This workflow corresponds to n8n.io template #13459 — we link there as the canonical source.
This workflow follows the Agent → Airtabletool 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": "ac9787a4-30a4-4b0c-a436-96216c92c9f1",
"name": "When User Asks Question",
"type": "@n8n/n8n-nodes-langchain.chatTrigger",
"position": [
0,
0
],
"parameters": {
"public": true,
"options": {}
},
"typeVersion": 1.4
},
{
"id": "ec8d0024-a6a9-4e99-b13a-674bc58e810c",
"name": "CRM Assistant Agent",
"type": "@n8n/n8n-nodes-langchain.agent",
"position": [
208,
0
],
"parameters": {
"options": {}
},
"typeVersion": 3
},
{
"id": "5c42efa4-f4da-453b-9fee-ee2814186e7c",
"name": "OpenAI Chat Model",
"type": "@n8n/n8n-nodes-langchain.lmChatOpenAi",
"position": [
80,
208
],
"parameters": {
"model": {
"__rl": true,
"mode": "list",
"value": "gpt-4.1-mini"
},
"options": {},
"builtInTools": {}
},
"credentials": {
"openAiApi": {
"name": "<your credential>"
}
},
"typeVersion": 1.3
},
{
"id": "3c6433ae-da9b-4bc8-895b-bedcabe92207",
"name": "Conversation Memory",
"type": "@n8n/n8n-nodes-langchain.memoryBufferWindow",
"position": [
224,
208
],
"parameters": {},
"typeVersion": 1.3
},
{
"id": "78ff4f41-2b27-4871-8bbd-f60b464a5a2b",
"name": "Search Contacts",
"type": "n8n-nodes-base.airtableTool",
"position": [
368,
208
],
"parameters": {
"base": {
"__rl": true,
"mode": "list",
"value": "appXXXXXXXXXXXXXX",
"cachedResultUrl": "https://airtable.com/appXXXXXXXXXXXXXX",
"cachedResultName": "Contacts Database"
},
"table": {
"__rl": true,
"mode": "list",
"value": "tblXXXXXXXXXXXXXX",
"cachedResultUrl": "https://airtable.com/appXXXXXXXXXXXXXX/tblXXXXXXXXXXXXXX",
"cachedResultName": "Contacts"
},
"options": {},
"operation": "search"
},
"credentials": {
"airtableTokenApi": {
"name": "<your credential>"
}
},
"typeVersion": 2.1
},
{
"id": "32ee730c-f4e5-42e3-b0cc-dba03cd495fe",
"name": "Search Companies",
"type": "n8n-nodes-base.airtableTool",
"position": [
480,
144
],
"parameters": {
"base": {
"__rl": true,
"mode": "list",
"value": "appXXXXXXXXXXXXXX",
"cachedResultUrl": "https://airtable.com/appXXXXXXXXXXXXXX",
"cachedResultName": "Companies Database"
},
"table": {
"__rl": true,
"mode": "list",
"value": "tblYYYYYYYYYYYYYY",
"cachedResultUrl": "https://airtable.com/appXXXXXXXXXXXXXX/tblYYYYYYYYYYYYYY",
"cachedResultName": "Companies"
},
"options": {},
"operation": "search"
},
"credentials": {
"airtableTokenApi": {
"name": "<your credential>"
}
},
"typeVersion": 2.1
},
{
"id": "doc-note-1771263655471",
"name": "Workflow Description",
"type": "n8n-nodes-base.stickyNote",
"position": [
-700,
-150
],
"parameters": {
"width": 600,
"height": 854,
"content": "## Workflow Overview\n\nThis workflow creates an intelligent AI chat agent that can query and retrieve data from your Airtable base using natural language. Simply ask questions about your contacts or companies, and the agent will search the appropriate tables and provide answers based on your data.\n\n### First Setup\n\n**Airtable Connection:**\n1. Create a Personal Access Token at [airtable.com/create/tokens](https://airtable.com/create/tokens)\n2. Add these scopes: `data.records:read`, `data.records:write`, and `schema.bases:read`\n3. Grant access to your bases and save the token\n4. Add the token to n8n as an Airtable credential\n\n**OpenAI Connection:**\nConnect your OpenAI API account credentials in the OpenAI Chat Model node.\n\n### Configuration\n\n**Airtable Tools:**\nReconfigure both Airtable tool nodes to point to your own Airtable base and tables:\n- Update the base URL to your Airtable base\n- Set the appropriate table for Contacts searches\n- Set the appropriate table for Companies searches\n\n**Chat Model:**\nThe workflow uses GPT-4.1-mini by default, but you can select a different OpenAI model in the settings if needed.\n\nOnce published, use the chat interface to ask questions about your data in plain English!"
},
"typeVersion": 1
},
{
"id": "contact-note-1771263708644",
"name": "Creator Contact Info",
"type": "n8n-nodes-base.stickyNote",
"position": [
-700,
-610
],
"parameters": {
"color": 5,
"width": 600,
"height": 440,
"content": "# Contact Us:\n## Milan @ SmoothWork - [Book a Free Consulting Call](https://smoothwork.ai/book-a-call/)\n\n\n\n### We help businesses eliminate busywork by building compact business tools tailored to your process.\n### Contact us for customizing this, or building similar automations.\n\n\ud83d\udce7 hello@smoothwork.ai\n\u25b6\ufe0f [Check us on YouTube](https://www.youtube.com/@vasarmilan)\n\ud83d\udcde [Book a Free Consulting Call](https://smoothwork.ai/book-a-call/)\n\ud83d\udcbc [Add me on Linkedin](https://www.linkedin.com/in/mil%C3%A1n-v%C3%A1s%C3%A1rhelyi-3a9985123/)\n"
},
"typeVersion": 1
},
{
"id": "video-note-1771324743907",
"name": "Video Walkthrough",
"type": "n8n-nodes-base.stickyNote",
"position": [
-90,
-610
],
"parameters": {
"width": 420,
"height": 340,
"content": "# Video Walkthrough\n[](https://youtu.be/lQh1fuIrBN8)"
},
"typeVersion": 1
}
],
"connections": {
"Search Contacts": {
"ai_tool": [
[
{
"node": "CRM Assistant Agent",
"type": "ai_tool",
"index": 0
}
]
]
},
"Search Companies": {
"ai_tool": [
[
{
"node": "CRM Assistant Agent",
"type": "ai_tool",
"index": 0
}
]
]
},
"OpenAI Chat Model": {
"ai_languageModel": [
[
{
"node": "CRM Assistant Agent",
"type": "ai_languageModel",
"index": 0
}
]
]
},
"Conversation Memory": {
"ai_memory": [
[
{
"node": "CRM Assistant Agent",
"type": "ai_memory",
"index": 0
}
]
]
},
"When User Asks Question": {
"main": [
[
{
"node": "CRM Assistant 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.
airtableTokenApiopenAiApi
For the full experience including quality scoring and batch install features for each workflow upgrade to Pro
About this workflow
[](https://youtu.be/lQh1fuIrBN8)
Source: https://n8n.io/workflows/13459/ — 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.
✨ Intro This workflow shows how to go beyond a “plain” AI chatbot by:
Build an MCP server with Airtable. Uses chatTrigger, agent, memoryBufferWindow, mcpClientTool. Chat trigger; 13 nodes.
Build an MCP server with Airtable. Uses chatTrigger, agent, memoryBufferWindow, mcpClientTool. Chat trigger; 13 nodes.
This template is designed for anyone who wants to integrate MCP with their AI Agents using Airtable. Whether you're a developer, a data analyst, or an automation enthusiast, if you're looking to lever
🔥 AI Agent with Airtable. Uses agent, lmChatOpenAi, memoryBufferWindow, chatTrigger. Chat trigger; 11 nodes.