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 →
{
"name": "Think Agents",
"nodes": [
{
"parameters": {
"options": {
"systemMessage": "=# Overview\nYou are a helpful assistant.\n\n## Tool\nThink - Use this tool to think deeply"
}
},
"type": "@n8n/n8n-nodes-langchain.agent",
"typeVersion": 1.8,
"position": [
-160,
-280
],
"id": "e81e5558-dbc8-4ae3-9918-8d10be8d726f",
"name": "Think Agent"
},
{
"parameters": {
"options": {}
},
"type": "@n8n/n8n-nodes-langchain.chatTrigger",
"typeVersion": 1.1,
"position": [
-340,
-280
],
"id": "85e43887-021c-4405-baab-0a37fb698f8e",
"name": "When chat message received"
},
{
"parameters": {},
"type": "@n8n/n8n-nodes-langchain.toolThink",
"typeVersion": 1,
"position": [
100,
60
],
"id": "75a35571-844c-4460-83e8-ab95dc931694",
"name": "Think"
},
{
"parameters": {
"model": {
"__rl": true,
"value": "claude-3-5-sonnet-20241022",
"mode": "list",
"cachedResultName": "Claude 3.5 Sonnet (New)"
},
"options": {}
},
"type": "@n8n/n8n-nodes-langchain.lmChatAnthropic",
"typeVersion": 1.3,
"position": [
-200,
60
],
"id": "e0bf7c2b-d4cc-49a6-8c30-a68f1e05e465",
"name": "Claude 3.5 Sonnet",
"credentials": {
"anthropicApi": {
"name": "<your credential>"
}
}
},
{
"parameters": {
"content": "# Think",
"height": 240,
"width": 280,
"color": 4
},
"type": "n8n-nodes-base.stickyNote",
"typeVersion": 1,
"position": [
0,
-40
],
"id": "074bd63b-587a-4b06-8a91-931422e12130",
"name": "Sticky Note"
},
{
"parameters": {
"content": "# Models\n",
"height": 240,
"width": 420,
"color": 5
},
"type": "n8n-nodes-base.stickyNote",
"typeVersion": 1,
"position": [
-440,
-40
],
"id": "01a2cd99-d489-4c84-8233-ff877ec11014",
"name": "Sticky Note1"
},
{
"parameters": {
"content": "# Agent\n",
"height": 320,
"width": 720
},
"type": "n8n-nodes-base.stickyNote",
"typeVersion": 1,
"position": [
-440,
-380
],
"id": "726debc9-7901-4396-aad9-c4979ec0560c",
"name": "Sticky Note2"
},
{
"parameters": {
"model": {
"__rl": true,
"value": "gpt-4.1-mini",
"mode": "list",
"cachedResultName": "gpt-4.1-mini"
},
"options": {}
},
"type": "@n8n/n8n-nodes-langchain.lmChatOpenAi",
"typeVersion": 1.2,
"position": [
-360,
60
],
"id": "a48afbea-028d-4370-9275-e3bc47189143",
"name": "GPT 4.1",
"credentials": {
"openAiApi": {
"name": "<your credential>"
}
}
},
{
"parameters": {
"model": {
"__rl": true,
"value": "gpt-4.1",
"mode": "list",
"cachedResultName": "gpt-4.1"
},
"options": {}
},
"type": "@n8n/n8n-nodes-langchain.lmChatOpenAi",
"typeVersion": 1.2,
"position": [
640,
-160
],
"id": "f898ba75-bcca-4d1b-b9b1-021cfb8ab4fb",
"name": "GPT-4.1",
"credentials": {
"openAiApi": {
"name": "<your credential>"
}
}
},
{
"parameters": {
"mode": "retrieve-as-tool",
"toolName": "knowledge_base",
"toolDescription": "Use this tool to access company policies and FAQs",
"pineconeIndex": {
"__rl": true,
"value": "sample",
"mode": "list",
"cachedResultName": "sample"
},
"options": {
"pineconeNamespace": "FAQ"
}
},
"type": "@n8n/n8n-nodes-langchain.vectorStorePinecone",
"typeVersion": 1.1,
"position": [
1120,
-160
],
"id": "7a95a23f-7bb2-4d14-95ef-cdde732a3378",
"name": "knowlege_base",
"credentials": {
"pineconeApi": {
"name": "<your credential>"
}
}
},
{
"parameters": {
"options": {}
},
"type": "@n8n/n8n-nodes-langchain.embeddingsOpenAi",
"typeVersion": 1.2,
"position": [
1120,
20
],
"id": "7bbaa8c7-335b-4b1f-b9f2-33df2c45331b",
"name": "Embeddings OpenAI",
"credentials": {
"openAiApi": {
"name": "<your credential>"
}
}
},
{
"parameters": {
"sendTo": "={{ /*n8n-auto-generated-fromAI-override*/ $fromAI('To', ``, 'string') }}",
"subject": "={{ /*n8n-auto-generated-fromAI-override*/ $fromAI('Subject', ``, 'string') }}",
"emailType": "text",
"message": "={{ /*n8n-auto-generated-fromAI-override*/ $fromAI('Message', `sign off emails as \"Nate\"`, 'string') }}",
"options": {
"appendAttribution": false
}
},
"type": "n8n-nodes-base.gmailTool",
"typeVersion": 2.1,
"position": [
1420,
-160
],
"id": "988f9d6c-d1e6-4707-bf03-db811aac45a1",
"name": "Send Email",
"credentials": {
"gmailOAuth2": {
"name": "<your credential>"
}
}
},
{
"parameters": {
"operation": "search",
"base": {
"__rl": true,
"value": "appK0rbtvf9e7vt6w",
"mode": "list",
"cachedResultName": "Contacts",
"cachedResultUrl": "https://airtable.com/appK0rbtvf9e7vt6w"
},
"table": {
"__rl": true,
"value": "tbl08JGCfUK1RhXsG",
"mode": "list",
"cachedResultName": "Contacts",
"cachedResultUrl": "https://airtable.com/appK0rbtvf9e7vt6w/tbl08JGCfUK1RhXsG"
},
"options": {}
},
"type": "n8n-nodes-base.airtableTool",
"typeVersion": 2.1,
"position": [
1560,
-160
],
"id": "25117100-7ed3-4be0-9c68-dedba5295072",
"name": "Contacts",
"credentials": {
"airtableTokenApi": {
"name": "<your credential>"
}
}
},
{
"parameters": {
"toolDescription": "Use this tool to search the web",
"method": "POST",
"url": "https://api.tavily.com/search",
"authentication": "genericCredentialType",
"genericAuthType": "httpHeaderAuth",
"sendBody": true,
"specifyBody": "json",
"jsonBody": "{\n \"query\": \"{searchTerm}\",\n \"topic\": \"general\",\n \"search_depth\": \"basic\",\n \"chunks_per_source\": 3,\n \"max_results\": 1,\n \"time_range\": null,\n \"days\": 7,\n \"include_answer\": true,\n \"include_raw_content\": false,\n \"include_images\": false,\n \"include_image_descriptions\": false,\n \"include_domains\": [],\n \"exclude_domains\": []\n}",
"placeholderDefinitions": {
"values": [
{
"name": "searchTerm",
"description": "What the user is requesting to search the web for"
}
]
}
},
"type": "@n8n/n8n-nodes-langchain.toolHttpRequest",
"typeVersion": 1.1,
"position": [
1720,
-160
],
"id": "a386616a-026e-404c-9952-f5812f889634",
"name": "Web Search",
"credentials": {
"httpHeaderAuth": {
"name": "<your credential>"
}
}
},
{
"parameters": {
"modelName": "models/gemini-2.0-flash",
"options": {}
},
"type": "@n8n/n8n-nodes-langchain.lmChatGoogleGemini",
"typeVersion": 1,
"position": [
480,
-160
],
"id": "3b398e05-4ce2-4b5c-aafc-56ecc89ffadf",
"name": "2.0 Flash",
"credentials": {
"googlePalmApi": {
"name": "<your credential>"
}
}
},
{
"parameters": {},
"type": "@n8n/n8n-nodes-langchain.toolThink",
"typeVersion": 1,
"position": [
980,
-160
],
"id": "4c038ebb-14eb-4901-add8-c1acd5b07227",
"name": "Think1"
},
{
"parameters": {
"options": {
"systemMessage": "=# Overview\nYou are a helpful assistant.\n\n## Tools\nThink - Use this tool to think deeply when you run into an issue before asking the user \nContacts - Use this tool to lookup contact information like an email address.\nSend Email - Use this tool to send an email\nWeb Search - Use this to search the internet. \nknowledge_base - Use this tool to lookup internal policies of FAQs\n\n## Instructions\n1) Call the neccessary tools based on the user request\n2) Use the \"Think\" tool to verify you took the right steps\n\n## Important\n- Never make up an email address. If you can't find it, think about what you should do."
}
},
"type": "@n8n/n8n-nodes-langchain.agent",
"typeVersion": 1.8,
"position": [
1000,
-380
],
"id": "f7af93ef-cca7-46a5-80d7-1786f86f8b7b",
"name": "Think Agent1"
},
{
"parameters": {
"model": {
"__rl": true,
"value": "claude-3-5-sonnet-20241022",
"mode": "list",
"cachedResultName": "Claude 3.5 Sonnet (New)"
},
"options": {}
},
"type": "@n8n/n8n-nodes-langchain.lmChatAnthropic",
"typeVersion": 1.3,
"position": [
820,
-160
],
"id": "f10585a5-4f95-4077-882f-fc3b2c0d4bf5",
"name": "Claude 3.5 Sonnet1",
"credentials": {
"anthropicApi": {
"name": "<your credential>"
}
}
},
{
"parameters": {
"content": "# Example 2) Tool Calling",
"height": 680,
"width": 1620,
"color": 5
},
"type": "n8n-nodes-base.stickyNote",
"typeVersion": 1,
"position": [
340,
-480
],
"id": "7c35e651-37ef-494a-b62f-ab3e1b9e4ff1",
"name": "Sticky Note3"
},
{
"parameters": {
"content": "# Example 1) Riddles\n",
"height": 80,
"width": 720,
"color": 5
},
"type": "n8n-nodes-base.stickyNote",
"typeVersion": 1,
"position": [
-440,
-480
],
"id": "3cfcc85c-63b0-4ba1-9434-7bbea3709dbd",
"name": "Sticky Note4"
},
{
"parameters": {
"name": "quoter",
"description": "Use this tool to get a quote. Send over the number of guests and the dates requested.",
"workflowId": {
"__rl": true,
"value": "QpmzSqqw8uCpUTF1",
"mode": "list",
"cachedResultName": "Quoter"
},
"workflowInputs": {
"mappingMode": "defineBelow",
"value": {},
"matchingColumns": [],
"schema": [],
"attemptToConvertTypes": false,
"convertFieldsToString": false
}
},
"type": "@n8n/n8n-nodes-langchain.toolWorkflow",
"typeVersion": 2.1,
"position": [
2700,
-40
],
"id": "89a73e17-6231-4ab4-81e5-d0a6d623aa93",
"name": "quoter"
},
{
"parameters": {
"name": "availability",
"description": "Call this tool to get availability information. Only send over the dates the user requested.",
"workflowId": {
"__rl": true,
"value": "NxuKUt5jT8TDOtXs",
"mode": "list",
"cachedResultName": "Availability"
},
"workflowInputs": {
"mappingMode": "defineBelow",
"value": {},
"matchingColumns": [],
"schema": [],
"attemptToConvertTypes": false,
"convertFieldsToString": false
}
},
"type": "@n8n/n8n-nodes-langchain.toolWorkflow",
"typeVersion": 2.1,
"position": [
2840,
-40
],
"id": "d13b60f3-7501-44ff-9a8e-fea2e5d94ffe",
"name": "availability"
},
{
"parameters": {
"model": {
"__rl": true,
"value": "gpt-4.1",
"mode": "list",
"cachedResultName": "gpt-4.1"
},
"options": {}
},
"type": "@n8n/n8n-nodes-langchain.lmChatOpenAi",
"typeVersion": 1.2,
"position": [
2420,
-60
],
"id": "69041381-8c76-47c3-a7eb-de153d4642cf",
"name": "GPT-4.",
"credentials": {
"openAiApi": {
"name": "<your credential>"
}
}
},
{
"parameters": {
"options": {
"systemMessage": "=# Overview\nYou are a helpful assistant.\n\n## Instructions\n1) Send the requested dates to the availability tool\n2) Send the requested dates and number of guests to the quoter tool\n3) Use the think tool to verify everything has been done correctly. There should be a quote and an availability status\n"
}
},
"type": "@n8n/n8n-nodes-langchain.agent",
"typeVersion": 1.8,
"position": [
2180,
-300
],
"id": "42fbb926-0a0f-4ef2-b643-b00842342f17",
"name": "Think Agent2"
},
{
"parameters": {
"modelName": "models/gemini-2.0-flash",
"options": {}
},
"type": "@n8n/n8n-nodes-langchain.lmChatGoogleGemini",
"typeVersion": 1,
"position": [
2120,
-60
],
"id": "f9007af5-a6df-4d92-94c9-8c93d6384ee3",
"name": "2.0 Flash1",
"credentials": {
"googlePalmApi": {
"name": "<your credential>"
}
}
},
{
"parameters": {
"model": {
"__rl": true,
"value": "claude-3-5-sonnet-20241022",
"mode": "list",
"cachedResultName": "Claude 3.5 Sonnet (New)"
},
"options": {}
},
"type": "@n8n/n8n-nodes-langchain.lmChatAnthropic",
"typeVersion": 1.3,
"position": [
2280,
-60
],
"id": "aabd014f-e372-49e1-8d34-f4825515b37d",
"name": "Claude 3.5 Sonnet2",
"credentials": {
"anthropicApi": {
"name": "<your credential>"
}
}
},
{
"parameters": {},
"type": "@n8n/n8n-nodes-langchain.toolThink",
"typeVersion": 1,
"position": [
3080,
-40
],
"id": "b8b9d564-d535-4a05-b4ee-459a98ef36f4",
"name": "Think2"
},
{
"parameters": {
"content": "# Tools\n",
"height": 220,
"width": 340,
"color": 5
},
"type": "n8n-nodes-base.stickyNote",
"typeVersion": 1,
"position": [
2640,
-120
],
"id": "2b539dec-28ea-43f7-8f8a-19857bce6ba3",
"name": "Sticky Note5"
},
{
"parameters": {
"content": "# Think",
"height": 220,
"color": 4
},
"type": "n8n-nodes-base.stickyNote",
"typeVersion": 1,
"position": [
3000,
-120
],
"id": "6aa4f533-64de-4c4a-b645-99188e7a1d31",
"name": "Sticky Note6"
},
{
"parameters": {
"content": "# Models\n",
"height": 220,
"width": 600
},
"type": "n8n-nodes-base.stickyNote",
"typeVersion": 1,
"position": [
2020,
-120
],
"id": "cf0dead8-2420-403f-bf4c-ee3faffd588f",
"name": "Sticky Note7"
},
{
"parameters": {
"content": "# Think Agent\n",
"height": 240,
"width": 600,
"color": 6
},
"type": "n8n-nodes-base.stickyNote",
"typeVersion": 1,
"position": [
2020,
-380
],
"id": "a719f989-ec66-4a6a-bce3-69aab8e5735b",
"name": "Sticky Note8"
},
{
"parameters": {
"content": "# Example 3) Sub-workflows\n",
"height": 80,
"width": 600,
"color": 5
},
"type": "n8n-nodes-base.stickyNote",
"typeVersion": 1,
"position": [
2020,
-480
],
"id": "d9a267c6-ccd9-4663-99de-073a6552595e",
"name": "Sticky Note9"
},
{
"parameters": {
"inputSource": "passthrough"
},
"type": "n8n-nodes-base.executeWorkflowTrigger",
"typeVersion": 1.1,
"position": [
2080,
220
],
"id": "526d585e-e851-4016-9521-6854ba1d11f7",
"name": "When Executed by Another Workflow"
},
{
"parameters": {
"modelId": {
"__rl": true,
"value": "gpt-4.1-nano",
"mode": "list",
"cachedResultName": "GPT-4.1-NANO"
},
"messages": {
"values": [
{
"content": "={{ $json.query }}"
},
{
"content": "Based on the incoming information, please provide a quote.\n\nThe quote should be $500 per person, per day.",
"role": "system"
}
]
},
"options": {}
},
"type": "@n8n/n8n-nodes-langchain.openAi",
"typeVersion": 1.8,
"position": [
2320,
220
],
"id": "acaf7ac9-4055-4fd3-b795-0dab55d09cc7",
"name": "Quoter",
"credentials": {
"openAiApi": {
"name": "<your credential>"
}
}
},
{
"parameters": {
"modelId": {
"__rl": true,
"value": "gpt-4.1-nano",
"mode": "list",
"cachedResultName": "GPT-4.1-NANO"
},
"messages": {
"values": [
{
"content": "={{ $json.query }}"
},
{
"content": "Based on the incoming information, please provide availability.\n\nAssume that all dates are currently available.",
"role": "system"
}
]
},
"options": {}
},
"type": "@n8n/n8n-nodes-langchain.openAi",
"typeVersion": 1.8,
"position": [
2340,
500
],
"id": "afd5f719-149a-4596-a54d-55aa18a16503",
"name": "Availability",
"credentials": {
"openAiApi": {
"name": "<your credential>"
}
}
},
{
"parameters": {
"content": "## Quoter",
"height": 280,
"width": 660,
"color": 2
},
"type": "n8n-nodes-base.stickyNote",
"typeVersion": 1,
"position": [
2020,
120
],
"id": "0c4471fb-ce96-484c-be21-19a34b2bcf49",
"name": "Sticky Note10"
},
{
"parameters": {
"content": "## Availability",
"height": 280,
"width": 660,
"color": 2
},
"type": "n8n-nodes-base.stickyNote",
"typeVersion": 1,
"position": [
2020,
420
],
"id": "57b4ff97-8be3-4752-ae1f-aee42ad8d0be",
"name": "Sticky Note11"
},
{
"parameters": {
"content": "# \ud83d\udee0\ufe0f Setup Guide \n**Author:** [Nate Herk](https://www.youtube.com/@nateherk)\n\n1. **Connect the Chat Trigger** \n Plug the Chat Trigger into whichever agent you want to use.\n\n2. **Assign the Correct Model** \n Ensure you're using the correct chat model for the agent. Double-check which model is being passed into the agent node.\n\n3. **Add Credentials** \n Make sure all relevant credentials are configured:\n - Your chat models (e.g. OpenAI, Claude, etc.)\n - Any external tools or services used by the agent\n\n4. **Sub-Workflows Setup** \n For sub-workflows like **Quoter** and **Availability**:\n - Each should be placed in its **own separate workflow**\n - Each must begin with a **\"When Executed by Another Workflow\"** trigger node\n - Use the same pattern shown in the template (e.g. how the Quoter is triggered)\n\n\u2705 Once everything is connected and credentialed properly, you\u2019re good to go!\n",
"height": 520,
"width": 600
},
"type": "n8n-nodes-base.stickyNote",
"typeVersion": 1,
"position": [
-440,
-1040
],
"id": "8dd7bce7-b656-4012-876c-fc6123c7e031",
"name": "Sticky Note12"
}
],
"connections": {
"When chat message received": {
"main": [
[
{
"node": "Think Agent",
"type": "main",
"index": 0
}
]
]
},
"Think": {
"ai_tool": [
[
{
"node": "Think Agent",
"type": "ai_tool",
"index": 0
}
]
]
},
"Claude 3.5 Sonnet": {
"ai_languageModel": [
[]
]
},
"GPT 4.1": {
"ai_languageModel": [
[
{
"node": "Think Agent",
"type": "ai_languageModel",
"index": 0
}
]
]
},
"knowlege_base": {
"ai_tool": [
[
{
"node": "Think Agent1",
"type": "ai_tool",
"index": 0
}
]
]
},
"Embeddings OpenAI": {
"ai_embedding": [
[
{
"node": "knowlege_base",
"type": "ai_embedding",
"index": 0
}
]
]
},
"Send Email": {
"ai_tool": [
[
{
"node": "Think Agent1",
"type": "ai_tool",
"index": 0
}
]
]
},
"Contacts": {
"ai_tool": [
[
{
"node": "Think Agent1",
"type": "ai_tool",
"index": 0
}
]
]
},
"Web Search": {
"ai_tool": [
[
{
"node": "Think Agent1",
"type": "ai_tool",
"index": 0
}
]
]
},
"Think1": {
"ai_tool": [
[
{
"node": "Think Agent1",
"type": "ai_tool",
"index": 0
}
]
]
},
"Claude 3.5 Sonnet1": {
"ai_languageModel": [
[
{
"node": "Think Agent1",
"type": "ai_languageModel",
"index": 0
}
]
]
},
"quoter": {
"ai_tool": [
[
{
"node": "Think Agent2",
"type": "ai_tool",
"index": 0
}
]
]
},
"availability": {
"ai_tool": [
[
{
"node": "Think Agent2",
"type": "ai_tool",
"index": 0
}
]
]
},
"GPT-4.": {
"ai_languageModel": [
[
{
"node": "Think Agent2",
"type": "ai_languageModel",
"index": 0
}
]
]
},
"Think2": {
"ai_tool": [
[
{
"node": "Think Agent2",
"type": "ai_tool",
"index": 0
}
]
]
},
"When Executed by Another Workflow": {
"main": [
[
{
"node": "Quoter",
"type": "main",
"index": 0
}
]
]
}
},
"active": false,
"settings": {
"executionOrder": "v1"
},
"versionId": "08118a04-b641-4612-a39d-2db7eeeac6c9",
"meta": {
"templateCredsSetupCompleted": true
},
"id": "uKbrAfdWLTpt5fhU",
"tags": []
}
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.
airtableTokenApianthropicApigmailOAuth2googlePalmApihttpHeaderAuthopenAiApipineconeApi
Pro
For the full experience including quality scoring and batch install features for each workflow upgrade to Pro
How this works
This workflow empowers you to build intelligent conversational agents that reason step-by-step and execute tasks autonomously, saving hours on repetitive customer support or data analysis. It's ideal for developers, marketers, or operations teams seeking to automate complex interactions without coding from scratch. The core chain begins with a chat trigger capturing user messages, then feeds them into the Think Agent node, which leverages tools like toolThink and language models such as Claude 3.5 Sonnet or GPT-4 for thoughtful responses, optionally storing context in Pinecone vector stores for continuity.
Use this when handling dynamic queries requiring multi-step reasoning, like generating personalised reports from chat inputs or integrating with external APIs for real-time decisions. Avoid it for simple rule-based automations, where basic if-then logic suffices, or high-volume transactions needing ultra-low latency. Common variations include swapping Anthropic for OpenAI models to tweak creativity levels, or adding custom tools for domain-specific actions like CRM updates.
About this workflow
Think Agents. Uses agent, chatTrigger, toolThink, lmChatAnthropic. Chat trigger; 38 nodes.
Source: https://github.com/Zie619/n8n-workflows — 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 workflow acts as a 24/7 sales agent, engaging leads across WhatsApp, Instagram, Facebook, Telegram, and your website. It intelligently transcribes audio messages, answers questions using a knowle
Chat Trigger, Memory Postgres Chat, Tool Workflow +20
• Create a Google Drive folder to watch. • Connect your Google Drive account in n8n and authorize access. • Point the Google Drive Trigger node to this folder (new/modified files trigger the flow).
Agent, Chat Trigger, Memory Buffer Window +14
The workflow operates through a three-step process that handles incoming chat messages with intelligent tool orchestration: Message Trigger: The node triggers whenever a user message arrives and passe
Chat Trigger, Memory Postgres Chat, OpenAI Embeddings +16
Build an All-Source Knowledge Assistant with Claude, RAG, Perplexity, and Drive. Uses chatTrigger, memoryPostgresChat, embeddingsOpenAi, rerankerCohere. Chat trigger; 40 nodes.
Chat Trigger, Memory Postgres Chat, OpenAI Embeddings +16
Advanced Ai Demo Presented At Ai Developers 14 Meetup. Uses slack, stickyNote, textSplitterRecursiveCharacterTextSplitter, embeddingsOpenAi. Chat trigger; 39 nodes.
Slack, Text Splitter Recursive Character Text Splitter, OpenAI Embeddings +14