Workflow Templates

Workflow updated on 17/06/2024:** Added 'Summarize' node to avoid creating a row for each Notion content block in the Supabase table.* Store Notion's Pages as Vector Documents into Supabase This workflow assumes you have a Supabase project with a table that has a vector column. If you don't have it, follow the instructions here: Supabase Langchain Guide Workflow Description This workflow automates the process of storing Notion pages as vector documents in a Supabase database with a vector column. The steps are as follows: Notion Page Added Trigger: Monitors a specified Notion database for newly added pages. You can create a specific Notion database where you copy the pages you want to store in Supabase. Node: Page Added in Notion Database Retrieve Page Content: Fetches all block content from the newly added Notion page. Node: Get Blocks Content Filter Non-Text Content: Excludes blocks of type "image" and "video" to focus on textual content. Node: Filter - Exclude Media Content Summarize Content: Concatenates the Notion blocks content to create a single text for embedding. Node: Summarize - Concatenate Notion's blocks content Store in Supabase: Stores the processed documents and their embeddings into a Supabase table with a vector column. Node: Store Documents in Supabase Generate Embeddings: Utilizes OpenAI's API to generate embeddings for the textual content. Node: Generate Text Embeddings Create Metadata and Load Content: Loads the block content and creates associated metadata, such as page ID and block ID. Node: Load Block Content & Create Metadata Split Content into Chunks: Divides the text into smaller chunks for easier processing and embedding generation. Node: Token Splitter

This n8n workflow verifies the deliverability of mailing addresses stored in Groundhogg CRM by integrating with Lob’s address verification service. Who is this for? This template is designed for Groundhogg CRM users who need to ensure the accuracy of mailing addresses stored in their CRM systems. What problem is this workflow solving? / Use Case This workflow addresses the challenge of maintaining accurate mailing addresses in CRM databases by verifying the deliverability of addresses. What this workflow does A new contact is created in Groundhogg CRM Webhook sent to n8n Verify if the address is deliverable via LOB Report back to Groundhogg CRM Set Up Steps Watch this setup video: https://www.youtube.com/watch?v=nrV0P0Yz8FI Takes 10-30 minutes to set up Accounts Needed: Groundhogg CRM LOB Account (https://www.lob.com $0.00/mo 300 US addresses Verifications) n8n Before using this template, ensure you have API keys for your Groundhogg CRM app and Lob. Set up authentication for both services within n8n. How to customize this workflow to your needs You can customize this workflow by adjusting the trigger settings to match Groundhogg CRM’s workflow configuration. Additionally, you can modify the actions taken based on the deliverability outcome, such as updating custom fields or sending notifications.

Description This workflow automatically scans food delivery platforms and restaurant websites to find the best deals and discounts. It helps you save money on meals by aggregating special offers and promotions in one place. Overview This workflow automates finding the best food deals and discounts from various websites. It uses Bright Data to scrape deal information and can be configured to send you notifications or save the deals to a spreadsheet. Tools Used n8n:** The automation platform that orchestrates the workflow. Bright Data:** For scraping food deal websites without getting blocked. (Optional) Google Sheets/Discord/Telegram:** To store or get notified about the deals. How to Install Import the Workflow: Download the .json file and import it into your n8n instance. Configure Bright Data: Add your Bright Data credentials to the Bright Data node. Set Up Notifications (Optional): Configure the nodes for Google Sheets, Discord, or Telegram if you want to receive notifications. Customize: Specify the websites you want to scrape for deals. Use Cases Foodies:** Always be the first to know about the best restaurant deals in your city. Students:** Save money by finding cheap eats and special offers. Families:** Plan your meals around the best grocery and restaurant discounts. Connect with Me Website:** https://www.nofluff.online YouTube:** https://www.youtube.com/@YaronBeen/videos LinkedIn:** https://www.linkedin.com/in/yaronbeen/ Get Bright Data:** https://get.brightdata.com/1tndi4600b25 (Using this link supports my free workflows with a small commission) #n8n #automation #fooddeals #brightdata #webscraping #discounts #fooddiscounts #mealdeals #restaurantdeals #savemoney #foodoffers #n8nworkflow #workflow #nocode #foodtech #dealfinder #specialoffers #fooddelivery #budgetmeals #foodsavings #dealhunting #foodautomation #moneysaving #foodhacks #bestdeals #foodscraping

Run Apache Airflow DAG and Retrieve XCom Value What this workflow does This workflow integrates the Apache Airflow API DAGRun and XCom. It enables n8n to trigger Airflow DAGs and retrieve the execution results. Preparation: Update Airflow API Link Prefix Navigate to the airflow-api node. Update the prefix of the Airflow API link in the format: http(s)://ip:port. Example: https://airflow.example.com Configure Authentication Go to the Airflow: dag_run node. Update the Basic Auth credentials with your Airflow username and password. Repeat this step for Airflow: dag_run - state and Airflow: dag_run - get result nodes. Security Note: Using Basic Authentication requires storing credentials in plaintext. If possible, consider using API Keys or Tokens for enhanced security. An example is setting Airflow's API Authentication to basic\_auth. Choose other authentication methods if needed. Ensure the user account has the following permissions: can create on DAG Runs, can read on DAG Runs, can read on XComs, can edit on DAGs, and can read on DAGs. How to Use: To execute this workflow, use the Execute Sub-workflow node with the following input parameters: dag\_id**: The DAG ID (name) in Airflow that you want to trigger. task\_id**: The Task ID (name) from which you want to retrieve the XCom return\_value. conf**: Input data for the Airflow DAG run. wait**: Delay (in seconds) between each Airflow: dag_run - state check. wait\_time**: The maximum time (in seconds) to wait for Airflow: dag_run - state before returning an error. Output: The workflow returns the XCom result from Airflow: dag_run - get result. The XCom return_value is stored in the value field.

Universal AI Assistant - Webhook-Ready Conversational AI Transform any platform into an intelligent conversational experience with this plug-and-play n8n workflow. This AI assistant can be seamlessly integrated into websites, mobile apps, or any system that supports webhook connections. Key Features: 🔗 Universal Integration - Connect to any platform via webhook (websites, apps, bots) 🧠 Powered by Google Gemini 2.0 Flash - Fast, accurate, and context-aware responses 💾 Session Memory - Maintains conversation context for natural follow-up interactions ⚡ Real-time Responses - Instant webhook responses for smooth user experiences 🎯 Customizable Personality - Easy prompt modification for brand-specific tone Perfect For: Website Chat Widgets - Add AI support to any website instantly WhatsApp/Telegram Bots - Power messaging platforms with intelligent responses Mobile App Integration - Embed conversational AI into iOS/Android apps Customer Support Systems - Automate first-line support with context retention Lead Qualification - Intelligent pre-screening of prospects before human handoff Simple Implementation: Just send POST requests to the webhook URL with: json{ "message": "User's question here", "sessionId": "unique-session-identifier" } Ready to deploy in minutes - No complex setup required. Perfect for small businesses wanting to add AI capabilities without technical overhead. This workflow gives you a production-ready foundation that you can customize for specific client needs. The session-based memory makes it ideal for customer support scenarios where context matters, and the webhook approach means it integrates with virtually any platform your clients are already using.

This workflow captures Squarespace newsletter signups in a Google Sheet and automatically creates new Mailchimp contacts in the selected audience. It overcomes the limitation in Squarespace’s native Mailchimp integration, which only supports new, empty audiences. You can trigger the workflow manually or schedule it for continuous synchronization. Step-by-step tutorial First, you need to connect Squarespace newsletter block submission to Google Drive In Mailchimp node, choose your targeted audience in List Name or ID Connect a Squarespace Form to Google Drive To connect a form to Google Drive: In the form's storage options, click Connect on Google Drive. Log into your Google account. Click Allow to permit Squarespace to connect to Google Drive. Enter a Spreadsheet Name. This creates a new spreadsheet for your form submissions. Columns in my sheet: Submitted On Email Address Name This structure is inspired by Squarespace’s newsletter block connection, but you can modify it based on your preferred data format. 👉 Clone my Google Sheets template Requirements Credentials To use this workflow, you need: Mailchimp API Key** – Required to add contacts to Mailchimp. Google Sheets API credentials** – Required to retrieve signups from the spreadsheet. 📌 Mailchimp API Authentication Guide Explore More Templates 👉 Check out my other n8n templates

This n8n template demonstrates how to create an automated emotional story generation system that produces structured video prompts and generates corresponding images using AI. The workflow creates a complete story with 5 scenes featuring a Pakistani character named Yusra, converts them into Veo 3 video generation prompts, and generates images for each scene. Use cases include: Automated story creation for social media content Video pre-production with AI-generated storyboards Content creation for educational or entertainment purposes Multi-scene narrative development with consistent character design Good to know: Uses Gemini 2.5 Flash Lite for story generation and prompt conversion Uses Gemini 2.0 Flash Exp for image generation The image generation model may be geo-restricted in some regions Workflow includes automatic Google Drive organization and Google Sheets tracking How it works: Story Creation: Gemini AI creates a 5-scene emotional story featuring Yusra, a Pakistani girl aged 20-25 in traditional dress Folder Organization: AI generates a unique folder name with timestamp for project organization Google Sheets Setup: Creates a new sheet to track all scenes and their processing status Scene Processing: Each scene is processed individually with character and action prompts Veo 3 Prompt Conversion: Converts natural language scene descriptions into structured JSON format optimized for Veo 3 video generation, including parameters like: Detailed scene descriptions Camera movements and angles Lighting and mood settings Style and quality specifications Aspect ratios and technical parameters Image Generation: Uses Gemini's image generation model to create visual representations of each scene File Management: Automatically uploads images to Google Drive and organizes them in project folders Status Tracking: Updates Google Sheets with processing status and file URLs Automated Workflow: Includes conditional logic to handle different processing states and file movements How to use: Execute the workflow manually or set up automated triggers The system will automatically create a new story with 5 scenes Each scene gets processed through the AI pipeline Generated images are organized in Google Drive folders Track progress through the Google Sheets interface The workflow handles all file management and status updates automatically Requirements: Gemini API access for both text and image generation Google Drive for file storage and organization Google Sheets for project tracking and management n8n instance with appropriate node access Customizing this workflow: Modify the character description in the Story Creator node Adjust the number of scenes by changing the story prompt Customize the Veo 3 prompt parameters for different video styles Add additional AI models or processing steps Integrate with other content creation tools Modify the folder naming convention or organization structure Technical Features: Automated retry logic for failed operations Conditional processing based on status flags Batch processing for multiple scenes Error handling and status tracking File organization with timestamp-based naming Integration with Google Workspace services This template is perfect for content creators, educators, or anyone looking to automate story-based content creation with AI assistance.

n8n Workflow Backup to Google Drive – Automated Export of All Your Workflows This workflow is designed to automatically create backups of all your workflows in n8n and store them as individual .json files in Google Drive. It's a fully automated system that helps developers, agencies, or automation teams ensure their automation logic is always safe, versioned, and ready to restore or share. What is this for? If you’re building and managing multiple automations inside n8n, losing a workflow due to accidental deletion or misconfiguration can cost you hours of work. This template solves that by exporting all your workflows into separate files and storing them in a dated Google Drive folder. It helps with disaster recovery, version tracking, and team collaboration — without any manual exporting. How this works: -Once triggered (manually or via a schedule), the workflow performs the following steps: -Creates a new folder in your Google Drive, named with today’s date (e.g. “Workflow Backups Monday 16-05-2025”). -Connects to your n8n instance using the internal API and retrieves a list of all existing workflows. -Iterates over each workflow, converts it into a .json file using the built-in file conversion node. -Uploads each individual .json file to the newly created folder in Google Drive. -Optionally, the workflow finds and deletes old backup folders to keep your Google Drive clean and avoid clutter. You get a clean, timestamped folder with all your flows — ready to restore, send, or store securely. You can trigger it manually or schedule it (e.g., to run weekly on Monday mornings). How to set it up: Import the provided workflow JSON into your n8n instance. Set up your credentials: -Replace the placeholder “Google demo” with your actual Google Drive OAuth2 credentials in all Google Drive nodes. -Replace the placeholder “n8n demo” with your n8n API credentials so the workflow can fetch your flows. -Go to the node “Create new folder” and replace the folder ID with your own destination folder in Google Drive where backups should be stored. -(Optional) Enable the “Schedule Trigger” to run the backup automatically once a week or on your preferred interval. You’re ready to go — test it with the Manual Trigger first and check your Google Drive for results.

UTM Link Creator & QR Code Generator with Scheduled Google Analytics Reports This workflow enables marketers to generate UTM-tagged links, convert them into QR codes, and automate performance tracking in Google Analytics with scheduled reports every 7 days. This solution helps monitor traffic sources from different marketing channels and optimize campaign performance based on analytics data. Prerequisites Before implementing this workflow, ensure you have the following: Google Analytics 4 (GA4) Account & Access Ensure you have a GA4 property set up. Access to the GA4 Data API to schedule performance tracking. Refer to the Google Analytics Data API Overview for more information. Airtable Account & API Key Create an Airtable base to store UTM links, QR codes, and analytics data. Obtain an Airtable API key from your Account Settings. Detailed instructions are available in the Airtable API Authentication Guide. Step-by-Step Guide to Setting Up the Workflow 1. Generate UTM Links Create a form or interface to input: Base URL** (e.g., https://example.com) Campaign Name** (utm_campaign) Source** (utm_source) Medium** (utm_medium) Term** (Optional: utm_term) Content** (Optional: utm_content) Append UTM parameters to generate a trackable URL. 2. Store UTM Links & QR Codes in Airtable Set up an Airtable base with the following columns: UTM Link** QR Code** Campaign Name** Source** Medium** Date Created** Adjust as needed based on your tracking requirements. For guidance on setting up your Airtable base and using the API, refer to the Airtable Web API Documentation. 3. Convert UTM Links to QR Codes Use a QR code generator API (e.g., goqr.me, qrserver.com) to generate QR codes for each UTM link and store them in Airtable. 4. Schedule Google Analytics Performance Reports (Every 7 Days) Use the Google Analytics Data API to pull weekly performance reports based on UTM parameters. Extract key metrics such as: Sessions Users Bounce Rate Conversions Revenue (if applicable) Store the data in Airtable for tracking and analysis. Adjust timeframe as needed For more details on accessing and using the Google Analytics Data API, consult the Google Analytics Data API Overview. Benefits of This Workflow ✅ Track Marketing Campaigns: Easily monitor which channels drive traffic. ✅ Automate QR Code Creation: Seamless integration of UTM links with QR codes. ✅ Scheduled Google Analytics Reports: No manual reporting—everything runs automatically. ✅ Improve Data-Driven Decisions: Optimize ad spend and marketing strategies based on performance insights. This version ensures proper Markdown structure, includes relevant documentation links, and improves readability. Let me know if you need any further refinements! 🚀

This workflow transcribes audio files stored in AWS S3 and stores the information in Google Sheets. Google Drive Trigger node** triggers the workflow when a new file is uploaded in Google Drive. AWS S3 1 node** uploads the new file to an S3 bucket. AWS S3 2 node** gets the file from the S3 bucket. AWS Transcribe 1 node** creates a transciption job for the respective audio file. Wait node** waits for the transcription job from the previous node to be complete before proceeding with the workflow (necessary in case the service is busy or the file to be transcribed is large, delaying the workflow). AWS Transcribe 2 node** gets the information of the transcription job. Set node** sets the necessary values to be included in the data set. Google Sheets node** adds the transcription information to a sheet that serves as data set.

Want to check out all my flows, follow me on: https://maxmitcham.substack.com/ https://www.linkedin.com/in/max-mitcham/ Email Manager - Intelligent Gmail Classification This automation flow is designed to automatically monitor incoming Gmail messages, analyze their content and context using AI, and intelligently classify them with appropriate labels for better email organization and prioritization. ⚙️ How It Works (Step-by-Step): 📧 Gmail Monitoring (Trigger) Continuously monitors your Gmail inbox: Polls for new emails every minute Captures all incoming messages automatically Triggers workflow for each new email received 📖 Email Content Extraction Retrieves complete email details: Full email body and headers Sender information and recipient lists Subject line and metadata Existing Gmail labels and categories Email threading information (replies/forwards) 🔍 Email History Analysis AI agent checks relationship context: Searches for previous emails from the same sender Checks sent folder for prior outbound correspondence Determines if this is a first-time contact (cold email) Analyzes conversation thread history 🤖 Intelligent Classification Agent Advanced AI categorization using: Claude Sonnet 4 for sophisticated email analysis Context-aware classification based on email history Content analysis for intent and urgency detection Header analysis for automated vs. human-sent emails 🏷️ Smart Label Assignment Automatically applies appropriate Gmail labels: To Respond: Requires direct action/reply FYI: For awareness, no action needed Notification: Service updates, policy changes Marketing: Promotional content and sales pitches Meeting Update: Calendar-related communications Comment: Document/task feedback 📋 Structured Processing Ensures consistent labeling: Uses structured output parsing for reliability Returns specific Label ID for Gmail integration Applies label automatically to the email Maintains classification accuracy 🛠️ Tools Used: n8n: Workflow automation platform Gmail API: Email monitoring and label management Anthropic Claude: Advanced email content analysis Gmail Tools: Email history checking and search Structured Output Parser: Consistent AI responses 📦 Key Features: Real-time email monitoring and classification Context-aware analysis using email history Intelligent cold vs. warm email detection Multiple classification categories for organization Automatic Gmail label application Header analysis for automated email detection Thread-aware conversation tracking 🚀 Ideal Use Cases: Busy executives managing high email volumes Sales professionals prioritizing prospect communications Support teams organizing customer inquiries Marketing teams filtering promotional content Anyone wanting automated email organization Teams needing consistent email prioritization `

What it does This is a simplistic demo workflow showing how to extract a license plate number from an image of a car submitted via a form – or in more general terms showcasing how you can: use a form trigger to upload files and feed it into an LLM use a changeable LLM model for image-to-text analysis Set up steps Import the workflow Ensure you have registered and account, purchased some credits and created and API key for OpenRouter.ai Create/adapt the OpenRouter credential with your indivial API key for OpenRouter "Test workflow" and submit an image of a car with license plate to extract its number How to adapt By changing the "prompt" in th "Settings" node you can quickly adapt this exemplatory workflow to other image-to-text use cases, such as: summarization: "summarize what's seen in the image" location finding: "identify the location where the image was taken" text extraction: "extract all text from the image and return it as markdown" Thanks to using OpenRouter, you also can quickly experiment with finding good model choices by simply changing the "model" in the "Settings" node. The following models gave good results for this demo use-case: google/gemini-2.0-flash-001 meta-llama/llama-3.2-90b-vision-instruct openai/gpt-4o The llama-3.2-11b and even claude-3.5-sonnet didn't recognize all characters in all test images. Using a generic LLM-model offers a quick way of prototyping an image-to-text application. For specific use cases in serious and scalable production deployments, consider using an API based service specifically made to that purpose, such as: Google Cloud Vision API Microsoft Azure Computer Vision Azure AI Document Intelligence Amazon Textract