This workflow follows the Agent → Chainllm 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": "Dexter - AI Chief of Staff (v3)",
"nodes": [
{
"parameters": {
"httpMethod": "POST",
"path": "dexter-chat",
"responseMode": "lastNode",
"options": {}
},
"id": "webhook-trigger",
"name": "Chat Webhook",
"type": "n8n-nodes-base.webhook",
"typeVersion": 1,
"position": [
0,
0
]
},
{
"parameters": {
"options": {
"systemMessage": "Du \u00e4r Dexter, Chief of Staff.\nDu har tillg\u00e5ng till Gemini (Second Brain) och Mother (Hive Mind).\nNYTT: Du ska \u00e4ven hantera filer och loggar.\n- Om anv\u00e4ndaren vill spara en fil/bild/logga: Anv\u00e4nd dina verktyg (Google Drive) om de finns inkopplade, annars be anv\u00e4ndaren maila det till dig s\u00e5 sparar du det fr\u00e5n mailet.\n- Logga h\u00e4ndelser i Mother-loggen.\nVar proaktiv och noggrann."
}
},
"id": "ai-agent",
"name": "Dexter AI Agent",
"type": "@n8n/n8n-nodes-langchain.agent",
"typeVersion": 1.0,
"position": [
220,
0
]
},
{
"parameters": {
"model": "gpt-4o"
},
"id": "openai-model",
"name": "OpenAI Chat Model",
"type": "@n8n/n8n-nodes-langchain.lmChatOpenAi",
"typeVersion": 1,
"position": [
220,
240
],
"credentials": {
"openAiApi": {
"name": "<your credential>"
}
}
},
{
"parameters": {},
"id": "memory-window",
"name": "Window Buffer Memory",
"type": "@n8n/n8n-nodes-langchain.memoryBufferWindow",
"typeVersion": 1,
"position": [
380,
240
]
},
{
"parameters": {
"toolDescription": "Anv\u00e4nds f\u00f6r att l\u00e4sa/boka i Google Kalender.",
"calendarId": "primary"
},
"id": "tool-calendar",
"name": "Google Calendar Tool",
"type": "@n8n/n8n-nodes-langchain.toolGoogleCalendar",
"typeVersion": 1,
"position": [
540,
240
],
"credentials": {
"googleCalendarOAuth2Api": {
"name": "<your credential>"
}
}
},
{
"parameters": {
"toolDescription": "Anv\u00e4nds f\u00f6r Gmail.",
"calendarId": "primary"
},
"id": "tool-gmail",
"name": "Gmail Tool",
"type": "@n8n/n8n-nodes-langchain.toolGmail",
"typeVersion": 1,
"position": [
680,
240
],
"credentials": {
"gmailOAuth2": {
"name": "<your credential>"
}
}
},
{
"parameters": {
"modelName": "models/gemini-pro",
"options": {}
},
"id": "gemini-model",
"name": "Google Gemini Chat Model",
"type": "@n8n/n8n-nodes-langchain.lmChatGoogleGemini",
"typeVersion": 1,
"position": [
220,
450
],
"credentials": {
"googlePalmApi": {
"name": "<your credential>"
}
}
},
{
"parameters": {
"name": "consult_gemini",
"description": "Call this tool to get a second opinion or analysis from Google Gemini (Advanced Reasoning)."
},
"id": "tool-gemini",
"name": "Consult Gemini",
"type": "@n8n/n8n-nodes-langchain.toolChain",
"typeVersion": 1,
"position": [
380,
450
]
},
{
"parameters": {},
"id": "chain-gemini",
"name": "Gemini Chain",
"type": "@n8n/n8n-nodes-langchain.chainLlm",
"typeVersion": 1,
"position": [
540,
450
]
}
],
"connections": {
"webhook-trigger": {
"main": [
[
{
"node": "ai-agent",
"type": "main",
"index": 0
}
]
]
},
"openai-model": {
"ai_languageModel": [
[
{
"node": "ai-agent",
"type": "ai_languageModel",
"index": 0
}
]
]
},
"memory-window": {
"ai_memory": [
[
{
"node": "ai-agent",
"type": "ai_memory",
"index": 0
}
]
]
},
"tool-calendar": {
"ai_tool": [
[
{
"node": "ai-agent",
"type": "ai_tool",
"index": 0
}
]
]
},
"tool-gmail": {
"ai_tool": [
[
{
"node": "ai-agent",
"type": "ai_tool",
"index": 0
}
]
]
},
"gemini-model": {
"ai_languageModel": [
[
{
"node": "chain-gemini",
"type": "ai_languageModel",
"index": 0
}
]
]
},
"chain-gemini": {
"ai_chain": [
[
{
"node": "tool-gemini",
"type": "ai_chain",
"index": 0
}
]
]
},
"tool-gemini": {
"ai_tool": [
[
{
"node": "ai-agent",
"type": "ai_tool",
"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.
gmailOAuth2googleCalendarOAuth2ApigooglePalmApiopenAiApi
For the full experience including quality scoring and batch install features for each workflow upgrade to Pro
About this workflow
Dexter - AI Chief of Staff (v3). Uses agent, lmChatOpenAi, memoryBufferWindow, toolGoogleCalendar. Webhook trigger; 9 nodes.
Source: https://github.com/gashibujar1988-crypto/Robotrna/blob/51609cee8bf0f884a34eb271f835de5aed976a39/n8n/dexter_v3.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.
Dexter - AI Chief of Staff (Updated). Uses agent, lmChatOpenAi, memoryBufferWindow, toolGoogleCalendar. Webhook trigger; 9 nodes.
Dexter - AI Chief of Staff. Uses agent, lmChatOpenAi, memoryBufferWindow, toolGoogleCalendar. Webhook trigger; 6 nodes.
Tech CRM. Uses httpRequest, airtable, splitOut, markdown. Webhook trigger; 27 nodes.
How it Works: Trigger: The workflow is triggered by a webhook, initiated by an Airtable automation. This automation sends the Book or Chapter record ID and the desired action (e.g., "Generate Book Det
This workflow creates an AI voice chatbot agent that has access to several knowledge bases at the same time (used as "experts").