Jitesh Dugar This workflow corresponds to n8n.io template #13033 — we link there as the canonical source.
This workflow follows the Airtable → 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 →
{
"meta": {
"templateCredsSetupCompleted": true
},
"nodes": [
{
"id": "8c8ca031-b331-45e8-954a-67256d21895d",
"name": "Sticky_Intake",
"type": "n8n-nodes-base.stickyNote",
"position": [
256,
-224
],
"parameters": {
"color": 7,
"width": 466,
"height": 330,
"content": "## \ud83d\udce5 PHASE 1: Intake & Validation\nTriggers on Gmail attachments. Validates PDF format, filters out non-invoice emails, and performs initial data quality checks."
},
"typeVersion": 1
},
{
"id": "41d5378a-b652-4229-94a0-ba00dcd853e1",
"name": "Sticky_Parsing",
"type": "n8n-nodes-base.stickyNote",
"position": [
736,
-224
],
"parameters": {
"color": 7,
"width": 550,
"height": 362,
"content": "## \ud83d\udd2c PHASE 2: AI Parsing & Extraction\n**Parse PDF to JSON:** Converts binary PDF to structured data. **AI Ledger Mapper:** Extracts financial fields with intelligent pattern matching and confidence scoring."
},
"typeVersion": 1
},
{
"id": "69631f3b-3285-49ac-80e1-364df5c6c6d1",
"name": "Sticky_Sync",
"type": "n8n-nodes-base.stickyNote",
"position": [
1312,
-368
],
"parameters": {
"color": 7,
"width": 650,
"height": 650,
"content": "## \ud83d\ude80 PHASE 3: Ledger Sync & Archival\nUpdates Google Sheets ledger, creates Airtable records, archives to Drive. High-value or low-confidence items trigger Slack escalations for manual review."
},
"typeVersion": 1
},
{
"id": "69ed7655-68d0-4266-beab-2c715f24f648",
"name": "Sticky_ReviewQueue",
"type": "n8n-nodes-base.stickyNote",
"position": [
1312,
352
],
"parameters": {
"color": 7,
"width": 578,
"height": 350,
"content": "## \u26a0\ufe0f PHASE 4: Review Queue\nLow confidence scores (<0.7) or high-value invoices (>$5000) require manual approval before final posting."
},
"typeVersion": 1
},
{
"id": "23803aa6-c52d-4c26-a617-4e979a82d69f",
"name": "Gmail: Watch Invoices",
"type": "n8n-nodes-base.gmailTrigger",
"position": [
320,
-64
],
"parameters": {},
"typeVersion": 2
},
{
"id": "8d464849-1f13-4476-a6d8-aca8768f5e65",
"name": "IF: Valid PDF Attachment",
"type": "n8n-nodes-base.if",
"position": [
480,
-64
],
"parameters": {
"options": {},
"conditions": {
"options": {
"leftValue": "",
"caseSensitive": false,
"typeValidation": "strict"
},
"combinator": "and",
"conditions": [
{
"operator": {
"type": "array",
"operation": "notEmpty"
},
"leftValue": "={{ $json.attachments }}",
"rightValue": ""
},
{
"operator": {
"type": "string",
"operation": "equals"
},
"leftValue": "={{ $json.attachments[0].mimeType }}",
"rightValue": "application/pdf"
}
]
}
},
"typeVersion": 2
},
{
"id": "9ceec5e8-db65-45fc-8a25-113ccab7f9de",
"name": "Code: Pre-Processor",
"type": "n8n-nodes-base.code",
"position": [
640,
-64
],
"parameters": {
"jsCode": "// Code Node: Pre-Processing & Metadata\nconst items = $input.all();\n\nreturn items.map(item => {\n const attachment = item.json.attachments[0];\n \n // Extract email metadata\n item.json.emailSubject = item.json.subject || '';\n item.json.senderEmail = item.json.from?.address || 'user@example.com';\n item.json.senderName = item.json.from?.name || 'Unknown Sender';\n item.json.receivedDate = item.json.date || new Date().toISOString();\n item.json.gmailMessageId = item.json.id || '';\n \n // Attachment metadata\n item.json.attachmentName = attachment.name;\n item.json.attachmentSize = attachment.size || 0;\n item.json.attachmentMimeType = attachment.mimeType;\n \n // Generate processing ID\n item.json.processingId = `INV-${Date.now()}-${Math.random().toString(36).substring(2, 8).toUpperCase()}`;\n item.json.intakeTimestamp = new Date().toISOString();\n \n return item;\n});"
},
"typeVersion": 2
},
{
"id": "46fec074-98c4-4b8b-814f-d7609ce7619f",
"name": "HTML to PDF: Parse to JSON",
"type": "n8n-nodes-htmlcsstopdf.htmlcsstopdf",
"position": [
816,
-64
],
"parameters": {
"resource": "pdfManipulation",
"operation": "parsePdfToJson"
},
"credentials": {
"htmlcsstopdfApi": {
"name": "<your credential>"
}
},
"typeVersion": 1
},
{
"id": "01d6530b-1b4b-45df-a9ca-39457bd9a87c",
"name": "Code: AI Ledger Mapper",
"type": "n8n-nodes-base.code",
"position": [
976,
-64
],
"parameters": {
"jsCode": "// Code Node: AI-Powered Financial Data Extraction\nconst item = $input.first();\nconst text = item.json.text || '';\nconst lines = text.split('\\n');\n\n// Enhanced pattern matching for invoice fields\nconst patterns = {\n // Amount patterns\n total: [\n /(?:total|amount due|balance due|grand total)[:\\s]*\\$?([0-9,]+\\.\\d{2})/i,\n /(?:total)[:\\s]*([0-9,]+\\.\\d{2})/i,\n /\\$([0-9,]+\\.\\d{2})(?:\\s*(?:total|due))/i\n ],\n \n // Tax patterns\n tax: [\n /(?:tax|vat|gst|sales tax)[:\\s]*\\$?([0-9,]+\\.\\d{2})/i,\n /(?:tax amount)[:\\s]*([0-9,]+\\.\\d{2})/i\n ],\n \n // Vendor patterns\n vendor: [\n /(?:from|vendor|supplier|bill from)[:\\s]*([A-Za-z0-9\\s&\\.,'\\-]+?)(?:\\n|$)/i,\n /^([A-Z][A-Za-z0-9\\s&\\.,'\\-]{3,40})$/m, // Company name at start of line\n /(?:payable to)[:\\s]*([A-Za-z0-9\\s&\\.,'\\-]+)/i\n ],\n \n // Invoice number patterns\n invoiceNumber: [\n /(?:invoice|inv|bill)(?:\\s*#|\\s*no\\.?|\\s*number)[:\\s]*([A-Z0-9\\-]+)/i,\n /#([A-Z0-9\\-]{3,20})/\n ],\n \n // Date patterns\n invoiceDate: [\n /(?:invoice date|date|issued)[:\\s]*(\\d{1,2}[/-]\\d{1,2}[/-]\\d{2,4})/i,\n /(\\d{1,2}\\/\\d{1,2}\\/\\d{2,4})/\n ],\n \n // Due date patterns\n dueDate: [\n /(?:due date|payment due)[:\\s]*(\\d{1,2}[/-]\\d{1,2}[/-]\\d{2,4})/i\n ],\n \n // Subtotal patterns\n subtotal: [\n /(?:subtotal|sub-total)[:\\s]*\\$?([0-9,]+\\.\\d{2})/i\n ]\n};\n\n// Function to try multiple patterns\nfunction extractField(patterns, text) {\n for (const pattern of patterns) {\n const match = text.match(pattern);\n if (match && match[1]) {\n return match[1].trim();\n }\n }\n return null;\n}\n\n// Extract all fields\nconst totalStr = extractField(patterns.total, text);\nconst taxStr = extractField(patterns.tax, text);\nconst subtotalStr = extractField(patterns.subtotal, text);\nconst vendorRaw = extractField(patterns.vendor, text);\nconst invoiceNumber = extractField(patterns.invoiceNumber, text);\nconst invoiceDate = extractField(patterns.invoiceDate, text);\nconst dueDate = extractField(patterns.dueDate, text);\n\n// Parse amounts\nconst totalAmount = totalStr ? parseFloat(totalStr.replace(/[,$]/g, '')) : 0;\nconst taxAmount = taxStr ? parseFloat(taxStr.replace(/[,$]/g, '')) : 0;\nconst subtotalAmount = subtotalStr ? parseFloat(subtotalStr.replace(/[,$]/g, '')) : (totalAmount - taxAmount);\n\n// Clean vendor name\nconst vendorName = vendorRaw ? vendorRaw.replace(/[\\n\\r]/g, ' ').trim().substring(0, 100) : 'Unknown Vendor';\n\n// Calculate confidence score\nlet confidence = 0;\nlet confidenceFactors = [];\n\nif (totalAmount > 0) {\n confidence += 0.4;\n confidenceFactors.push('amount_found');\n}\nif (vendorRaw && vendorRaw.length > 3) {\n confidence += 0.3;\n confidenceFactors.push('vendor_found');\n}\nif (invoiceNumber) {\n confidence += 0.15;\n confidenceFactors.push('invoice_number_found');\n}\nif (taxAmount > 0) {\n confidence += 0.1;\n confidenceFactors.push('tax_found');\n}\nif (invoiceDate) {\n confidence += 0.05;\n confidenceFactors.push('date_found');\n}\n\n// Validation checks\nconst isValidAmount = totalAmount > 0 && totalAmount < 1000000;\nconst isValidVendor = vendorName !== 'Unknown Vendor' && vendorName.length > 2;\nconst mathCheck = Math.abs((subtotalAmount + taxAmount) - totalAmount) < 1; // Allow $1 rounding\n\nif (mathCheck) {\n confidence += 0.05;\n confidenceFactors.push('math_verified');\n}\n\n// Build structured output\nitem.json.extracted = {\n vendorName: vendorName,\n totalAmount: totalAmount,\n taxAmount: taxAmount,\n subtotalAmount: subtotalAmount,\n invoiceNumber: invoiceNumber || 'NOT_FOUND',\n invoiceDate: invoiceDate || item.json.receivedDate?.split('T')[0] || '',\n dueDate: dueDate || '',\n confidence: Math.min(confidence, 0.99),\n confidenceFactors: confidenceFactors,\n validationStatus: isValidAmount && isValidVendor ? 'PASS' : 'REVIEW_REQUIRED',\n extractedAt: new Date().toISOString(),\n rawTextLength: text.length\n};\n\n// Flatten for easier access\nitem.json.vendorName = vendorName;\nitem.json.totalAmount = totalAmount;\nitem.json.taxAmount = taxAmount;\nitem.json.subtotalAmount = subtotalAmount;\nitem.json.invoiceNumber = invoiceNumber || 'NOT_FOUND';\nitem.json.invoiceDate = invoiceDate || item.json.receivedDate?.split('T')[0] || '';\nitem.json.dueDate = dueDate || '';\nitem.json.confidence = item.json.extracted.confidence;\nitem.json.validationStatus = item.json.extracted.validationStatus;\n\n// Categorization\nif (totalAmount > 5000) {\n item.json.category = 'HIGH_VALUE';\n} else if (totalAmount > 1000) {\n item.json.category = 'MEDIUM_VALUE';\n} else {\n item.json.category = 'LOW_VALUE';\n}\n\n// Risk flag\nitem.json.requiresReview = confidence < 0.7 || totalAmount > 5000;\n\nreturn item;"
},
"typeVersion": 2
},
{
"id": "2f7df52f-a24c-4323-b275-9b2faf4f83ed",
"name": "IF: Auto-Approve",
"type": "n8n-nodes-base.if",
"position": [
1136,
-64
],
"parameters": {
"options": {},
"conditions": {
"options": {
"leftValue": "",
"caseSensitive": true,
"typeValidation": "strict"
},
"combinator": "and",
"conditions": [
{
"operator": {
"type": "boolean",
"operation": "equals"
},
"leftValue": "={{ $json.requiresReview }}",
"rightValue": false
}
]
}
},
"typeVersion": 2
},
{
"id": "9ed956df-b1a5-4756-91e7-b2fb13354242",
"name": "Google Sheets: Add Row",
"type": "n8n-nodes-base.googleSheets",
"position": [
1424,
-240
],
"parameters": {
"columns": {
"value": {
"Category": "={{ $json.category }}",
"Due Date": "={{ $json.dueDate }}",
"Subtotal": "={{ $json.subtotalAmount }}",
"Tax Amount": "={{ $json.taxAmount }}",
"Sender Name": "={{ $json.senderName }}",
"Vendor Name": "={{ $json.vendorName }}",
"Invoice Date": "={{ $json.invoiceDate }}",
"Processed At": "={{ $json.extractedAt }}",
"Sender Email": "={{ $json.senderEmail }}",
"Total Amount": "={{ $json.totalAmount }}",
"Processing ID": "={{ $json.processingId }}",
"Received Date": "={{ $json.receivedDate }}",
"Invoice Number": "={{ $json.invoiceNumber }}",
"Confidence Score": "={{ $json.confidence }}",
"Gmail Message ID": "={{ $json.gmailMessageId }}",
"Validation Status": "={{ $json.validationStatus }}"
},
"schema": [],
"mappingMode": "defineBelow",
"matchingColumns": []
},
"options": {},
"operation": "append",
"sheetName": {
"__rl": true,
"mode": "list",
"value": "gid=0",
"cachedResultName": "Sheet1"
},
"documentId": {
"__rl": true,
"mode": "list",
"value": "YOUR_SHEET_ID",
"cachedResultName": "Invoice Ledger"
}
},
"credentials": {
"googleSheetsOAuth2Api": {
"name": "<your credential>"
}
},
"typeVersion": 4.4
},
{
"id": "17a425a2-a110-4798-b4fc-b307be2ec658",
"name": "Airtable: Create Record",
"type": "n8n-nodes-base.airtable",
"position": [
1424,
-80
],
"parameters": {
"base": {
"__rl": true,
"mode": "list",
"value": "YOUR_BASE_ID",
"cachedResultName": "Invoice Processing"
},
"table": {
"__rl": true,
"mode": "list",
"value": "Invoices",
"cachedResultName": "Invoices"
},
"options": {},
"operation": "create"
},
"typeVersion": 2
},
{
"id": "45f0dd21-60cb-4542-9d07-30114e2a69c1",
"name": "Google Drive: Archive Invoice",
"type": "n8n-nodes-base.googleDrive",
"position": [
1424,
80
],
"parameters": {
"driveId": {
"__rl": true,
"mode": "list",
"value": "My Drive"
},
"options": {},
"folderId": {
"__rl": true,
"mode": "list",
"value": "INVOICE_ARCHIVE_FOLDER_ID",
"cachedResultName": "Invoice Archive"
}
},
"credentials": {
"googleDriveOAuth2Api": {
"name": "<your credential>"
}
},
"typeVersion": 3
},
{
"id": "4f5a2de1-9ad5-4e10-bc0a-c0f774ee9789",
"name": "Slack: Success Notification",
"type": "n8n-nodes-base.slack",
"position": [
1632,
-48
],
"parameters": {
"operation": "create"
},
"typeVersion": 2.1
},
{
"id": "95f9207e-2c14-40fc-a2e2-61ebff886a3f",
"name": "Slack: Review Required",
"type": "n8n-nodes-base.slack",
"position": [
1360,
464
],
"parameters": {
"operation": "create"
},
"typeVersion": 2.1
},
{
"id": "72e9a7e4-5a64-4068-9da5-c3af5ee35751",
"name": "Google Sheets: Review Queue",
"type": "n8n-nodes-base.googleSheets",
"position": [
1552,
480
],
"parameters": {
"columns": {
"value": {
"Status": "PENDING_REVIEW",
"Category": "={{ $json.category }}",
"Confidence": "={{ $json.confidence }}",
"Flagged At": "={{ $now.toISO() }}",
"Vendor Name": "={{ $json.vendorName }}",
"Total Amount": "={{ $json.totalAmount }}",
"Processing ID": "={{ $json.processingId }}",
"Review Reason": "={{ $json.confidence < 0.7 ? 'Low Confidence' : 'High Value' }}",
"Gmail Message ID": "={{ $json.gmailMessageId }}"
},
"schema": [],
"mappingMode": "defineBelow",
"matchingColumns": []
},
"options": {},
"operation": "append",
"sheetName": {
"__rl": true,
"mode": "list",
"value": "gid=1",
"cachedResultName": "Review Queue"
},
"documentId": {
"__rl": true,
"mode": "list",
"value": "YOUR_SHEET_ID",
"cachedResultName": "Invoice Ledger"
}
},
"credentials": {
"googleSheetsOAuth2Api": {
"name": "<your credential>"
}
},
"typeVersion": 4.4
},
{
"id": "23726aef-e060-43f0-8786-516092fd7bc0",
"name": "Gmail: Review Alert",
"type": "n8n-nodes-base.gmail",
"position": [
1728,
464
],
"parameters": {
"sendTo": "user@example.com",
"message": "=**INVOICE PENDING MANUAL REVIEW**\n\nAn invoice has been flagged for review due to {{ $json.confidence < 0.7 ? 'low confidence score' : 'high value' }}.\n\n**Invoice Details:**\n- Processing ID: {{ $json.processingId }}\n- Vendor: {{ $json.vendorName }}\n- Invoice Number: {{ $json.invoiceNumber }}\n- Date: {{ $json.invoiceDate }}\n- Total Amount: ${{ $json.totalAmount.toFixed(2) }}\n- Tax: ${{ $json.taxAmount.toFixed(2) }}\n- Confidence Score: {{ ($json.confidence * 100).toFixed(1) }}%\n\n**Sender Information:**\n- From: {{ $json.senderName }} ({{ $json.senderEmail }})\n- Received: {{ $json.receivedDate }}\n\n**Action Required:**\nPlease review the original email in Gmail (Message ID: {{ $json.gmailMessageId }}) and verify the extracted data.\n\nOnce reviewed, update the status in the Review Queue sheet.\n\n---\nAutomated Invoice Processing System",
"options": {
"ccList": "user@example.com",
"attachmentsUi": {
"attachmentsBinary": [
{}
]
}
},
"subject": "=Invoice Review Required: {{ $json.vendorName }} - ${{ $json.totalAmount }}"
},
"credentials": {
"gmailOAuth2": {
"name": "<your credential>"
}
},
"typeVersion": 2.1
},
{
"id": "f04e30d3-7349-4042-9832-5d06d54d1244",
"name": "Sticky Note",
"type": "n8n-nodes-base.stickyNote",
"position": [
-272,
-992
],
"parameters": {
"width": 448,
"height": 704,
"content": "## \ud83d\udcb0 Autonomous Invoice Extraction Hub (v11.0)\n\nIndustrial-grade pipeline for automated financial data entry: Gmail \u2192 JSON Parsing \u2192 AI Ledger Mapping \u2192 Multi-Tier Sync.\n\n### \u2699\ufe0f Core Sovereign Logic\n* **PHASE 1: Intake & Validation:** Monitors Gmail for PDF attachments and performs binary integrity checks.\n* **PHASE 2: AI Parsing:** Uses **HTML to PDF (Parse)** to convert unstructured PDF data into structured JSON objects.\n* **PHASE 3: Intelligence Mapping:** Custom Code Node extracts Vendor, Total, Tax, and Due Date with pattern-matching confidence scoring.\n* **PHASE 4: Auto-Approval Gating:** - **Green Path:** Confidence > 0.7 & Value < $5k \u2192 Auto-posts to Sheets/Airtable.\n - **Amber Path:** Low confidence or high value \u2192 Diverts to Review Queue & Slack Alert.\n* **PHASE 5: Compliance Archival:** Vaults original invoices in Google Drive with forensic metadata.\n\n### \ud83d\udccb Setup & Prerequisites\n1. **Compulsory Node:** **HTML to PDF (Parse)** for data atomization.\n2. **Targets:** Set your Google Sheet ID (Ledger & Review tabs) and Airtable Base.\n3. **Alerts:** Configure Slack Webhook for manual review escalations.\n\n**Metrics:** `Extraction_Confidence`, `Tax_Variance`, `Approval_Latency`."
},
"typeVersion": 1
}
],
"connections": {
"IF: Auto-Approve": {
"main": [
[
{
"node": "Google Sheets: Add Row",
"type": "main",
"index": 0
},
{
"node": "Airtable: Create Record",
"type": "main",
"index": 0
},
{
"node": "Google Drive: Archive Invoice",
"type": "main",
"index": 0
}
],
[
{
"node": "Slack: Review Required",
"type": "main",
"index": 0
}
]
]
},
"Code: Pre-Processor": {
"main": [
[
{
"node": "HTML to PDF: Parse to JSON",
"type": "main",
"index": 0
}
]
]
},
"Code: AI Ledger Mapper": {
"main": [
[
{
"node": "IF: Auto-Approve",
"type": "main",
"index": 0
}
]
]
},
"Slack: Review Required": {
"main": [
[
{
"node": "Google Sheets: Review Queue",
"type": "main",
"index": 0
}
]
]
},
"IF: Valid PDF Attachment": {
"main": [
[
{
"node": "Code: Pre-Processor",
"type": "main",
"index": 0
}
]
]
},
"HTML to PDF: Parse to JSON": {
"main": [
[
{
"node": "Code: AI Ledger Mapper",
"type": "main",
"index": 0
}
]
]
},
"Google Sheets: Review Queue": {
"main": [
[
{
"node": "Gmail: Review Alert",
"type": "main",
"index": 0
}
]
]
},
"Google Drive: Archive Invoice": {
"main": [
[
{
"node": "Slack: Success Notification",
"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.
gmailOAuth2googleDriveOAuth2ApigoogleSheetsOAuth2ApihtmlcsstopdfApi
Pro
For the full experience including quality scoring and batch install features for each workflow upgrade to Pro
About this workflow
This is an elite enterprise-grade solution for Accounts Payable and Finance Ops teams. It automates the high-volume extraction of unstructured data from PDF invoices using the HTML to PDF (Parse PDF to JSON) node, transforming raw email attachments into validated, audit-ready…
Source: https://n8n.io/workflows/13033/ — 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 guide will walk you through setting up your n8n workflow. By the end, you'll have a fully automated system for managing your recruitment pipeline.
Google Calendar Trigger, Slack, HTTP Request +4
This n8n workflow automates the end-to-end client onboarding process: capturing client details, validating emails, assigning tiers, generating welcome packs, creating tasks, notifying teams, archiving
Google Sheets, Gmail, Airtable +5
This workflow is perfect for recruiters, HR professionals, and startup founders who receive job applications by email and want to automate the process of parsing, matching, and evaluating resumes. If
Gmail Trigger, Airtable, HTTP Request +2
This is an enterprise-grade Intelligent Document Processing (IDP) hub designed to handle high-volume document ingestion, classification, and departmental routing. It transforms monolithic bulk scans i
Notion, Slack, Google Sheets +3
Xmind Sales Email v2. Uses gmailTrigger, notion, googleSheets, googleSheetsTrigger. Event-driven trigger; 37 nodes.
Gmail Trigger, Notion, Google Sheets +6