Gilbert Onyebuchi This workflow corresponds to n8n.io template #12460 — we link there as the canonical source.
This workflow follows the Agent → Google Gemini 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 →
{
"meta": {
"templateCredsSetupCompleted": true
},
"nodes": [
{
"id": "1356b3c8-8cad-4ff4-8262-a691840401ad",
"name": "Setup Instructions",
"type": "n8n-nodes-base.stickyNote",
"position": [
-720,
-560
],
"parameters": {
"width": 504,
"height": 1148,
"content": "# Email chatbot workflow using AI Agent and SendGrid\n\n## Watch this tutorial\n@[youtube](aZU_vAyBuSQ)\n\n## How it works\nThis workflow automatically replies to incoming emails using AI-powered responses:\n- Monitor your inbox for new emails via IMAP connection\n- Extract and clean email content (sender, subject, body)\n- Generate contextual customer service replies using Google Gemini AI\n- Send automated responses through SendGrid with conversation memory\n- Maintain conversation context for follow-up emails\n\n## Setup\n1. **Connect your email:** Add IMAP credentials in the \"Read incoming emails\" node\n2. **Add Google Gemini API:** Get your API key from [Google AI Studio](https://aistudio.google.com/) and connect it to credentials\n3. **Configure SendGrid:** Add your SendGrid API key and set your \"from\" email address in the \"Send reply email\" node\n4. **Customize AI prompt:** Update the prompt in \"Generate reply email\" node to match your brand voice\n5. **Test workflow:** Send a test email to your inbox and verify the auto-reply works correctly\n\n## Need help or want to Customize? Contact me\nEmail: gcgilbs@gmail.com\nLinkedIn: [Gilbert Onyebuchi](https://www.linkedin.com/in/gilbert-onyebuchi/)\n"
},
"typeVersion": 1
},
{
"id": "1b31d1d5-5524-4eb0-a595-9e015ed8ad5e",
"name": "Google Gemini Chat Model",
"type": "@n8n/n8n-nodes-langchain.lmChatGoogleGemini",
"position": [
64,
224
],
"parameters": {
"options": {}
},
"credentials": {
"googlePalmApi": {
"name": "<your credential>"
}
},
"typeVersion": 1
},
{
"id": "e80e12a5-79b8-484b-bd2c-912891c542d2",
"name": "Simple Memory",
"type": "@n8n/n8n-nodes-langchain.memoryBufferWindow",
"position": [
224,
240
],
"parameters": {
"sessionKey": "session_key",
"sessionIdType": "customKey"
},
"typeVersion": 1.3
},
{
"id": "206c2148-923a-4a12-859b-3cf0eb3bd113",
"name": "Sticky Note",
"type": "n8n-nodes-base.stickyNote",
"position": [
-208,
-384
],
"parameters": {
"color": 7,
"width": 800,
"height": 288,
"content": "## 1. Read incoming email"
},
"typeVersion": 1
},
{
"id": "2aa834ca-d260-4801-9128-27f2ba668f10",
"name": "Sticky Note1",
"type": "n8n-nodes-base.stickyNote",
"position": [
-208,
-80
],
"parameters": {
"color": 7,
"width": 800,
"height": 480,
"content": "## 2. Generate email reply and send"
},
"typeVersion": 1
},
{
"id": "2ac3002e-4966-4bed-91cf-dd3e04ab4c1f",
"name": "Pause for 20 seconds",
"type": "n8n-nodes-base.wait",
"position": [
96,
-272
],
"parameters": {
"amount": 20
},
"typeVersion": 1.1
},
{
"id": "f18aa35c-562a-436f-9b31-cca486028648",
"name": "Set your details",
"type": "n8n-nodes-base.set",
"position": [
320,
-272
],
"parameters": {
"options": {},
"assignments": {
"assignments": [
{
"id": "5f43db65-a2ab-4f0f-831d-803e355b49f0",
"name": "from",
"type": "string",
"value": "={{ $json.metadata[\"return-path\"] }}"
},
{
"id": "13bfcb4f-88c5-4136-84f2-ab90980e3c61",
"name": "subject",
"type": "string",
"value": "={{ $json.subject }}"
},
{
"id": "21211eda-8f99-4be8-a634-a5e851d993a6",
"name": "body",
"type": "string",
"value": "={{\n $json.textPlain\n .split(\"\\r\\n\\r\\n\")\n .slice(1)\n .join(\" \")\n .replace(/\\r\\n/g, \" \")\n .replace(/\\s+/g, \" \")\n .replace(/\u00e2\u0080\u0099/g, \"\u2019\")\n .replace(/\u00e2\u0080\u0093/g, \"\u2013\")\n .replace(/\u00e2\u0080\u0094/g, \"\u2014\")\n .replace(/\u00e2\u0080\u009c/g, \"\u201c\")\n .replace(/\u00e2\u0080\u009d/g, \"\u201d\")\n .trim()\n}}"
}
]
}
},
"typeVersion": 3.4
},
{
"id": "fd1c7b07-eddd-448b-b01f-91e423811384",
"name": "Check if email exists",
"type": "n8n-nodes-base.if",
"notes": "Ensures the email has content before processing",
"position": [
-128,
32
],
"parameters": {
"conditions": {
"string": [
{
"value1": "={{ $json.from }}",
"operation": "isNotEmpty"
}
]
}
},
"typeVersion": 1
},
{
"id": "8b0cbe4c-556e-46bd-8123-52f551d1b04b",
"name": "Send reply email",
"type": "n8n-nodes-base.sendGrid",
"position": [
400,
16
],
"parameters": {
"subject": "=Re {{ $('Set your details').item.json.subject }}",
"toEmail": "={{ $('Set your details').item.json.from }}",
"fromName": "Your_name",
"resource": "mail",
"fromEmail": "Your_email_address",
"contentValue": "={{ $json.output }}\nGilbert Onyebuchi",
"additionalFields": {}
},
"credentials": {
"sendGridApi": {
"name": "<your credential>"
}
},
"typeVersion": 1
},
{
"id": "f1af183f-2008-4512-9b5c-4293a5757b71",
"name": "Generate reply email",
"type": "@n8n/n8n-nodes-langchain.agent",
"position": [
96,
16
],
"parameters": {
"text": "=You are my helpful customer service chatbot. Give me a reply to this email: \"{{ $json.body }}\"\n\n\n\nRemember. Output only the reply, nothing else",
"options": {},
"promptType": "define"
},
"typeVersion": 3
},
{
"id": "560fe41f-b83f-4f21-b675-38676a2ec8d2",
"name": "Read incoming emails",
"type": "n8n-nodes-base.emailReadImap",
"notes": "CONFIGURE THIS:\n- Host: imap.gmail.com (for Gmail) or your email provider's IMAP server\n- Port: 993 (SSL) or 143 (standard)\n- User: your-email@company.com\n- Password: your email password or app password\n- Check 'Secure': Yes for SSL",
"position": [
-128,
-272
],
"parameters": {
"options": {},
"postProcessAction": "nothing"
},
"credentials": {
"imap": {
"name": "<your credential>"
}
},
"typeVersion": 2
}
],
"connections": {
"Simple Memory": {
"ai_memory": [
[
{
"node": "Generate reply email",
"type": "ai_memory",
"index": 0
}
]
]
},
"Set your details": {
"main": [
[
{
"node": "Check if email exists",
"type": "main",
"index": 0
}
]
]
},
"Generate reply email": {
"main": [
[
{
"node": "Send reply email",
"type": "main",
"index": 0
}
]
]
},
"Pause for 20 seconds": {
"main": [
[
{
"node": "Set your details",
"type": "main",
"index": 0
}
]
]
},
"Read incoming emails": {
"main": [
[
{
"node": "Pause for 20 seconds",
"type": "main",
"index": 0
}
]
]
},
"Check if email exists": {
"main": [
[
{
"node": "Generate reply email",
"type": "main",
"index": 0
}
]
]
},
"Google Gemini Chat Model": {
"ai_languageModel": [
[
{
"node": "Generate reply email",
"type": "ai_languageModel",
"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.
googlePalmApiimapsendGridApi
For the full experience including quality scoring and batch install features for each workflow upgrade to Pro
About this workflow
Transform your inbox into an intelligent assistant! This workflow automatically reads incoming emails, generates personalized AI responses using Google Gemini, and sends professional replies—all on autopilot.
Source: https://n8n.io/workflows/12460/ — 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 n8n workflow automates communication with meeting invitees to decrease no-show rates by sending timely email and WhatsApp reminders, and a clarification request if more information is needed to p
AI-Agent-with-MCP-and-Tools. Uses agent, lmChatGoogleGemini, memoryBufferWindow, notionTool. Manual trigger; 6 nodes.
reasoning_+_anti_deception_agent_vs_agent_eval_workflow. Uses httpRequestTool, agent, memoryBufferWindow, lmChatGoogleGemini. Event-driven trigger; 28 nodes.
ModelRouter. Uses chatTrigger, agent, modelSelector, httpRequest. Chat trigger; 28 nodes.
Flexible and scalable chatbot template, designed mainly for Spanish conversations but capable of handling English and other languages. Integrates Google Gemini API for text and image generation, and T