HumationHuman + Automation
Back to Catalog

Automate invoice processing from Gmail with Azure GPT-4.1 and human verification

Sachin ShresthaSachin Shrestha
647 views
2/3/2026
AIText ProcessingSEOOpenAIContent Generation
Official Page

This workflow contains community nodes that are only compatible with the self-hosted version of n8n.

This n8n workflow automates invoice management by integrating Gmail, PDF analysis, and Azure OpenAI GPT-4.1, with an optional human verification step for accuracy and control. It's ideal for businesses or individuals who regularly receive invoice emails and want to streamline their accounts payable process with minimal manual effort.

The system continuously monitors Gmail for new messages from specified senders. When it detects an email with a PDF attachment and relevant subject line (e.g., "Invoice"), it automatically extracts text from the PDF, analyzes it using Azure OpenAI, and determines if it is a valid invoice. If the AI is uncertain, the workflow sends a manual approval request to a human reviewer. Valid invoices are saved to local storage with a timestamped filename, and a confirmation email is sent upon successful processing.

🎯 Who This Is For

  1. Small to medium businesses
  2. Freelancers or consultants who receive invoices via email
  3. IT or automation teams looking to streamline document workflows
  4. Anyone using n8n with access to Gmail and Azure OpenAI

✅ Features

  • Gmail Monitoring – Automatically checks for new emails from trusted senders
  • AI-Powered Invoice Detection – Uses Azure GPT-4.1 to intelligently verify PDF contents
  • PDF Text Extraction – Extracts readable text for analysis
  • Human-in-the-Loop Verification – Requests approval when AI confidence is low
  • Secure File Storage – Saves invoices locally with structured filenames
  • Email Notifications – Sends confirmations or manual review alerts

⚙️ Setup Instructions

1. Prerequisites

  • An active n8n instance (self-hosted or cloud)
  • A Gmail account with OAuth2 credentials
  • An Azure OpenAI account with access to the GPT-4.1 model
  • A local directory for saving invoices (e.g., C:/Test/Invoices/)

2. Gmail OAuth2 Setup

  • In n8n, create Gmail OAuth2 credentials.
  • Configure it with Gmail API access (read emails and attachments).
  • Update the Gmail Trigger node to filter by sender email (e.g., sender@gmail.com).

3. Azure OpenAI Setup

  • Create Azure OpenAI API credentials in n8n.
  • Ensure your endpoint is correctly set and GPT-4.1 access is enabled.
  • Link the credentials in the AI Analysis node.

4. Customize Workflow Settings

  • Sender Email – Update in Gmail Trigger
  • Notification Email – Update in Send Notification node
  • Save Directory – Change in Save Invoice node

5. Testing the Workflow

  • Send a test email from the configured sender with a PDF invoice.
  • Wait for the workflow to trigger and check for:
  • File saved in the directory
  • Confirmation email received
  • Manual review request (if needed)

🔄 Workflow Steps

Gmail Trigger → Check for PDF Invoice → Extract PDF Text → Analyze with GPT-4.1 → ↳ If Invoice: Save & Notify ↳ If Uncertain: Request Human Review ↳ If Not Invoice: Send Invalid Alert

Automate Invoice Processing from Gmail with Azure GPT-4 and Human Verification

This n8n workflow automates the extraction and processing of invoice information from incoming Gmail emails, leveraging Azure OpenAI's GPT-4 for data extraction and including a human verification step via email.

What it does

This workflow streamlines the invoice processing pipeline by:

  1. Triggering on New Emails: It continuously monitors a specified Gmail account for new emails.
  2. Extracting Invoice Data: For emails identified as containing invoices, it uses Azure OpenAI's GPT-4 model to extract key information (e.g., invoice number, amount, vendor, date) from the email content or attachments.
  3. Human Verification: The extracted data is then sent to a designated email address for human review and approval.
  4. Conditional Processing: Based on the human verification outcome, the workflow proceeds. If approved, it can continue with further processing (e.g., saving to a database, initiating payment). If rejected or an error occurs during extraction, it can stop with an error.
  5. Saving Attachments: Any binary files (like PDF invoices) are saved locally.

Prerequisites/Requirements

To use this workflow, you will need:

  • n8n Instance: A running n8n instance.
  • Gmail Account: A Gmail account configured as a credential in n8n for both triggering and sending verification emails.
  • Azure OpenAI Service: Access to Azure OpenAI with a deployed GPT-4 (or similar chat) model. You will need an Azure OpenAI API key and endpoint configured as a credential in n8n.
  • Local File System: Access to the file system where n8n is running to save binary files.

Setup/Usage

  1. Import the Workflow:
    • Download the provided JSON file.
    • In your n8n instance, click on "Workflows" in the left sidebar.
    • Click "New" -> "Import from JSON" and paste the workflow JSON or upload the file.
  2. Configure Credentials:
    • Gmail Trigger: Configure your Gmail credential for the "Gmail Trigger" node (Node 824) to monitor for new emails.
    • Azure OpenAI Chat Model: Configure your Azure OpenAI credential for the "Azure OpenAI Chat Model" node (Node 1253). This typically involves your Azure OpenAI API Key, endpoint, and deployment name.
    • Information Extractor: Ensure the "Information Extractor" node (Node 1273) is correctly configured to use the Azure OpenAI Chat Model.
    • Gmail (for verification): Configure your Gmail credential for the "Gmail" node (Node 356) to send out human verification emails.
  3. Adjust Workflow Logic:
    • "If" Node (Node 20): This node likely contains the logic for routing based on the extracted data or verification status. You will need to define the conditions for approval/rejection based on the output of the "Information Extractor" and the human verification step.
    • "Merge" Node (Node 24): This node is used to combine data streams, likely after a conditional branch. Review its configuration to ensure it merges the correct data.
    • "Write Binary File" Node (Node 46): Configure the path where you want to save the invoice attachments.
    • "Stop and Error" Node (Node 528): This node is used for error handling. Customize the error message if needed.
    • "Sticky Note" Node (Node 565): This is a comment node; you can update or remove it as needed for documentation.
  4. Activate the Workflow: Once all credentials and configurations are set, activate the workflow by toggling the "Active" switch in the top right corner of the workflow editor.

The workflow will now automatically start processing new emails according to your defined logic.

Related Templates

AI multi-agent executive team for entrepreneurs with Gemini, Perplexity and WhatsApp

This workflow is an AI-powered multi-agent system built for startup founders and small business owners who want to automate decision-making, accountability, research, and communication, all through WhatsApp. The “virtual executive team,” is designed to help small teams to work smarter. This workflow sends you market analysis, market and sales tips, It can also monitor what your competitors are doing using perplexity (Research agent) and help you stay a head, or make better decisions. And when you feeling stuck with your start-up accountability director is creative enough to break the barrier 🎯 Core Features 🧑‍💼 1. President (Super Agent) Acts as the main controller that coordinates all sub-agents. Routes messages, assigns tasks, and ensures workflow synchronization between the AI Directors. 📊 2. Sales & Marketing Director Uses SerpAPI to search for market opportunities, leads, and trends. Suggests marketing campaigns, keywords, or outreach ideas. Can analyze current engagement metrics to adjust content strategy. 🕵️‍♀️ 3. Business Research Director Powered by Perplexity AI for competitive and market analysis. Monitors competitor moves, social media engagement, and product changes. Provides concise insights to help the founder adapt and stay ahead. ⏰ 4. Accountability Director Keeps the founder and executive team on track. Sends motivational nudges, task reminders, and progress reports. Promotes consistency and discipline — key traits for early-stage success. 🗓️ 5. Executive Secretary Handles scheduling, email drafting, and reminders. Connects with Google Calendar, Gmail, and Sheets through OAuth. Automates follow-ups, meeting summaries, and notifications directly via WhatsApp. 💬 WhatsApp as the Main Interface Interact naturally with your AI team through WhatsApp Business API. All responses, updates, and summaries are delivered to your chat. Ideal for founders who want to manage operations on the go. ⚙️ How It Works Trigger: The workflow starts from a WhatsApp Trigger node (via Meta Developer Account). Routing: The President agent analyzes the incoming message and determines which Director should handle it. Processing: Marketing or sales queries go to the Sales & Marketing Director. Research questions are handled by the Business Research Director. Accountability tasks are assigned to the Accountability Director. Scheduling or communication requests are managed by the Secretary. Collaboration: Each sub-agent returns results to the President, who summarizes and sends the reply back via WhatsApp. Memory: Context is maintained between sessions, ensuring personalized and coherent communication. 🧩 Integrations Required Gemini API – for general intelligence and task reasoning Supabase- for RAG and postgres persistent memory Perplexity API – for business and competitor analysis SerpAPI – for market research and opportunity scouting Google OAuth – to connect Sheets, Calendar, and Gmail WhatsApp Business API – for message triggers and responses 🚀 Benefits Acts like a team of tireless employees available 24/7. Saves time by automating research, reminders, and communication. Enhances accountability and strategy consistency for founders. Keeps operations centralized in a simple WhatsApp interface. 🧰 Setup Steps Create API credentials for: WhatsApp (via Meta Developer Account) Gemini, Perplexity, and SerpAPI Google OAuth (Sheets, Calendar, Gmail) Create a supabase account at supabase Add the credentials in the corresponding n8n nodes. Customize the system prompts for each Director based on your startup’s needs. Activate and start interacting with your virtual executive team on WhatsApp. Use Case You are a small organisation or start-up that can not afford hiring; marketing department, research department and secretar office, then this workflow is for you 💡 Need Customization? Want to tailor it for your startup or integrate with CRM tools like Notion or HubSpot? You can easily extend the workflow or contact the creator for personalized support. Consider adjusting the system prompt to suite your business

ShadrackBy Shadrack
331

🎓 How to transform unstructured email data into structured format with AI agent

This workflow automates the process of extracting structured, usable information from unstructured email messages across multiple platforms. It connects directly to Gmail, Outlook, and IMAP accounts, retrieves incoming emails, and sends their content to an AI-powered parsing agent built on OpenAI GPT models. The AI agent analyzes each email, identifies relevant details, and returns a clean JSON structure containing key fields: From – sender’s email address To – recipient’s email address Subject – email subject line Summary – short AI-generated summary of the email body The extracted information is then automatically inserted into an n8n Data Table, creating a structured database of email metadata and summaries ready for indexing, reporting, or integration with other tools. --- Key Benefits ✅ Full Automation: Eliminates manual reading and data entry from incoming emails. ✅ Multi-Source Integration: Handles data from different email providers seamlessly. ✅ AI-Driven Accuracy: Uses advanced language models to interpret complex or unformatted content. ✅ Structured Storage: Creates a standardized, query-ready dataset from previously unstructured text. ✅ Time Efficiency: Processes emails in real time, improving productivity and response speed. *✅ Scalability: Easily extendable to handle additional sources or extract more data fields. --- How it works This workflow automates the transformation of unstructured email data into a structured, queryable format. It operates through a series of connected steps: Email Triggering: The workflow is initiated by one of three different email triggers (Gmail, Microsoft Outlook, or a generic IMAP account), which constantly monitor for new incoming emails. AI-Powered Parsing & Structuring: When a new email is detected, its raw, unstructured content is passed to a central "Parsing Agent." This agent uses a specified OpenAI language model to intelligently analyze the email text. Data Extraction & Standardization: Following a predefined system prompt, the AI agent extracts key information from the email, such as the sender, recipient, subject, and a generated summary. It then forces the output into a strict JSON structure using a "Structured Output Parser" node, ensuring data consistency. Data Storage: Finally, the clean, structured data (the from, to, subject, and summarize fields) is inserted as a new row into a specified n8n Data Table, creating a searchable and reportable database of email information. --- Set up steps To implement this workflow, follow these configuration steps: Prepare the Data Table: Create a new Data Table within n8n. Define the columns with the following names and string type: From, To, Subject, and Summary. Configure Email Credentials: Set up the credential connections for the email services you wish to use (Gmail OAuth2, Microsoft Outlook OAuth2, and/or IMAP). Ensure the accounts have the necessary permissions to read emails. Configure AI Model Credentials: Set up the OpenAI API credential with a valid API key. The workflow is configured to use the model, but this can be changed in the respective nodes if needed. Connect the Nodes: The workflow canvas is already correctly wired. Visually confirm that the email triggers are connected to the "Parsing Agent," which is connected to the "Insert row" (Data Table) node. Also, ensure the "OpenAI Chat Model" and "Structured Output Parser" are connected to the "Parsing Agent" as its AI model and output parser, respectively. Activate the Workflow: Save the workflow and toggle the "Active" switch to ON. The triggers will begin polling for new emails according to their schedule (e.g., every minute), and the automation will start processing incoming messages. --- Need help customizing? Contact me for consulting and support or add me on Linkedin.

DavideBy Davide
1616

Send WooCommerce discount coupons to customers via WhatsApp using Rapiwa API

Who is this for? This workflow is ideal for WooCommerce store owners who want to automatically send promotional WhatsApp messages to their customers when new coupons are created. It’s designed for marketers and eCommerce managers looking to boost engagement, streamline coupon sharing, and track campaign performance effortlessly through Google Sheets. Overview This workflow listens for WooCommerce coupon creation events (coupon.created) and uses customer billing data to send promotional WhatsApp messages via the Rapiwa API. The flow formats the coupon data, cleans phone numbers, verifies WhatsApp registration with Rapiwa, sends the promotional message when verified, and logs each attempt to Google Sheets (separate sheets for verified/sent and unverified/not sent). What this Workflow Does Listens for new coupon creation events in WooCommerce via the WooCommerce Trigger node Retrieves all customer data from the WooCommerce store Processes customers in batches to control throughput Cleans and formats customer phone numbers for WhatsApp Verifies if phone numbers are valid WhatsApp accounts using Rapiwa API Sends personalized WhatsApp messages with coupon details to verified numbers Logs all activities to Google Sheets for tracking and analysis Handles both verified and unverified numbers appropriately Key Features Automated coupon distribution: Triggers when new coupons are created in WooCommerce Customer data retrieval: Fetches all customer information from WooCommerce Phone number validation: Verifies WhatsApp numbers before sending messages Personalized messaging: Includes customer name and coupon details in messages Dual logging system: Tracks both successful and failed message attempts Rate limiting: Uses batching and wait nodes to prevent API overload Data formatting: Structures coupon information for consistent messaging Google Sheet Column Structure A Google Sheet formatted like this ➤ sample The workflow uses a Google Sheet with the following columns to track coupon distribution: | name | number | email | address1 | couponCode | couponTitle | couponType | couponAmount | createDate | expireDate | validity | status | | ----------- | ------------- | --------------------------------------------------- | --------- | ---------- | -------------- | ---------- | ------------ | ------------------- | ------------------- | ---------- | -------- | | Abdul Mannan | 8801322827799 | contact@spagreen.net | mirpur-DOHS | 62dhryst | eid offer 2025 | percent | 20.00 | 2025-09-11 06:08:02 | 2025-09-15 00:00:00 | unverified | not sent | | Abdul Mannan | 8801322827799 | contact@spagreen.net | mirpur-DOHS | 62dhryst | eid offer 2025 | percent | 20.00 | 2025-09-11 06:08:02 | 2025-09-15 00:00:00 | verified | sent | Requirements n8n instance with the following nodes: WooCommerce Trigger, Code, SplitInBatches, HTTP Request, IF, Google Sheets, Wait WooCommerce store with API access Rapiwa account with API access for WhatsApp verification and messaging Google account with Sheets access Customer phone numbers in WooCommerce (stored in billing.phone field) Important Notes Phone Number Format: The workflow cleans phone numbers by removing all non-digit characters. Ensure your WooCommerce phone numbers are in a compatible format. API Rate Limits: Rapiwa and WooCommerce APIs have rate limits. Adjust batch sizes and wait times accordingly. Data Privacy: Ensure compliance with data protection regulations when sending marketing messages. Error Handling: The workflow logs unverified numbers but doesn't have extensive error handling. Consider adding error notifications for failed API calls. Message Content: The current message template references the first coupon only (coupons[0]). Adjust if you need to handle multiple coupons. Useful Links Dashboard: https://app.rapiwa.com Official Website: https://rapiwa.com Documentation: https://docs.rapiwa.com Support & Help WhatsApp: Chat on WhatsApp Discord: SpaGreen Community Facebook Group: SpaGreen Support Website: https://spagreen.net Developer Portfolio: Codecanyon SpaGreen

RapiwaBy Rapiwa
110