inderjeet Bhambra This workflow corresponds to n8n.io template #8009 — 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": "ZkrcFjipfY6GNmFZ",
"meta": {
"templateCredsSetupCompleted": true
},
"name": "AI Generated Zoom Summary",
"tags": [
{
"id": "TOmp11D0RTZnlXKe",
"name": "Creator Hub",
"createdAt": "2025-07-27T06:39:31.509Z",
"updatedAt": "2025-07-27T06:39:31.509Z"
}
],
"nodes": [
{
"id": "0d6d7996-0c0d-4968-906c-7164b26d998a",
"name": "Markdown",
"type": "n8n-nodes-base.markdown",
"position": [
-1040,
-480
],
"parameters": {
"html": "={{ $json.html || $json.textAsHtml}}",
"options": {
"bulletMarker": "-",
"keepDataImages": true
}
},
"typeVersion": 1
},
{
"id": "4c5d9061-f24d-49a3-a3a1-98f3cd669228",
"name": "Edit Fields1",
"type": "n8n-nodes-base.set",
"position": [
-768,
-480
],
"parameters": {
"options": {},
"assignments": {
"assignments": [
{
"id": "bd32465b-c630-4406-8f65-1b3665d1c7cb",
"name": "subject",
"type": "string",
"value": "={{ $json.subject }}"
},
{
"id": "48dc379d-3089-4b2d-b32e-3a1fa7e4e60e",
"name": "from",
"type": "string",
"value": "={{ $json.headers.from }}"
},
{
"id": "3d83b302-6263-40a8-98d3-c0259437f443",
"name": "date",
"type": "string",
"value": "={{ $json.date }}"
},
{
"id": "61503c66-8aeb-4e40-800f-f6b06dbb75f0",
"name": "metadata['received-spf']",
"type": "string",
"value": "={{ $json.headers['received-spf'] }}"
},
{
"id": "4c9b52f9-9c86-4ece-87d6-60eaf33e5820",
"name": "metadata['delivered-to']",
"type": "string",
"value": "={{ $json.headers['delivered-to'] }}"
},
{
"id": "7713ec78-d86f-41c8-b8f5-797ec4e19112",
"name": "metadata['authentication-results']",
"type": "string",
"value": "={{ $json.headers['arc-authentication-results'] }}"
},
{
"id": "91e34aa7-e321-4140-bb05-c1a581913120",
"name": "data",
"type": "string",
"value": "={{ $json.data || $json.textPlain}}"
}
]
}
},
"typeVersion": 3.4
},
{
"id": "c9461d9f-6273-41ab-ae19-a926eceb35d1",
"name": "Generate Summary",
"type": "@n8n/n8n-nodes-langchain.agent",
"position": [
-128,
-528
],
"parameters": {
"text": "={{ $json.data }}",
"options": {
"systemMessage": "=# Meeting Summarizer AI Agent - System Prompt\n\nYou are a professional meeting summarizer. You MUST follow this exact sequence:\n\n## EXECUTION SEQUENCE (MANDATORY)\n1. **FIRST**: Generate and output both formatted content blocks\n2. **SECOND**: Call the \"Send Email\" tool using the generated content\n\n## TASK\nProcess meeting transcript \u2192 Generate structured summary in 2 formats \u2192 Send email\n\n## CONTENT REQUIREMENTS\n\n### Required Sections (Extract from transcript):\n1. **Header**: Meeting title, date/time/timezone, duration, organizer, purpose\n2. **Attendees**: Names and roles \n3. **Overview**: 5-10 sentence executive summary\n4. **Key Discussion Points**: Main topics discussed (bold any decisions)\n5. **Action Items**: Tasks with assignee, due date, priority\n6. **Things to Remember**: Important notes/follow-ups\n7. **Closing**: Brief wrap-up\n\n### Formatting Rules:\n- Use \"[Not Provided]\" for missing information\n- Bold all decisions and commitments\n- Keep professional, concise tone\n- Make content scannable\n\n## STEP 1: OUTPUT FORMATTED CONTENT\n\nYou MUST output both blocks in this exact format:\n\n```\n[EMAIL_HTML]\n<table style=\"width:100%;max-width:600px;margin:0 auto;font-family:Arial,Helvetica,sans-serif;color:#000000;background:#ffffff;border-collapse:collapse\">\n <tr><td style=\"padding:20px\">\n <h1 style=\"color:#0056b3;margin:0 0 10px 0\">{Meeting Title}</h1>\n <p style=\"margin:0 0 5px 0\"><strong>Date:</strong> {Date} | <strong>Time:</strong> {Time} {Timezone}</p>\n <p style=\"margin:0 0 5px 0\"><strong>Duration:</strong> {Duration} | <strong>Organizer:</strong> {Organizer}</p>\n <p style=\"margin:0 0 20px 0\"><strong>Purpose:</strong> {Purpose}</p>\n \n <h2 style=\"color:#0056b3;margin:20px 0 10px 0\">Attendees</h2>\n <table style=\"width:100%;border-collapse:collapse;margin:0 0 20px 0\">\n <tr style=\"background:#f5f5f5\">\n <td style=\"padding:8px;border:1px solid #ddd\"><strong>Name</strong></td>\n <td style=\"padding:8px;border:1px solid #ddd\"><strong>Role</strong></td>\n </tr>\n <!-- Add attendee rows -->\n </table>\n \n <h2 style=\"color:#0056b3;margin:20px 0 10px 0\">Overview</h2>\n <p style=\"margin:0 0 20px 0\">{Overview content}</p>\n \n <h2 style=\"color:#0056b3;margin:20px 0 10px 0\">Key Discussion Points</h2>\n <ul style=\"margin:0 0 20px 0;padding-left:20px\">\n <!-- Add discussion points -->\n </ul>\n \n <h2 style=\"color:#0056b3;margin:20px 0 10px 0\">Action Items</h2>\n <ol style=\"margin:0 0 20px 0;padding-left:20px\">\n <!-- Add action items -->\n </ol>\n \n <h2 style=\"color:#0056b3;margin:20px 0 10px 0\">Things to Remember</h2>\n <ul style=\"margin:0 0 20px 0;padding-left:20px\">\n <!-- Add items to remember -->\n </ul>\n \n <h2 style=\"color:#0056b3;margin:20px 0 10px 0\">Closing Note</h2>\n <p style=\"margin:0\">{Closing statement}</p>\n </td></tr>\n</table>\n[/EMAIL_HTML]\n\n[GOOGLE_DOCS_TEXT]\nMEETING TITLE: {Meeting Title}\nDATE: {Date} TIME: {Time} {Timezone} DURATION: {Duration}\nORGANIZER: {Organizer}\nPURPOSE: {Purpose}\n\nATTENDEES\n{Name} \u2014 {Role}\n{Name} \u2014 {Role}\n\nOVERVIEW\n{5-10 sentence executive summary}\n\nKEY DISCUSSION POINTS\n\u2022 {Discussion point}\n\u2022 {Discussion point with DECISION: decision made}\n\nACTION ITEMS\n1. {Task} \u2014 {Assignee} \u2014 Due: {Date} \u2014 Priority: {Priority}\n2. {Task} \u2014 {Assignee} \u2014 Due: {Date} \u2014 Priority: {Priority}\n\nTHINGS TO REMEMBER\n\u2022 {Important note}\n\u2022 {Follow-up item}\n\nCLOSING NOTE\n{Brief wrap-up statement}\n[/GOOGLE_DOCS_TEXT]\n```\n\n## STEP 2: SEND EMAIL TOOL\n\n**ONLY AFTER** outputting both content blocks above, call the \"Send Email\" tool with these parameters:\n\n- `to`: Extract emails from transcript or use \"[Not Provided]\"\n- `cc`: Optional additional recipients (default: \"\")\n- `subject`: \"Meeting Summary: {Meeting Title} \u2013 {YYYY-MM-DD}\"\n- `html_body`: The HTML content (everything between [EMAIL_HTML] markers, excluding the markers)\n- `text_body`: The plain text content (everything between [GOOGLE_DOCS_TEXT] markers, excluding the markers)\n\n## CRITICAL RULES\n\n1. **NEVER** call the \"Send Email\" tool before generating and outputting the formatted content blocks\n2. **ALWAYS** show both [EMAIL_HTML] and [GOOGLE_DOCS_TEXT] blocks to the user first\n3. **THEN** call the tool using the exact content from those blocks\n4. Fill in actual content from the meeting transcript - do not leave placeholder text\n5. If information is missing, use \"[Not Provided]\" but still generate complete summaries\n\n## ERROR PREVENTION\n\n- If transcript is unclear: Extract what you can and note \"[Not Provided]\" for missing items\n- If no attendees found: Create single row with \"[Not Provided]\" in both columns \n- If no action items: Write \"No specific action items were identified in this meeting\"\n- Always generate complete HTML and text versions before calling the email tool"
},
"promptType": "define"
},
"typeVersion": 2.2
},
{
"id": "9a5f39c8-b9d2-40ca-8f1f-7677ac674c26",
"name": "Update a document",
"type": "n8n-nodes-base.googleDocs",
"position": [
-480,
96
],
"parameters": {
"actionsUi": {
"actionFields": [
{
"text": "={{ $('DocFormat').item.json.message.content.content }}",
"action": "insert"
}
]
},
"operation": "update",
"documentURL": "={{ $json.id }}"
},
"credentials": {
"googleDocsOAuth2Api": {
"name": "<your credential>"
}
},
"typeVersion": 2
},
{
"id": "91e2b358-de19-435b-a5a8-2b26a103c17e",
"name": "Create a document",
"type": "n8n-nodes-base.googleDocs",
"position": [
-784,
96
],
"parameters": {
"title": "={{ $json.message.content.title }}",
"folderId": "default"
},
"credentials": {
"googleDocsOAuth2Api": {
"name": "<your credential>"
}
},
"typeVersion": 2
},
{
"id": "89436018-84e6-4682-8ac0-894e5cffb59c",
"name": "DocFormat",
"type": "@n8n/n8n-nodes-langchain.openAi",
"position": [
-1184,
-64
],
"parameters": {
"modelId": {
"__rl": true,
"mode": "list",
"value": "gpt-4.1",
"cachedResultName": "GPT-4.1"
},
"options": {
"topP": 1,
"temperature": 0.3
},
"messages": {
"values": [
{
"content": "={{ $json.data }}"
},
{
"role": "=system",
"content": "=You are a formatting specialist AI agent. You will transform Markdown input from {{ $json.data }} into valid JSON for creating a Google Doc\u2013ready plain\u2011text document.\n\n## TASKS\n1. Extract the Subject value from the input.\n2. Sanitize the Subject to create a safe filename (the JSON \"title\").\n3. Convert the remaining content into a clean, Google Docs\u2013friendly plain\u2011text layout (the JSON \"content\").\n4. Output a JSON object with exactly two keys in this order: \"title\", \"content\".\n\n## OUTPUT CONSTRAINTS\n- Output ONLY a single JSON object. No code fences, no comments, no extra keys, no trailing commas.\n- JSON must be valid UTF\u20118, with proper escaping for quotes (\\\") and backslashes (\\\\).\n- Use \\n for line breaks inside the \"content\" string. Do not include literal unescaped newlines.\n\n## SUBJECT EXTRACTION\n- Primary: If a line matches /^Subject\\s*:\\s*(.+)\\s*$/i, use the captured value.\n- Secondary: If no Subject line, use the first level\u20111 heading (e.g., a line starting with \"# \").\n- Tertiary: If neither exists, use the first non\u2011empty line truncated to 80 characters.\n- Fallback: If no suitable text, use \"Meeting_Notes\".\n\n## TITLE SANITIZATION (\"title\")\n- Trim leading/trailing whitespace.\n- Replace spaces with underscores.\n- Remove or replace these characters with underscore: / \\ : * ? \" < > | # % { } $ ! ' @ + ` = ^ ~ [ ] ( ) ; , .\n- Collapse multiple underscores to a single underscore.\n- Limit to 120 characters; trim from the end if longer.\n- Preserve alphanumerics and Unicode letters/numbers where safe; normalize to NFC.\n- If empty after sanitization, use \"Meeting_Notes\".\n\n## CONTENT FORMAT (\"content\")\nProduce plain text only (no Markdown), using this exact structure and headings. Use a single blank line between sections and no trailing spaces. Use \"- \" as the bullet prefix. Replace missing fields with [Not Provided].\n\nMeeting Notes\n=============\n\nSubject: [Subject]\nMeeting Date: [Meeting Date]\nTime: [Time]\nDuration: [Duration]\n\nRoles\n-----\nOrganizer: [Organizer]\nAttendees: [Attendees]\n\nOverview\n--------\n[One to three sentences.]\n\nKey Discussion Points\n---------------------\n- [Point 1]\n- [Point 2]\n- [Point 3]\n\nAction Items / Follow-Ups\n-------------------------\n- Task: [Task]\n Assignee: [Assignee]\n Due: [Due Date]\n Priority: [Priority]\n\nThings to Remember\n------------------\n- [Reminder 1]\n- [Reminder 2]\n\nClosing Note\n------------\n[Short closing sentence inviting review/follow-up.]\n\n## CONVERSION RULES\n- Replace all placeholders with extracted values; if a value is missing, insert [Not Provided].\n- Remove all Markdown syntax from the input (e.g., #, ##, **, *, _, >, inline code, tables).\n- Lists: convert any list style (*, -, 1.) to \"- \" bullets in the final output.\n- Emphasis: drop bold/italic styling; retain words as plain text (no Markdown markers).\n- Tables: convert to bullet blocks using \"Field: Value\" pairs per row; do not attempt column alignment.\n- Normalize whitespace: collapse multiple spaces to single spaces within lines; preserve intended paragraph breaks.\n- Do not include invisible control characters or non\u2011breaking spaces.\n\n## EDGE CASES\n- Malformed or partial Markdown: best\u2011effort parsing; prioritize content extraction over styling.\n- Oversized content: keep all content; do not truncate, but maintain formatting rules.\n- Email addresses, URLs, and IDs: keep as plain text.\n- Ensure there are no dangling or duplicate section headers; include empty sections with [Not Provided] where needed.\n\n## VALIDATION\n- Ensure the final output is valid JSON and contains both keys: \"title\" (string) and \"content\" (string).\n- No additional keys, arrays, or objects.\n- No code fences or explanatory text before or after the JSON object.\n"
}
]
},
"jsonOutput": true
},
"credentials": {
"openAiApi": {
"name": "<your credential>"
}
},
"typeVersion": 1.8
},
{
"id": "57e18985-bb3a-4182-98e0-2bb3afa53ae4",
"name": "No Operation, do nothing",
"type": "n8n-nodes-base.noOp",
"position": [
-112,
-64
],
"parameters": {},
"typeVersion": 1
},
{
"id": "6a57c8ce-dc50-403c-a182-0fb644cf1404",
"name": "Sticky Note",
"type": "n8n-nodes-base.stickyNote",
"position": [
-1840,
-720
],
"parameters": {
"width": 672,
"height": 512,
"content": "## \ud83d\udce7 **EMAIL TRIGGER (GMAIL) - Entry Point**\n**What it does:**\n- Monitors your email inbox for new Zoom meeting summaries\n - Check for subject: 'Meeting assets', 'Zoom', 'Meeting Assets'\n- You may add a Trigger for Sender: no-reply@zoom.us"
},
"typeVersion": 1
},
{
"id": "c53117a0-979c-4368-b99b-239cced75185",
"name": "Sticky Note2",
"type": "n8n-nodes-base.stickyNote",
"position": [
-1152,
-720
],
"parameters": {
"width": 624,
"height": 416,
"content": "## \ud83d\udcdd **MARKDOWN CONVERTER - Content Processing**\n**Configuration:**\n- Converts HTML content to markdown format\n- Uses \"-\" as bullet markers\n- Preserves data images\n- Makes content easier to process by AI"
},
"typeVersion": 1
},
{
"id": "c1c573e8-e270-4f21-ae50-aeb77a809dae",
"name": "Sticky Note1",
"type": "n8n-nodes-base.stickyNote",
"position": [
-496,
-768
],
"parameters": {
"width": 672,
"height": 560,
"content": "## \ud83e\udd16 **GENERATE SUMMARY - AI Processing Hub**\n\n**AI Instructions:**\n- Creates EMAIL-SAFE HTML for email clients\n- Generates Google Docs compatible text\n- Professional formatting with proper structure\n- Includes: Header, Attendees, Overview, Discussion Points, Action Items\n\n**\ud83d\udd17 Connected Tools:**\n- **Send Email Tool** (via AI tool connection)\n- **GPT-4.1 Language Model** (for processing)"
},
"typeVersion": 1
},
{
"id": "d6737471-a63d-4349-9067-95aa7346b550",
"name": "Apply Formatting",
"type": "n8n-nodes-base.markdown",
"position": [
240,
-352
],
"parameters": {
"html": "={{ $json.output }}",
"options": {}
},
"typeVersion": 1
},
{
"id": "8cefd430-13d2-4744-a3af-e1f6207577df",
"name": "Sticky Note3",
"type": "n8n-nodes-base.stickyNote",
"position": [
-1504,
-144
],
"parameters": {
"width": 592,
"height": 400,
"content": "## \ud83d\udcc4 **DOCFORMAT - Google Docs Preparation**\n\n**Process:**\n1. Extracts subject for document title\n2. Sanitizes title for filename safety\n3. Formats content for Google Docs\n4. Returns JSON with title and content\n\n**Output Structure:**\n```json\n{\n \"title\": \"Sanitized_Meeting_Title\",\n \"content\": \"Google Docs formatted text...\"\n}\n```"
},
"typeVersion": 1
},
{
"id": "d0734d45-4754-432f-b15a-8215f2714bc3",
"name": "Sticky Note4",
"type": "n8n-nodes-base.stickyNote",
"position": [
-880,
-144
],
"parameters": {
"width": 640,
"height": 432,
"content": "## \ud83d\udcc1 **CREATE A DOCUMENT - Google Docs Integration**\n\n**Configuration:**\n- Uses title from DocFormat output\n- Creates in default folder. Change this to specific folder name.\n- Authenticated with Google Docs OAuth2\n\n**\ud83d\udd17 Flow:** DocFormat \u2192 Create Document \u2192 Update Document"
},
"typeVersion": 1
},
{
"id": "27352f49-fb07-4e53-be73-b463480f90cd",
"name": "Gmail Trigger",
"type": "n8n-nodes-base.gmailTrigger",
"position": [
-1792,
-528
],
"parameters": {
"simple": false,
"filters": {
"q": "subject: 'Meeting assets', 'Zoom', 'Meeting Assets'",
"readStatus": "unread"
},
"options": {},
"pollTimes": {
"item": [
{
"mode": "everyMinute"
}
]
}
},
"credentials": {
"gmailOAuth2": {
"name": "<your credential>"
}
},
"typeVersion": 1.3
},
{
"id": "1fb05ae4-9ea8-4d81-8e3f-a3148979eecb",
"name": "Mark a message as read",
"type": "n8n-nodes-base.gmail",
"position": [
-1584,
-384
],
"parameters": {
"messageId": "={{ $json.id }}",
"operation": "markAsRead"
},
"credentials": {
"gmailOAuth2": {
"name": "<your credential>"
}
},
"typeVersion": 2.1
},
{
"id": "4b126e38-bb28-47d3-8a80-3e8b7d004a96",
"name": "No Operation, do nothing1",
"type": "n8n-nodes-base.noOp",
"position": [
-1360,
-384
],
"parameters": {},
"typeVersion": 1
},
{
"id": "c8852068-3b60-4780-b08b-5e6506babd93",
"name": "gpt-4O",
"type": "@n8n/n8n-nodes-langchain.lmChatOpenAi",
"position": [
-416,
-352
],
"parameters": {
"model": {
"__rl": true,
"mode": "list",
"value": "gpt-4o",
"cachedResultName": "gpt-4o"
},
"options": {
"topP": 1,
"temperature": 0.3,
"frequencyPenalty": 0
}
},
"credentials": {
"openAiApi": {
"name": "<your credential>"
}
},
"typeVersion": 1.2
},
{
"id": "737f1067-5bf5-4113-af7a-9cc1ae6d1705",
"name": "Send Email",
"type": "n8n-nodes-base.gmailTool",
"position": [
-128,
-336
],
"parameters": {
"sendTo": "={{ $('Gmail Trigger').item.json.headers.to }}",
"message": "={{ /*n8n-auto-generated-fromAI-override*/ $fromAI('Message', ``, 'string') }}",
"options": {
"appendAttribution": false
},
"subject": "={{ /*n8n-auto-generated-fromAI-override*/ $fromAI('Subject', ``, 'string') }}"
},
"credentials": {
"gmailOAuth2": {
"name": "<your credential>"
}
},
"typeVersion": 2.1
}
],
"active": false,
"settings": {
"executionOrder": "v1"
},
"versionId": "99cbaa6c-4395-4239-9fed-ecb1fe5030cc",
"connections": {
"gpt-4O": {
"ai_languageModel": [
[
{
"node": "Generate Summary",
"type": "ai_languageModel",
"index": 0
}
]
]
},
"Markdown": {
"main": [
[
{
"node": "Edit Fields1",
"type": "main",
"index": 0
}
]
]
},
"DocFormat": {
"main": [
[
{
"node": "Create a document",
"type": "main",
"index": 0
}
]
]
},
"Send Email": {
"ai_tool": [
[
{
"node": "Generate Summary",
"type": "ai_tool",
"index": 0
}
]
]
},
"Edit Fields1": {
"main": [
[
{
"node": "Generate Summary",
"type": "main",
"index": 0
}
]
]
},
"Gmail Trigger": {
"main": [
[
{
"node": "Markdown",
"type": "main",
"index": 0
},
{
"node": "Mark a message as read",
"type": "main",
"index": 0
}
]
]
},
"Apply Formatting": {
"main": [
[
{
"node": "DocFormat",
"type": "main",
"index": 0
}
]
]
},
"Generate Summary": {
"main": [
[
{
"node": "Apply Formatting",
"type": "main",
"index": 0
}
]
]
},
"Create a document": {
"main": [
[
{
"node": "Update a document",
"type": "main",
"index": 0
}
]
]
},
"Update a document": {
"main": [
[
{
"node": "No Operation, do nothing",
"type": "main",
"index": 0
}
]
]
},
"Mark a message as read": {
"main": [
[
{
"node": "No Operation, do nothing1",
"type": "main",
"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.
gmailOAuth2googleDocsOAuth2ApiopenAiApi
Pro
For the full experience including quality scoring and batch install features for each workflow upgrade to Pro
About this workflow
This automated workflow transforms Zoom meeting emails into professional summaries and Google Docs. It monitors your Gmail for Zoom meeting notification emails, extracts meeting content using AI-powered analysis, and generates both email-safe HTML summaries and Google…
Source: https://n8n.io/workflows/8009/ — 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.
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
AI Agents Vs AI Workflow. Uses lmChatOpenAi, gmailTrigger, gmail, gmailTool. Event-driven trigger; 30 nodes.
OpenAI Chat, Gmail Trigger, Gmail +7
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
This workflow is the core of a three-part email automation system. It monitors your Gmail inbox in real time, classifies every inbound customer email with AI, retrieves contextually relevant data from
OpenAI Chat, Memory Buffer Window, Agent +5