Roshan Ramani This workflow corresponds to n8n.io template #6026 — we link there as the canonical source.
This workflow follows the Agent → Gmail 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 →
{
"id": "gXutAybKcZqblZjF",
"meta": {
"templateCredsSetupCompleted": true
},
"name": "AI Email Reply Assistant with Telegram Approval",
"tags": [],
"nodes": [
{
"id": "a29a7c9c-cab6-479a-89f3-71c0abf02727",
"name": "Structured Output Parser1",
"type": "@n8n/n8n-nodes-langchain.outputParserStructured",
"position": [
680,
1140
],
"parameters": {
"jsonSchemaExample": "{\n \"email\": \"email address\",\n \"subject\": \"subject text\",\n \"body\": \" body text .\"\n}\n"
},
"typeVersion": 1.2
},
{
"id": "954febca-8faf-4899-838f-854a5c344b97",
"name": "Send a message",
"type": "n8n-nodes-base.gmail",
"position": [
1340,
820
],
"parameters": {
"sendTo": "={{ $('AI: Generate Email Reply').item.json.output.email }}",
"message": "={{ $('AI: Generate Email Reply').item.json.output.body }}",
"options": {},
"subject": "={{ $('AI: Generate Email Reply').item.json.output.subject }}",
"emailType": "text"
},
"credentials": {
"gmailOAuth2": {
"name": "<your credential>"
}
},
"typeVersion": 2.1
},
{
"id": "feff315f-c008-4b67-bd89-0d88c79005ac",
"name": "Trigger: New Email",
"type": "n8n-nodes-base.gmailTrigger",
"position": [
-1000,
960
],
"parameters": {
"simple": false,
"filters": {},
"options": {},
"pollTimes": {
"item": [
{
"mode": "everyMinute"
}
]
}
},
"credentials": {
"gmailOAuth2": {
"name": "<your credential>"
}
},
"typeVersion": 1.1
},
{
"id": "b69c3e8d-cd36-4c72-8a8d-006dddd0280c",
"name": "Check: Is Email in Inbox?",
"type": "n8n-nodes-base.if",
"position": [
-780,
960
],
"parameters": {
"options": {},
"conditions": {
"options": {
"version": 2,
"leftValue": "",
"caseSensitive": true,
"typeValidation": "strict"
},
"combinator": "and",
"conditions": [
{
"id": "3f7094d8-2756-493d-8721-be7d4c83297b",
"operator": {
"type": "array",
"operation": "contains",
"rightType": "any"
},
"leftValue": "={{ $json.labelIds }}",
"rightValue": "INBOX"
}
]
}
},
"typeVersion": 2.2
},
{
"id": "3cc06ffd-8a5d-4daf-a4c1-55953fba0cc8",
"name": "AI: Should We Reply?",
"type": "@n8n/n8n-nodes-langchain.agent",
"position": [
-320,
940
],
"parameters": {
"text": "=todays date:- {{ $now }}\nmail date:- {{ $json.headers.date }}\nfrom :- {{ $json.headers.from }}\nsubject :- {{ $json.headers.subject.toJsonString() }}\n\ncontent :- {{ $json.text }}",
"options": {
"systemMessage": "You are a smart AI email assistant. Your job is to analyze each email and decide if it needs a response from the user. Most emails are promotions, newsletters, or notifications that do not need replies \u2014 skip those.\n\nOnly reply \"yes\" if:\n\nThe email asks a question\n\nThe email requests information or action\n\nThe email seems urgent or time-sensitive\n\nThe email involves work, deadlines, appointments, personal matters, or legal/financial implications\n\nOtherwise, reply \"no\".\n\nRespond in strict JSON format like this:\n\njson\nCopy\nEdit\n{\n \"response\": \"yes\"\n}\nor\n\njson\nCopy\nEdit\n{\n \"response\": \"no\"\n}\nDo not explain. No comments. Only JSON."
},
"promptType": "define",
"hasOutputParser": true
},
"typeVersion": 2
},
{
"id": "47ddc596-591f-470c-bafd-6a5ee7881935",
"name": "Parse: Reply Decision JSON",
"type": "@n8n/n8n-nodes-langchain.outputParserStructured",
"position": [
-120,
1160
],
"parameters": {
"jsonSchemaExample": "{\n\t\"response\": \"no\"\n}"
},
"typeVersion": 1.2
},
{
"id": "02b4791e-6301-46b8-ad85-4c627651e08a",
"name": " Check: Response Required?",
"type": "n8n-nodes-base.if",
"position": [
100,
940
],
"parameters": {
"options": {},
"conditions": {
"options": {
"version": 2,
"leftValue": "",
"caseSensitive": true,
"typeValidation": "strict"
},
"combinator": "and",
"conditions": [
{
"id": "8aa9d41a-a218-456c-8b46-70b2e4a1af03",
"operator": {
"name": "filter.operator.equals",
"type": "string",
"operation": "equals"
},
"leftValue": "={{ $json.output.response }}",
"rightValue": "yes"
}
]
}
},
"typeVersion": 2.2
},
{
"id": "a5efce44-3718-4ad4-ba19-b558f029228b",
"name": " Exit: No Reply Needed",
"type": "n8n-nodes-base.noOp",
"position": [
280,
1200
],
"parameters": {},
"typeVersion": 1
},
{
"id": "10b4cdbf-b2e0-4a75-baf2-d81184db8967",
"name": "No Operation, do nothing",
"type": "n8n-nodes-base.noOp",
"position": [
-600,
1180
],
"parameters": {},
"typeVersion": 1
},
{
"id": "f44760d0-60bf-4f04-9b7c-b1d4159e76ba",
"name": "AI: Generate Email Reply",
"type": "@n8n/n8n-nodes-langchain.agent",
"position": [
500,
920
],
"parameters": {
"text": "=todays date:- {{ $now }}\nmail date:- {{ $('Trigger: New Email').item.json.headers.date }}\nfrom :- {{ $('Trigger: New Email').item.json.headers.from }}\nsubject :- {{ $('Trigger: New Email').item.json.headers.subject }}\n\ncontent :- {{ $('Trigger: New Email').item.json.text }}",
"options": {
"systemMessage": "=\ud83d\udce7 System Prompt: Email Reply Generator\nYou are an AI email assistant. Based on the following details, write a professional and relevant reply email on behalf of the user.\n\nToday's Date:\nOriginal Email Date:\nFrom: \nSubject:\nEmail Content:\n\n\u270d\ufe0f Instructions:\nWrite a clear and concise reply email that responds meaningfully to the content.\n\nKeep the tone professional, polite, and appropriate to the context.\n\nDo not include greetings like \"Hi\" or sign-offs like \"Best regards\" unless necessary.\n\nYour output must be strictly in the following JSON format:\n\n\n\n{\n \"email\": \"email address\",\n \"subject\": \"subject text\",\n \"body\": \" body text .\"\n}\n\n\n\nIf the email is promotional, spam, or clearly does not require a reply, leave both fields blank:\n\n\n{\n \"subject\": \"\",\n \"body\": \"\"\n}\n"
},
"promptType": "define",
"hasOutputParser": true
},
"typeVersion": 2
},
{
"id": "988af447-e485-4397-b6e8-c848d53384f8",
"name": "OpenAI Chat Model",
"type": "@n8n/n8n-nodes-langchain.lmChatOpenAi",
"position": [
-300,
1160
],
"parameters": {
"options": {
"baseURL": "https://api.openai.com/v1"
}
},
"credentials": {
"openAiApi": {
"name": "<your credential>"
}
},
"typeVersion": 1
},
{
"id": "79953edf-0e9a-42de-88f7-3202eefaf851",
"name": "OpenAI Chat Model1",
"type": "@n8n/n8n-nodes-langchain.lmChatOpenAi",
"position": [
520,
1140
],
"parameters": {
"options": {
"baseURL": "https://api.openai.com/v1"
}
},
"credentials": {
"openAiApi": {
"name": "<your credential>"
}
},
"typeVersion": 1
},
{
"id": "d1bbf2f7-4506-4296-97fc-2044619dd524",
"name": "Telegram: Send + Approve",
"type": "n8n-nodes-base.telegram",
"position": [
900,
920
],
"parameters": {
"chatId": "=7917193308",
"message": "=\ud83d\udce5 *New Email Received*\n\n\ud83d\udc64 *From:* \n{{ $('Trigger: New Email').item.json.headers.from }}\n\n\ud83d\udcdd *Subject:* \n{{ $('Trigger: New Email').item.json.headers.subject }}\n\n\ud83d\udcac *Content:* \n{{ $('Trigger: New Email').item.json.text }}\n\n\n\ud83e\udd16 *AI-Generated Response*\n\n\ud83d\udce4 *To:* \n{{ $('Trigger: New Email').item.json.headers.from }}\n\n\ud83d\udcdd *Subject:* \n{{ $json.output.subject }}\n\n\ud83d\udcac *Content:* \n{{ $json.output.body }}\n",
"options": {
"limitWaitTime": {
"values": {
"resumeUnit": "minutes",
"resumeAmount": 5
}
}
},
"operation": "sendAndWait",
"approvalOptions": {
"values": {
"approvalType": "double"
}
}
},
"credentials": {
"telegramApi": {
"name": "<your credential>"
}
},
"typeVersion": 1.2
},
{
"id": "f61104a3-2350-4d5e-b613-94b7607dadd2",
"name": "Check: Telegram Approved?",
"type": "n8n-nodes-base.if",
"position": [
1120,
920
],
"parameters": {
"options": {},
"conditions": {
"options": {
"version": 2,
"leftValue": "",
"caseSensitive": true,
"typeValidation": "loose"
},
"combinator": "and",
"conditions": [
{
"id": "c7315e3c-6ee1-40bb-8d74-0c70862f30a4",
"operator": {
"type": "string",
"operation": "equals"
},
"leftValue": "={{ $json.data.approved }}",
"rightValue": "true"
}
]
},
"looseTypeValidation": true
},
"typeVersion": 2.2
},
{
"id": "d1e81ee3-db7b-4a46-b02a-ddd299d5cadf",
"name": " Exit: Telegram Not Approved",
"type": "n8n-nodes-base.noOp",
"position": [
1340,
1020
],
"parameters": {},
"typeVersion": 1
},
{
"id": "27b00238-c6fe-49bb-b147-1121f6f6c897",
"name": "Sticky Note",
"type": "n8n-nodes-base.stickyNote",
"position": [
-1520,
360
],
"parameters": {
"width": 3180,
"height": 1320,
"content": "## \ud83e\udd16 AI Email Reply Assistant\n\n## \ud83d\udd04 What this workflow does\nThis automation monitors your Gmail inbox, intelligently decides which emails need replies, generates professional responses using AI, and sends them after your approval via Telegram.\n\n---\n\n#### \ud83e\udde9 Node-by-node Breakdown\n\n1. **\ud83d\udce5 Trigger: New Email**\n - Gmail Trigger node\n - Polls inbox every minute for new emails\n\n2. **\ud83d\udcc2 Check: Is Email in Inbox?**\n - Filters emails to only process those in INBOX\n - Skips sent, drafts, and other folders\n\n3. **\ud83e\udde0 AI: Should We Reply?**\n - AI analyzes email content to determine if reply is needed\n - Skips promotions, newsletters, and notifications\n - Only processes emails with questions, requests, or urgent matters\n\n4. **\u2705 Check: Response Required?**\n - Routes emails based on AI decision\n - Continues only if reply is needed\n\n5. **\u270d\ufe0f AI: Generate Email Reply**\n - Creates professional, contextual email response\n - Maintains appropriate tone and format\n - Generates subject line and body content\n\n6. **\ud83d\udcf1 Telegram: Send + Approve**\n - Shows original email and AI-generated response\n - Waits for your approval via Telegram buttons\n - 5-minute timeout for decision\n\n7. **\ud83d\ude80 Send a message**\n - Sends the approved reply via Gmail\n - Only executes if you approve via Telegram\n\n---\n\n#### \ud83d\udca1 Key Features\n- **Smart Filtering**: Only replies to emails that actually need responses\n- **Human Approval**: You control what gets sent\n- **Professional Tone**: AI maintains appropriate business communication\n- **Mobile Control**: Approve/reject replies directly from Telegram\n\n---\n\n#### \ud83d\udee0 Perfect for:\n- Busy professionals managing high email volume\n- Customer service representatives\n- Sales teams with quick response requirements\n- Anyone wanting AI assistance with email management\n\n---\n"
},
"typeVersion": 1
}
],
"active": false,
"settings": {
"executionOrder": "v1"
},
"versionId": "29633a52-57b2-462e-be6e-4473426433d0",
"connections": {
"OpenAI Chat Model": {
"ai_languageModel": [
[
{
"node": "AI: Should We Reply?",
"type": "ai_languageModel",
"index": 0
}
]
]
},
"OpenAI Chat Model1": {
"ai_languageModel": [
[
{
"node": "AI: Generate Email Reply",
"type": "ai_languageModel",
"index": 0
}
]
]
},
"Trigger: New Email": {
"main": [
[
{
"node": "Check: Is Email in Inbox?",
"type": "main",
"index": 0
}
]
]
},
"AI: Should We Reply?": {
"main": [
[
{
"node": " Check: Response Required?",
"type": "main",
"index": 0
}
]
]
},
"AI: Generate Email Reply": {
"main": [
[
{
"node": "Telegram: Send + Approve",
"type": "main",
"index": 0
}
]
]
},
"Telegram: Send + Approve": {
"main": [
[
{
"node": "Check: Telegram Approved?",
"type": "main",
"index": 0
}
]
]
},
"Check: Is Email in Inbox?": {
"main": [
[
{
"node": "AI: Should We Reply?",
"type": "main",
"index": 0
}
],
[
{
"node": "No Operation, do nothing",
"type": "main",
"index": 0
}
]
]
},
"Check: Telegram Approved?": {
"main": [
[
{
"node": "Send a message",
"type": "main",
"index": 0
}
],
[
{
"node": " Exit: Telegram Not Approved",
"type": "main",
"index": 0
}
]
]
},
"Structured Output Parser1": {
"ai_outputParser": [
[
{
"node": "AI: Generate Email Reply",
"type": "ai_outputParser",
"index": 0
}
]
]
},
" Check: Response Required?": {
"main": [
[
{
"node": "AI: Generate Email Reply",
"type": "main",
"index": 0
}
],
[
{
"node": " Exit: No Reply Needed",
"type": "main",
"index": 0
}
]
]
},
"Parse: Reply Decision JSON": {
"ai_outputParser": [
[
{
"node": "AI: Should We Reply?",
"type": "ai_outputParser",
"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.
gmailOAuth2openAiApitelegramApi
Pro
For the full experience including quality scoring and batch install features for each workflow upgrade to Pro
About this workflow
An intelligent email automation workflow that revolutionizes how you handle email responses. This sophisticated system monitors your Gmail inbox, uses AI to determine which emails require replies, generates professional responses, and sends them only after your approval via…
Source: https://n8n.io/workflows/6026/ — 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 automatically transforms your messy inbox into a neatly organized space while ensuring you never miss a critical message. It connects to your Gmail account and triggers for every new ema
Gmail Trigger, Output Parser Structured, Gmail Tool +8
Multi-Channel Email Intelligence Agent. Uses lmChatOpenAi, outputParserStructured, gmailTrigger, agent. Event-driven trigger; 18 nodes.
OpenAI Chat, Output Parser Structured, Gmail Trigger +6
Automate your personal productivity with this intelligent n8n workflow that integrates Telegram, Google Sheets, and OpenAI (GPT-4o). This system uses multiple AI agents to manage work hours, tasks, fi
Agent, OpenAI Chat, Telegram +9
This n8n workflow automates sales processes using AI agents integrated with Airtable as a CRM and Gmail for email handling. It consists of two main workflows: one for handling Airtable status changes
Airtable Trigger, Agent, OpenAI Chat +9
This workflow helps Customer Success Managers brain dump their client knowledge via voice notes and kickstart business review preparation by auto-generating a structured Google Slides draft in their o
Google Drive, Gmail, Telegram Trigger +7