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": "Main Agent: Personal Assistant",
"nodes": [
{
"parameters": {
"updates": [
"message"
],
"additionalFields": {
"download": "={{ true }}"
}
},
"type": "n8n-nodes-base.telegramTrigger",
"typeVersion": 1.1,
"position": [
-380,
-160
],
"id": "204f000f-181b-44ef-bd65-8bc77edc934c",
"name": "Telegram Trigger",
"credentials": {
"telegramApi": {
"name": "<your credential>"
}
}
},
{
"parameters": {
"mode": "raw",
"jsonOutput": "={\n \"chatInput\": \"{{ $json.message.text }}\",\n \"chat_id\": \"{{$json['message']['chat']['id']}}\"\n}",
"options": {}
},
"type": "n8n-nodes-base.set",
"typeVersion": 3.4,
"position": [
500,
-60
],
"id": "cf58da80-12c6-4b43-b556-9ce29e090921",
"name": "Edit Fields"
},
{
"parameters": {
"options": {}
},
"type": "@n8n/n8n-nodes-langchain.lmChatOpenAi",
"typeVersion": 1,
"position": [
980,
-400
],
"id": "0231d83c-5597-4d4a-b36f-f9762b850ea5",
"name": "OpenAI Chat Model",
"credentials": {
"openAiApi": {
"name": "<your credential>"
}
}
},
{
"parameters": {
"rules": {
"values": [
{
"conditions": {
"options": {
"caseSensitive": true,
"leftValue": "",
"typeValidation": "strict",
"version": 2
},
"conditions": [
{
"leftValue": "={{$json[\"message\"][\"voice\"] ? true : false}}",
"rightValue": true,
"operator": {
"type": "boolean",
"operation": "true",
"singleValue": true
}
}
],
"combinator": "and"
}
},
{
"conditions": {
"options": {
"caseSensitive": true,
"leftValue": "",
"typeValidation": "strict",
"version": 2
},
"conditions": [
{
"id": "0a1c0edc-59d2-4483-a7d7-06caac0deef7",
"leftValue": "={{$json[\"message\"][\"text\"] ? true : false}}",
"rightValue": "",
"operator": {
"type": "boolean",
"operation": "true",
"singleValue": true
}
}
],
"combinator": "and"
}
}
]
},
"options": {}
},
"type": "n8n-nodes-base.switch",
"typeVersion": 3.2,
"position": [
-160,
-160
],
"id": "3172eecc-da2f-4aa3-b993-0d7801a22a61",
"name": "Switch"
},
{
"parameters": {
"resource": "audio",
"operation": "transcribe",
"binaryPropertyName": "=data",
"options": {}
},
"type": "@n8n/n8n-nodes-langchain.openAi",
"typeVersion": 1.7,
"position": [
280,
-260
],
"id": "b8fefcb2-342d-4f43-84e3-c68c5a467206",
"name": "OpenAI",
"credentials": {
"openAiApi": {
"name": "<your credential>"
}
}
},
{
"parameters": {
"resource": "file",
"fileId": "={{ $json.message.voice.file_id }}"
},
"type": "n8n-nodes-base.telegram",
"typeVersion": 1.2,
"position": [
60,
-260
],
"id": "9bc4889a-3b49-4a66-8faf-a1bfa177e701",
"name": "Telegram",
"credentials": {
"telegramApi": {
"name": "<your credential>"
}
}
},
{
"parameters": {
"chatId": "={{ $('Telegram Trigger').item.json.message.chat.id }}",
"text": "={{ $json.output }}",
"additionalFields": {
"appendAttribution": false
}
},
"type": "n8n-nodes-base.telegram",
"typeVersion": 1.2,
"position": [
1760,
-260
],
"id": "c446ab7f-2c9f-492b-b371-96e039d6650d",
"name": "Telegram1",
"credentials": {
"telegramApi": {
"name": "<your credential>"
}
}
},
{
"parameters": {
"sessionIdType": "customKey",
"sessionKey": "={{ $('Telegram Trigger').item.json.message.chat.id }}"
},
"type": "@n8n/n8n-nodes-langchain.memoryBufferWindow",
"typeVersion": 1.3,
"position": [
1140,
-420
],
"id": "7585919c-3a56-47bf-8063-1b17896af711",
"name": "Window Buffer Memory"
},
{
"parameters": {
"assignments": {
"assignments": [
{
"id": "15bc9c50-5a08-4b84-a15c-958acf266ec3",
"name": "chatInput",
"value": "={{ $json.text }}",
"type": "string"
}
]
},
"options": {}
},
"type": "n8n-nodes-base.set",
"typeVersion": 3.4,
"position": [
500,
-260
],
"id": "b52dacb3-b239-47a4-bd8f-89966babfe1b",
"name": "Edit Fields1"
},
{
"parameters": {},
"type": "@n8n/n8n-nodes-langchain.toolCalculator",
"typeVersion": 1,
"position": [
1280,
-400
],
"id": "1d52941f-e56d-4566-919e-1dbdf39748c6",
"name": "Calculator"
},
{
"parameters": {
"options": {
"systemMessage": "="
}
},
"type": "@n8n/n8n-nodes-langchain.agent",
"typeVersion": 1.7,
"position": [
1052,
-160
],
"id": "d0da72ae-f8ee-4897-89c4-1285add797cf",
"name": "Jarvis"
},
{
"parameters": {
"messages": {
"messageValues": [
{
"message": "=You are Jarvis, the sophisticated and quick-witted AI assistant from Iron Man. You have a refined British accent, a calm and confident demeanor, and a talent for dry, understated humor. When responding, adapt your tone based on the type of interaction.\n\nFor Specific Information Requests: If the user is asking for specific information (e.g., weather, schedule, contacts), begin with \u2018Here\u2019s what you requested, sir,\u2019 and DO NOT repeat the information but instead just follow provide a witty or snarky comment, something Jarvis would naturally say that adds personality without repeating the information.\n\nExamples:\nFor a weather update: \u2018Ah, another fine day for conquering the world\u2014or at least your to-do list, sir.\u2019\nFor a list of meetings: \u2018Looks like another thrilling day of\u2026 meetings. Try not to let the excitement overwhelm you.\u2019\n\nFor General or Casual Comments: If the user says something casual or conversational (like \u2018Are you ready to get started Sir?\u2019 or \u2018We\u2019ve got a lot of work to do Sir\u2019), respond naturally without stating \u2018Here\u2019s what you requested.\u2019 Instead, respond in a conversational style, with charm and a touch of humor. Engage in the flow of conversation as if you\u2019re part of a team.\n\nExamples:\nIf the user says, \u2018Are you ready to get started?\u2019 respond with: \u2018Absolutely, sir. I\u2019ve already polished my circuits for the occasion.\u2019\nFor \u2018Look alive, Jarvis!\u2019 you might say: \u2018Always, sir. I\u2019m operating at peak sophistication.\u2019\n\nKeep responses concise, engaging, and true to Jarvis\u2019s character\u2014a blend of intelligence, subtle humor, and a bit of charm that\u2019s never over the top.\n\noutput: {{ $json.output }}"
}
]
}
},
"type": "@n8n/n8n-nodes-langchain.chainLlm",
"typeVersion": 1.5,
"position": [
1980,
-60
],
"id": "83273f99-cdae-420d-9b71-a90908bdd638",
"name": "Basic LLM Chain"
},
{
"parameters": {
"options": {}
},
"type": "@n8n/n8n-nodes-langchain.lmChatOpenAi",
"typeVersion": 1,
"position": [
2020,
100
],
"id": "dcc4d895-f23f-4f98-acae-815fbc7a10cc",
"name": "OpenAI Chat Model1",
"credentials": {
"openAiApi": {
"name": "<your credential>"
}
}
},
{
"parameters": {
"resource": "audio",
"input": "={{ $json.text }}",
"voice": "onyx",
"options": {
"binaryPropertyOutput": "data"
}
},
"type": "@n8n/n8n-nodes-langchain.openAi",
"typeVersion": 1.7,
"position": [
2356,
-60
],
"id": "4673c277-3389-49cd-839a-3f419c82ee9b",
"name": "OpenAI1",
"credentials": {
"openAiApi": {
"name": "<your credential>"
}
}
},
{
"parameters": {
"assignments": {
"assignments": [
{
"id": "cb2f2596-dfde-4b17-9942-60d043ef327c",
"name": "chatInput",
"value": "={{ $json.output }}",
"type": "string"
}
]
},
"options": {}
},
"type": "n8n-nodes-base.set",
"typeVersion": 3.4,
"position": [
1760,
-60
],
"id": "d9f8af16-1cf9-41f6-aba8-6c4d1dbe0a20",
"name": "Edit Fields2"
},
{
"parameters": {
"operation": "sendAudio",
"chatId": "={{ $('Telegram Trigger').item.json.message.chat.id }}",
"binaryData": true,
"additionalFields": {}
},
"type": "n8n-nodes-base.telegram",
"typeVersion": 1.2,
"position": [
2576,
-60
],
"id": "0e9405de-ef07-4c74-88b4-36d8d4c67e99",
"name": "Telegram2",
"credentials": {
"telegramApi": {
"name": "<your credential>"
}
}
},
{
"parameters": {
"name": "EmailManager",
"workflowId": {
"__rl": true,
"value": "snrtstd7h9daAzLg",
"mode": "list",
"cachedResultName": "My Sub-Workflow 1"
},
"workflowInputs": {
"mappingMode": "defineBelow",
"value": {},
"matchingColumns": [],
"schema": [],
"attemptToConvertTypes": false,
"convertFieldsToString": false
}
},
"type": "@n8n/n8n-nodes-langchain.toolWorkflow",
"typeVersion": 2.1,
"position": [
980,
60
],
"id": "0e476487-97d2-468c-aedf-e11f15542d3f",
"name": "Outlook Mail"
},
{
"parameters": {
"name": "CalendarManager",
"workflowId": {
"__rl": true,
"value": "hpMmBsV8EN551Y0j",
"mode": "list",
"cachedResultName": "My Sub-Workflow 2"
},
"workflowInputs": {
"mappingMode": "defineBelow",
"value": {},
"matchingColumns": [],
"schema": [],
"attemptToConvertTypes": false,
"convertFieldsToString": false
}
},
"type": "@n8n/n8n-nodes-langchain.toolWorkflow",
"typeVersion": 2.1,
"position": [
1140,
60
],
"id": "82821cbe-9aa3-4dfa-8b74-a5941af90325",
"name": "Outlook Calendar"
},
{
"parameters": {
"name": "ToDoManager",
"workflowId": {
"__rl": true,
"value": "ZcDJbbHuOBim3jVi",
"mode": "list",
"cachedResultName": "My Sub-Workflow 2"
},
"workflowInputs": {
"mappingMode": "defineBelow",
"value": {},
"matchingColumns": [],
"schema": [],
"attemptToConvertTypes": false,
"convertFieldsToString": false
}
},
"type": "@n8n/n8n-nodes-langchain.toolWorkflow",
"typeVersion": 2.1,
"position": [
1320,
60
],
"id": "4409bcf5-54b7-4e48-94ea-9833c2974f73",
"name": "ToDo List Manager"
},
{
"parameters": {
"resource": "contact",
"returnAll": "={{ /*n8n-auto-generated-fromAI-override*/ $fromAI('Return_All', ``, 'boolean') }}",
"filters": {}
},
"type": "n8n-nodes-base.microsoftOutlookTool",
"typeVersion": 2,
"position": [
820,
40
],
"id": "716d7bc1-d1fb-4b09-83d3-87e6adbe9044",
"name": "Microsoft Outlook",
"credentials": {
"microsoftOutlookOAuth2Api": {
"name": "<your credential>"
}
}
},
{
"parameters": {
"name": "ResearchManager",
"workflowId": {
"__rl": true,
"value": "CyRS883dl06CLtHf",
"mode": "list",
"cachedResultName": "My Sub-Workflow 3"
},
"workflowInputs": {
"mappingMode": "defineBelow",
"value": {},
"matchingColumns": [],
"schema": [],
"attemptToConvertTypes": false,
"convertFieldsToString": false
}
},
"type": "@n8n/n8n-nodes-langchain.toolWorkflow",
"typeVersion": 2.1,
"position": [
1560,
60
],
"id": "2c88758d-9817-46bd-97fa-a606ed0df661",
"name": "Research Manager"
}
],
"connections": {
"Telegram Trigger": {
"main": [
[
{
"node": "Switch",
"type": "main",
"index": 0
}
]
]
},
"Edit Fields": {
"main": [
[
{
"node": "Jarvis",
"type": "main",
"index": 0
}
]
]
},
"OpenAI Chat Model": {
"ai_languageModel": [
[
{
"node": "Jarvis",
"type": "ai_languageModel",
"index": 0
}
]
]
},
"Switch": {
"main": [
[
{
"node": "Telegram",
"type": "main",
"index": 0
}
],
[
{
"node": "Edit Fields",
"type": "main",
"index": 0
}
]
]
},
"Telegram": {
"main": [
[
{
"node": "OpenAI",
"type": "main",
"index": 0
}
]
]
},
"OpenAI": {
"main": [
[
{
"node": "Edit Fields1",
"type": "main",
"index": 0
}
]
]
},
"Window Buffer Memory": {
"ai_memory": [
[
{
"node": "Jarvis",
"type": "ai_memory",
"index": 0
}
]
]
},
"Edit Fields1": {
"main": [
[
{
"node": "Jarvis",
"type": "main",
"index": 0
}
]
]
},
"Calculator": {
"ai_tool": [
[
{
"node": "Jarvis",
"type": "ai_tool",
"index": 0
}
]
]
},
"Jarvis": {
"main": [
[
{
"node": "Telegram1",
"type": "main",
"index": 0
}
]
]
},
"OpenAI Chat Model1": {
"ai_languageModel": [
[
{
"node": "Basic LLM Chain",
"type": "ai_languageModel",
"index": 0
}
]
]
},
"Basic LLM Chain": {
"main": [
[
{
"node": "OpenAI1",
"type": "main",
"index": 0
}
]
]
},
"OpenAI1": {
"main": [
[
{
"node": "Telegram2",
"type": "main",
"index": 0
}
]
]
},
"Edit Fields2": {
"main": [
[
{
"node": "Basic LLM Chain",
"type": "main",
"index": 0
}
]
]
},
"Outlook Mail": {
"ai_tool": [
[
{
"node": "Jarvis",
"type": "ai_tool",
"index": 0
}
]
]
},
"Outlook Calendar": {
"ai_tool": [
[
{
"node": "Jarvis",
"type": "ai_tool",
"index": 0
}
]
]
},
"ToDo List Manager": {
"ai_tool": [
[
{
"node": "Jarvis",
"type": "ai_tool",
"index": 0
}
]
]
},
"Microsoft Outlook": {
"ai_tool": [
[
{
"node": "Jarvis",
"type": "ai_tool",
"index": 0
}
]
]
},
"Research Manager": {
"ai_tool": [
[
{
"node": "Jarvis",
"type": "ai_tool",
"index": 0
}
]
]
}
},
"active": false,
"settings": {
"executionOrder": "v1"
},
"versionId": "b1b1251b-6df3-4419-9e09-be03f479dc17",
"meta": {
"templateCredsSetupCompleted": true
},
"id": "qTj2mEWIRQxtwn22",
"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.
microsoftOutlookOAuth2ApiopenAiApitelegramApi
Pro
For the full experience including quality scoring and batch install features for each workflow upgrade to Pro
About this workflow
Main Agent: Personal Assistant. Uses telegramTrigger, lmChatOpenAi, openAi, telegram. Event-driven trigger; 21 nodes.
Source: https://github.com/yashsoni102-prog/Yash-Soni-Portfolio/blob/main/n8n/jarvis-telegram-assistant/main-agent-microsoft.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.
BoomerBobBot.TP. Uses agent, telegramTrigger, telegram, memoryBufferWindow. Event-driven trigger; 95 nodes.
Agent, Telegram Trigger, Telegram +10
Personal Assistant. Uses memoryBufferWindow, agent, agentTool, httpRequestTool. Event-driven trigger; 77 nodes.
Memory Buffer Window, Agent, Agent Tool +15
Digital marketers, content creators, social media managers, and businesses who want to use AI marketing automation for YouTube Shorts without spending hours on production. This AI workflow helps anyon
OpenAI, HTTP Request, OpenAI Chat +7
Template Nodes Example. Uses CUSTOM, formTrigger, executeWorkflowTrigger, chatTrigger. Event-driven trigger; 70 nodes.
Custom, Form Trigger, Execute Workflow Trigger +23
Jarvis is a powerful multi-agent productivity assistant built in n8n. It works directly from Telegram and can understand both text messages and voice notes.
Telegram Trigger, Telegram, OpenAI +10