"typeVersion": 1
},
{
"id": "cdc3acd8-ae03-4512-8011-4321fbd463c1",
"name": "Sticky Note1",
"type": "n8n-nodes-base.stickyNote",
"position": [
208,
368
],
"parameters": {
"color": 7,
"width": 544,
"height": 480,
"content": "## Draft Response"
},
"typeVersion": 1
},
{
"id": "bead3a0f-64a5-417b-ba2a-c053ef95ee17",
"name": "Sticky Note2",
"type": "n8n-nodes-base.stickyNote",
"position": [
784,
368
],
"parameters": {
"color": 7,
"width": 208,
"height": 480,
"content": "## Human Review"
},
"typeVersion": 1
},
{
"id": "8ca1ea87-8cd3-4507-b6fb-d2b6ece0cb9a",
"name": "Sticky Note3",
"type": "n8n-nodes-base.stickyNote",
"position": [
1024,
368
],
"parameters": {
"color": 7,
"width": 688,
"height": 480,
"content": "## Route and Send"
},
"typeVersion": 1
}
],
"connections": {
"If": {
"main": [
[
{
"node": "Gmail - Send Reply",
"type": "main",
"index": 0
}
],
[
{
"node": "Rejected Response",
"type": "main",
"index": 0
}
]
]
},
"AI Agent": {
"main": [
[
{
"node": "Human Approval",
"type": "main",
"index": 0
}
]
]
},
"Human Approval": {
"main": [
[
{
"node": "If",
"type": "main",
"index": 0
}
]
]
},
"Gmail - Send Reply": {
"main": [
[
{
"node": "Approved Response",
"type": "main",
"index": 0
}
]
]
},
"OpenRouter Chat Model": {
"ai_languageModel": [
[
{
"node": "AI Agent",
"type": "ai_languageModel",
"index": 0
}
]
]
},
"When chat message received": {
"main": [
[
{
"node": "AI Agent",
"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.
gmailOAuth2openRouterApi
For the full experience including quality scoring and batch install features for each workflow upgrade to Pro
About this workflow
Review AI-drafted customer responses before they go out. This template sets up a chat-based approval flow where an AI agent drafts a reply and a human reviewer approves or rejects it, all within the n8n chat interface.
Source: https://n8n.io/workflows/13847/ — 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.
This Chatbot automates the process of discovering job openings and generating tailored job application emails.
Send an AI a few details about your "Dream Customer" in normal english, then have it search the web and give you a "Dream 100" - 100 ideal prospects to connect with in your industry.
Turn any YouTube channel into a searchable knowledge base. The AI agent understands relationships between videos, topics, tools, and concepts - enabling powerful queries like "Which videos talk about
Overview Meet Maria, a sophisticated AI Booking Agent designed for Veterinary Clinics (but easily adaptable to any service business). This workflow transforms a simple chat interface into a full-scale
Aiden. Uses supabase, chat, memoryBufferWindow, memoryPostgresChat. Chat trigger; 20 nodes.