This workflow follows the Gmail → Gmail Trigger 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": "02 \u00b7 AI Email Triage \u2192 Draft, Alert or Archive",
"nodes": [
{
"parameters": {
"content": "## 02 \u00b7 AI email triage\n**Gmail trigger \u2192 GPT analysis \u2192 route by category**\n\n`urgent` pings Telegram \u00b7 `needs_reply` creates a Gmail draft \u00b7\n`fyi` and `noise` are logged only. Everything lands in one sheet.\n\nThe model never sends mail \u2014 it only drafts. A human presses send.",
"height": 280,
"width": 520,
"color": 7
},
"id": "00000002-0000-4000-8000-000000000000",
"name": "Overview",
"type": "n8n-nodes-base.stickyNote",
"typeVersion": 1,
"position": [
-260,
-220
]
},
{
"parameters": {
"pollTimes": {
"item": [
{
"mode": "everyMinute"
}
]
},
"simple": false,
"filters": {
"labelIds": [
"INBOX"
],
"readStatus": "unread"
},
"options": {}
},
"id": "00000002-0000-4000-8000-000000000001",
"name": "Gmail Trigger",
"type": "n8n-nodes-base.gmailTrigger",
"typeVersion": 1.2,
"position": [
-240,
140
],
"credentials": {
"gmailOAuth2": {
"name": "<your credential>"
}
}
},
{
"parameters": {
"mode": "runOnceForEachItem",
"jsCode": "// Gmail returns a lot of metadata; keep only what the model needs and cap the\n// body so a 40-page thread cannot blow up the token bill.\nconst item = $json;\n\nreturn {\n json: {\n message_id: item.id ?? '',\n thread_id: item.threadId ?? '',\n from: item.From ?? item.from ?? '',\n subject: item.Subject ?? item.subject ?? '(no subject)',\n body: String(item.text ?? item.snippet ?? '').slice(0, 6000),\n received_at: item.date ?? new Date().toISOString(),\n },\n};"
},
"id": "00000002-0000-4000-8000-000000000002",
"name": "Extract Email Fields",
"type": "n8n-nodes-base.code",
"typeVersion": 2,
"position": [
-20,
140
]
},
{
"parameters": {
"method": "POST",
"url": "https://api.openai.com/v1/chat/completions",
"authentication": "genericCredentialType",
"genericAuthType": "httpHeaderAuth",
"sendBody": true,
"specifyBody": "json",
"jsonBody": "={\n \"model\": \"gpt-4o-mini\",\n \"temperature\": 0,\n \"response_format\": { \"type\": \"json_object\" },\n \"messages\": [\n {\n \"role\": \"system\",\n \"content\": \"You triage a freelancer's inbox. Reply with JSON only, using exactly these keys: category (urgent|needs_reply|fyi|noise), topic (max 60 characters), summary (max 240 characters, English), sentiment (positive|neutral|negative), suggested_reply (a complete draft reply in the sender's language, empty string when category is fyi or noise), confidence (0-1). category=urgent means money, a production outage or a hard deadline within 24 hours. Newsletters, receipts and automated notifications are noise.\"\n },\n {\n \"role\": \"user\",\n \"content\": {{ JSON.stringify(`From: ${$json.from}\\nSubject: ${$json.subject}\\n\\n${$json.body}`) }}\n }\n ]\n}",
"options": {
"timeout": 60000
}
},
"id": "00000002-0000-4000-8000-000000000003",
"name": "Analyse Email",
"type": "n8n-nodes-base.httpRequest",
"typeVersion": 4.2,
"position": [
200,
140
],
"credentials": {
"httpHeaderAuth": {
"name": "<your credential>"
}
},
"retryOnFail": true,
"maxTries": 3,
"waitBetweenTries": 2000
},
{
"parameters": {
"jsCode": "const email = $('Extract Email Fields').first().json;\nconst raw = $json.choices?.[0]?.message?.content ?? '{}';\n\nlet parsed;\ntry {\n parsed = JSON.parse(raw);\n} catch (error) {\n // Unparseable output is routed to needs_reply so a human always sees it.\n parsed = { category: 'needs_reply', topic: 'unclassified', summary: String(raw).slice(0, 240) };\n}\n\nconst allowed = ['urgent', 'needs_reply', 'fyi', 'noise'];\nconst category = String(parsed.category ?? '').toLowerCase();\n\nreturn [\n {\n json: {\n ...email,\n category: allowed.includes(category) ? category : 'needs_reply',\n topic: parsed.topic ?? '',\n summary: parsed.summary ?? '',\n sentiment: parsed.sentiment ?? 'neutral',\n suggested_reply: parsed.suggested_reply ?? '',\n confidence: Number(parsed.confidence ?? 0),\n triaged_at: new Date().toISOString(),\n },\n },\n];"
},
"id": "00000002-0000-4000-8000-000000000004",
"name": "Parse Analysis",
"type": "n8n-nodes-base.code",
"typeVersion": 2,
"position": [
420,
140
]
},
{
"parameters": {
"rules": {
"values": [
{
"conditions": {
"options": {
"caseSensitive": true,
"leftValue": "",
"typeValidation": "loose",
"version": 2
},
"conditions": [
{
"id": "r1",
"leftValue": "={{ $json.category }}",
"rightValue": "urgent",
"operator": {
"type": "string",
"operation": "equals"
}
}
],
"combinator": "and"
},
"renameOutput": true,
"outputKey": "urgent"
},
{
"conditions": {
"options": {
"caseSensitive": true,
"leftValue": "",
"typeValidation": "loose",
"version": 2
},
"conditions": [
{
"id": "r2",
"leftValue": "={{ $json.category }}",
"rightValue": "needs_reply",
"operator": {
"type": "string",
"operation": "equals"
}
}
],
"combinator": "and"
},
"renameOutput": true,
"outputKey": "needs_reply"
}
]
},
"options": {
"fallbackOutput": "extra",
"renameFallbackOutput": "low_priority"
}
},
"id": "00000002-0000-4000-8000-000000000005",
"name": "Route by Category",
"type": "n8n-nodes-base.switch",
"typeVersion": 3.2,
"position": [
640,
140
]
},
{
"parameters": {
"chatId": "REPLACE_WITH_TELEGRAM_CHAT_ID",
"text": "=\ud83d\udea8 <b>Urgent email</b>\n\n<b>From:</b> {{ $json.from }}\n<b>Subject:</b> {{ $json.subject }}\n<b>Topic:</b> {{ $json.topic }}\n\n{{ $json.summary }}",
"additionalFields": {
"parse_mode": "HTML"
}
},
"id": "00000002-0000-4000-8000-000000000006",
"name": "Alert on Telegram",
"type": "n8n-nodes-base.telegram",
"typeVersion": 1.2,
"position": [
900,
-40
],
"credentials": {
"telegramApi": {
"name": "<your credential>"
}
},
"onError": "continueRegularOutput"
},
{
"parameters": {
"resource": "draft",
"subject": "=Re: {{ $json.subject }}",
"emailType": "text",
"message": "={{ $json.suggested_reply }}",
"options": {
"sendTo": "={{ $json.from }}",
"threadId": "={{ $json.thread_id }}"
}
},
"id": "00000002-0000-4000-8000-000000000007",
"name": "Create Gmail Draft",
"type": "n8n-nodes-base.gmail",
"typeVersion": 2.1,
"position": [
900,
140
],
"credentials": {
"gmailOAuth2": {
"name": "<your credential>"
}
},
"onError": "continueRegularOutput"
},
{
"parameters": {},
"id": "00000002-0000-4000-8000-000000000008",
"name": "Low Priority",
"type": "n8n-nodes-base.noOp",
"typeVersion": 1,
"position": [
900,
320
]
},
{
"parameters": {
"operation": "append",
"documentId": {
"__rl": true,
"value": "REPLACE_WITH_GOOGLE_SHEET_ID",
"mode": "id"
},
"sheetName": {
"__rl": true,
"value": "Inbox Triage",
"mode": "name"
},
"columns": {
"mappingMode": "defineBelow",
"value": {
"Triaged At": "={{ $json.triaged_at }}",
"From": "={{ $json.from }}",
"Subject": "={{ $json.subject }}",
"Category": "={{ $json.category }}",
"Topic": "={{ $json.topic }}",
"Sentiment": "={{ $json.sentiment }}",
"Summary": "={{ $json.summary }}",
"Confidence": "={{ $json.confidence }}",
"Message ID": "={{ $json.message_id }}"
},
"matchingColumns": [],
"schema": []
},
"options": {}
},
"id": "00000002-0000-4000-8000-000000000009",
"name": "Log Triage Result",
"type": "n8n-nodes-base.googleSheets",
"typeVersion": 4.5,
"position": [
1160,
140
],
"credentials": {
"googleSheetsOAuth2Api": {
"name": "<your credential>"
}
},
"retryOnFail": true,
"maxTries": 3,
"waitBetweenTries": 2000
}
],
"connections": {
"Gmail Trigger": {
"main": [
[
{
"node": "Extract Email Fields",
"type": "main",
"index": 0
}
]
]
},
"Extract Email Fields": {
"main": [
[
{
"node": "Analyse Email",
"type": "main",
"index": 0
}
]
]
},
"Analyse Email": {
"main": [
[
{
"node": "Parse Analysis",
"type": "main",
"index": 0
}
]
]
},
"Parse Analysis": {
"main": [
[
{
"node": "Route by Category",
"type": "main",
"index": 0
}
]
]
},
"Route by Category": {
"main": [
[
{
"node": "Alert on Telegram",
"type": "main",
"index": 0
}
],
[
{
"node": "Create Gmail Draft",
"type": "main",
"index": 0
}
],
[
{
"node": "Low Priority",
"type": "main",
"index": 0
}
]
]
},
"Alert on Telegram": {
"main": [
[
{
"node": "Log Triage Result",
"type": "main",
"index": 0
}
]
]
},
"Create Gmail Draft": {
"main": [
[
{
"node": "Log Triage Result",
"type": "main",
"index": 0
}
]
]
},
"Low Priority": {
"main": [
[
{
"node": "Log Triage Result",
"type": "main",
"index": 0
}
]
]
}
},
"active": false,
"settings": {
"executionOrder": "v1",
"saveManualExecutions": true
},
"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.
gmailOAuth2googleSheetsOAuth2ApihttpHeaderAuthtelegramApi
Pro
For the full experience including quality scoring and batch install features for each workflow upgrade to Pro
About this workflow
02 · AI Email Triage → Draft, Alert or Archive. Uses gmailTrigger, httpRequest, telegram, gmail. Event-driven trigger; 10 nodes.
Source: https://github.com/wanderfool95/n8n-ai-workflows/blob/main/workflows/02-email-triage-ai.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.
📘 Description
HTTP Request, Gmail Trigger, ClickUp +3
Email → AI triage → CRM pipeline (template). Uses gmailTrigger, httpRequest, googleSheets, gmail. Event-driven trigger; 17 nodes.
Gmail Trigger, HTTP Request, Google Sheets +2
Stay ahead in your trading game with this powerful n8n automation workflow. Designed for real-time efficiency, this setup continuously scans your Gmail inbox for trading alerts from TradingView and en
Gmail, Telegram, Google Sheets +1
Inbox-Attachment-Organizer. Uses googleSheets, gmail, telegram, lmChatGroq. Event-driven trigger; 51 nodes.
Google Sheets, Gmail, Telegram +6
This workflow accepts a suspected scam URL via an n8n form, enriches it with RDAP, certificate transparency, DNS/IP hosting data, urlscan.io results, and HTML fingerprints, then correlates findings ag
Form Trigger, HTTP Request, Data Table +2