Workflow Templates

Who is this for? This workflow is perfect for eCommerce teams, market researchers, and product analysts who want to track or extract product information from websites that restrict scraping tools. It’s also useful for virtual assistants handling product comparison tasks. What problem is this workflow solving? Many eCommerce and retail sites use dynamic content or anti-bot protections that make traditional scraping methods unreliable. This workflow bypasses those issues by taking a screenshot of the full page, using OCR to extract visible text, and summarizing product information with GPT-4o—all fully automated. What this workflow does This workflow monitors a Google Sheet for new URLs. Once a new link is added, it performs the following steps: Trigger on New URL in Sheet – Watches for new rows added to a Google Sheet. Screenshot URL via Dumpling AI – Sends the URL to Dumpling AI’s screenshot endpoint to capture a full-page image of the product webpage. Save Screenshot to Drive Folder – Uploads the screenshot to a specific Google Drive folder for reference or logging. Extract Text from Screenshot with Dumpling AI – Uses Dumpling AI’s image-to-text endpoint to pull all visible content from the screenshot. Extract Product Info from Screenshot Text with GPT-4o – Sends the extracted raw text to GPT-4o, prompting it to identify structured product information such as product name, price, ratings, deals, and purchase options. Split Each Product Entry – Splits the GPT response (an array of product objects) so each product becomes an individual item for saving. Save Products info to Google Sheet – Appends each product’s structured details to a separate sheet in the same spreadsheet. Setup Google Sheet Create a Google Sheet with at least two sheets: Sheet1 should contain a header row with a column labeled URL. Sheet2 should contain headers: Product Name, price, purchased, ratings, deal, buyingOptions. Connect your Google account in both the trigger and final write-back node. Dumpling AI Sign up at Dumpling AI Create an API key and use it for both HTTP modules: Screenshot URL via Dumpling AI Extract Text from Screenshot with Dumpling AI The screenshot endpoint used is https://app.dumplingai.com/api/v1/screenshot. Google Drive Create a folder for storing screenshots. In the Save Screenshot to Drive Folder node, select the correct folder or provide the folder ID. Make sure permissions allow uploading from n8n. OpenAI Provide an API key for GPT-4o in the Extract Product Info from Screenshot Text with GPT-4o node. The prompt is structured to return structured product listings in JSON format. Split & Save Split Each Product Entry takes the array of product objects from GPT and makes each one a separate execution. Save Products info to Google Sheet writes structured fields into Sheet2 under: Product Name, price, purchased, ratings, deal, buyingOptions. How to customize this workflow Adjust the GPT prompt to return different product fields (e.g., shipping info, product categories). Use a filter node to limit which types of products get written to the final sheet. Add sentiment analysis to analyze review content if available. Replace Google Drive with Dropbox or another file storage app. Notes Make sure you monitor your API usage on both Dumpling AI and OpenAI to avoid rate limits. This setup is great for snapshot-based extraction where scraping is blocked or unreliable.

How it works: This workflow automates the entire LinkedIn content distribution process — from AI-powered post creation to auto-posting on both personal LinkedIn profiles and LinkedIn groups, using GPT-4o and Google Sheets as the content source and control panel. Auto-generates professional LinkedIn posts from spreadsheet topics using GPT-4o. Posts to your LinkedIn profile and multiple groups. Updates status to avoid duplicate posting. Fully customizable and reusable with your spreadsheet. Set up Steps Create and Upload the Spreadsheet Name it: Linkedin Post Sheet1 (for post topics): Columns: ID | Linkedin Post Title | Status Add post titles under Linkedin Post Title Set Status to Pending Create new sheet name as "Groups" (for group distribution): Column: GroupIds Add LinkedIn Group IDs, one per row Connect Google Sheets Nodes Connect your Google account to these nodes: Linkedin Post topic (Reads post topics) Get group id (Reads LinkedIn groups) Update Status (Writes back the status after posting) Configure GPT-4o (OpenAI) Add your OpenAI API key in the Linkedin Post creator node This node will generate high-quality content from your topic titles Connect LinkedIn Account Add your LinkedIn credentials in the Linkedin user detail node Ensure appropriate permissions to post on profile and groups Activate the Workflow : Once live, the workflow will: Monitor the Google Sheet for Pending posts. Generate content via GPT-4o. Post to: Your LinkedIn Profile Each LinkedIn Group listed in the Groups sheet Update the post Status to Posted Customization Tips Want to personalize this template? Change AI tone or style in the OpenAI node prompt Add a scheduler node if you'd like to post at fixed intervals Use a Slack or Telegram approval step before posting Integrate analytics tools to track post performance Suggested Sticky Notes for Workflow | Node or Section | Sticky Note Content | | ---------------------- | --------------------------------------------------------------------------- | | Linkedin Post topic | Reads the topic titles and statuses from Sheet1 | | OpenAI (GPT-4o) | Generates content using topic title — you can modify the tone/prompt here | | Linkedin user detail | Your personal LinkedIn credentials — required to post | | Group loop | Iterates through LinkedIn Group IDs and posts the content | | Update Status | Updates spreadsheet so the topic isn't re-posted |

Who is this for? This workflow is ideal for: Customer support teams looking to reduce manual response time SaaS companies that frequently receive product inquiries E-commerce stores with common customer questions about orders, shipping, and returns What problem is this workflow solving? Manually responding to repetitive customer emails is inefficient, prone to inconsistency, and time-consuming. This workflow solves the issue by: Automatically replying to real customer inquiries 24/7 Ensuring every response is consistent, friendly, and based on approved knowledge Preventing responses to non-inquiries like newsletters or confirmations Logging every interaction for traceability, analysis, and compliance What this workflow does This AI-powered Gmail auto-responder intelligently handles inbound emails with the following steps: Monitors your Gmail inbox for new incoming emails in real time Classifies each email as either an “Inquiry” or “Not Inquiry” using GPT-4 Gets context from a Google Sheets FAQ database The context will be used to determine the most accurate and helpful response Generates a professional reply only if it’s a valid inquiry (e.g., pricing, refund, product details) Builds a context-aware, helpful response using verified knowledge only Sends the reply to the original sender automatically Logs everything to a Google Sheet — original email, AI response, timestamp, and email address Example Use Case: An email comes in: "Hi, I want to know your pricing and refund policy." The workflow: Detects it’s an inquiry Finds the pricing and refund FAQs in your Google Sheet Sends back a professional response like: "Hi! Thanks for reaching out. Our pricing starts at \$99/month. Refunds can be requested within 30 days of purchase. Let us know if you have more questions!" Logs the interaction to your “Enquiry\_Log” tab Setup Copy the Google Sheet template here: 👉 Gmail Auto-Responder – Google Sheet Template This contains: A FAQ_Context tab (your knowledge base) An Enquiry_Log tab (interaction logs) Connect your Gmail account to the Gmail Trigger and Gmail Send nodes Add your OpenAI API key in the classification and response generator nodes Link the Google Sheet in both the FAQ lookup and logging nodes Test with a sample email — try asking a pricing and refund question to see the complete process in action How to customize this workflow to your needs Adjust tone or brand voice** in the AI prompt for a more casual or formal reply Modify classification rules** if your use case includes more custom logic Expand the FAQ database** to include new questions and answers Add multilingual support** by customizing the AI prompt to detect and respond in different languages Integrate CRM or ticketing systems** (like HubSpot, Zendesk, or Notion) to log or escalate unanswered queries

Make OpenAI Citation for File Retrieval RAG Use case In this example, we will ensure that all texts from the OpenAI assistant search for citations and sources in the vector store files. We can also format the output for Markdown or HTML tags. This is necessary because the assistant sometimes generates strange characters, and we can also use dynamic references such as citations 1, 2, 3, for example. What this workflow does In this workflow, we will use an OpenAI assistant created within their interface, equipped with a vector store containing some files for file retrieval. The assistant will perform the file search within the OpenAI infrastructure and will return the content with citations. We will make an HTTP request to retrieve all the details we need to format the text output. Setup Insert an OpenAI Key How to adjust it to your needs At the end of the workflow, we have a block of code that will format the output, and there we can add Markdown tags to create links. Optionally, we can transform the Markdown formatting into HTML.

This n8n template demonstrates how to calculate the evaluation metric "Relevance" which in this scenario, measures the relevance of the agent's response to the user's question. The scoring approach is adapted from the open-source evaluations project RAGAS and you can see the source here https://github.com/explodinggradients/ragas/blob/main/ragas/src/ragas/metrics/_answer_relevance.py How it works This evaluation works best for Q&A agents. For our scoring, we analyse the agent's response and ask another AI to generate a question from it. This generated question is then compared to the original question using cosine similarity. A high score indicates relevance and the agent's successful ability to answer the question whereas a low score means agent may have added too much irrelevant info, went off script or hallucinated. Requirements n8n version 1.94+ Check out this Google Sheet for a sample data https://docs.google.com/spreadsheets/d/1YOnu2JJjlxd787AuYcg-wKbkjyjyZFgASYVV0jsij5Y/edit?usp=sharing

🤖 AI Cart Recovery Agent: Smart Abandoned Checkout Assistant Transform abandoned carts into recovered sales with intelligent automation. This sophisticated n8n workflow monitors checkout abandonment, implements smart waiting periods, and sends AI-generated personalized recovery emails only when needed - maximizing conversions while respecting customer experience. 🔄 How It Works This intelligent 7-step recovery system recovers lost sales automatically: Step 1: Initial Abandonment Detection The workflow fetches current abandoned checkout data from your e-commerce platform (Shopify, WooCommerce, etc.), identifying customers who added items but didn't complete their purchase. Step 2: Strategic Grace Period Instead of immediately sending recovery emails, the system waits 1 hour (customizable), giving customers natural time to complete their purchase without pressure or interruption. Step 3: Smart Re-verification After the waiting period, the workflow rechecks the abandonment status by fetching updated checkout data, ensuring accuracy before taking action. Step 4: Intelligent Decision Logic Advanced conditional logic compares initial and updated abandonment lists, determining if customers are still abandoned or have completed their purchase during the grace period. Step 5: AI-Powered Email Generation For customers still showing abandonment, GPT generates personalized recovery emails featuring: Customer's actual name for personal connection Specific products left in their cart Friendly, non-pushy messaging tone Optional discount incentives Compelling call-to-action to complete purchase Step 6: Automated Email Delivery Personalized recovery emails are sent directly to abandoned customers via Gmail or your preferred email service, maintaining professional branding and deliverability. Step 7: Comprehensive Activity Logging All recovery attempts are logged in Google Sheets for tracking, including customer details, email content, and campaign performance analytics. ⚙️ Setup Steps Prerequisites E-commerce platform with API access (Shopify, WooCommerce, BigCommerce) OpenAI API key for personalized email generation Gmail or SMTP email service for delivery Google Sheets for activity tracking and analytics n8n instance (cloud or self-hosted) E-commerce Platform Configuration Shopify Setup: API Endpoint: https://your-store.myshopify.com/admin/api/2023-10/checkouts.json Authentication: X-Shopify-Access-Token header Required Permissions: Read checkouts, Read customers Parameters: status=abandoned WooCommerce Setup: API Endpoint: https://your-site.com/wp-json/wc/v3/orders Authentication: Consumer Key/Secret or JWT Parameters: status=pending, status=failed Required Plugins: WooCommerce REST API Configuration Steps 1. Credential Setup E-commerce API**: Store admin API access tokens or keys OpenAI API Key**: GPT-4 access for intelligent email generation Gmail OAuth2**: Professional email delivery service Google Sheets OAuth2**: Activity logging and performance tracking 2. Abandonment Detection Configuration Monitoring Frequency**: Set workflow trigger schedule (hourly, daily) Grace Period Duration**: Customize wait time (default: 1 hour) Platform Integration**: Configure API endpoints for your specific platform Data Filtering**: Set criteria for what constitutes abandonment 3. AI Email Customization Default email generation includes: Personalization Level**: Customer name, product specifics, cart value Tone Customization**: Friendly, urgent, helpful, or premium Discount Integration**: Optional percentage or fixed amount offers Brand Voice**: Maintain consistent company messaging and style 4. Recovery Campaign Settings Email Timing**: Optimal sending times based on customer time zones Frequency Limits**: Prevent over-emailing with cooldown periods Segmentation Rules**: Different approaches for high-value vs standard carts Follow-up Sequences**: Multi-email recovery campaigns with escalating incentives 5. Performance Tracking Setup Analytics Dashboard**: Google Sheets with recovery metrics and ROI Success Tracking**: Monitor completion rates and revenue recovered A/B Testing**: Compare different email approaches and timing Customer Journey**: Track from abandonment through recovery completion 🚀 Use Cases E-commerce Retailers Fashion & Apparel**: Recover high-value clothing and accessory purchases Electronics**: Target abandoned tech purchases with technical support offers Home & Garden**: Remind customers about seasonal or home improvement items Beauty & Cosmetics**: Recover abandoned skincare and makeup purchases Subscription & SaaS Businesses Software Trials**: Convert abandoned trial signups into paid subscriptions Membership Sites**: Recover incomplete membership purchases Online Courses**: Re-engage learners who abandoned course purchases Digital Services**: Follow up on abandoned service bookings or consultations B2B E-commerce Office Supplies**: Recover bulk order abandonments with volume discounts Industrial Equipment**: Follow up on high-value equipment quote requests Professional Services**: Re-engage businesses that abandoned service bookings Software Licenses**: Recover enterprise software purchase abandonments Specialty Retailers Luxury Goods**: Provide white-glove service for high-value abandoned purchases Custom Products**: Follow up on personalized or custom order abandonments Seasonal Items**: Time-sensitive recovery for holiday or event-specific products Limited Edition**: Create urgency for exclusive or limited availability items Service-Based Businesses Travel & Hospitality**: Recover abandoned hotel, flight, or package bookings Event Tickets**: Re-engage customers who abandoned concert or event purchases Professional Services**: Follow up on abandoned consultation or service bookings Fitness & Wellness**: Recover abandoned membership or class package purchases 🔧 Advanced Customization Options Multi-Platform Integration Extend beyond single platform monitoring: Shopify Plus: Advanced checkout analytics and customer segmentation WooCommerce: Custom post-purchase and abandonment tracking Magento: Enterprise-level cart recovery with customer journey mapping BigCommerce: API-driven recovery with advanced personalization Custom Platforms: Webhook-based abandonment detection and recovery Intelligent Email Sequencing Create sophisticated recovery campaigns: Progressive Incentives**: Escalating discounts over multiple touchpoints Behavioral Triggers**: Different emails based on cart value, customer history Seasonal Campaigns**: Holiday-specific recovery messaging and offers Win-Back Sequences**: Long-term customer re-engagement beyond immediate recovery Advanced Personalization Enhance AI-generated content with: Purchase History Analysis**: Reference previous purchases and preferences Browsing Behavior**: Include recently viewed items and categories Geographic Personalization**: Local offers, shipping options, or store locations Demographic Targeting**: Age, gender, or interest-based messaging customization Performance Optimization Implement advanced tracking and optimization: Revenue Attribution**: Track exact recovery amounts and ROI calculations Customer Lifetime Value**: Prioritize high-value customer recovery efforts Conversion Funnel Analysis**: Identify optimal timing and messaging strategies Predictive Analytics**: Use ML to predict recovery likelihood and optimize approaches 📊 Recovery Email Examples Fashion Retailer Example: Subject: You left something stylish behind, Sarah! Hi Sarah, I noticed you were checking out those gorgeous items in your cart earlier - the Bohemian Summer Dress and Classic Leather Handbag have been waiting for you! I completely understand if you got busy or needed time to think it over. These pieces are still available and ready to ship to you today. Since you showed such great taste in selecting these items, I'd love to offer you 10% off your order to make the decision easier. Just use code WELCOME10 at checkout. Your cart includes: • Bohemian Summer Dress (Size M) - $89.99 • Classic Leather Handbag (Brown) - $156.99 Complete your purchase now and get free shipping to your door! [Complete My Purchase] Best regards, The StyleHub Team P.S. These items are popular and inventory is limited - don't wait too long! Software/SaaS Example: Subject: Your ProductivityPro trial is waiting, Mike Hi Mike, You were just one step away from unlocking the full power of ProductivityPro for your team at TechStartup Inc. I noticed you explored our Premium Plan features - the advanced reporting and team collaboration tools that could streamline your workflow and boost productivity by up to 40%. Since you invested time exploring our platform, I'd like to offer you an exclusive 25% discount on your first year. This offer is valid for the next 48 hours. Your selected plan: • ProductivityPro Premium (5 users) - $99/month • With 25% discount: $74/month (Save $300/year!) Ready to transform your team's productivity? [Activate My Account] Questions? Reply to this email or schedule a quick 15-minute demo call. Best regards, David Chen Customer Success Manager, ProductivityPro High-Value B2B Example: Subject: Your equipment quote is ready for approval, Jennifer Hi Jennifer, Thank you for your interest in our Industrial Packaging System for ManuCorp's new facility expansion. I understand that equipment investments of this scale require careful consideration and stakeholder alignment. Your configured system includes: • Model X5000 Packaging Line - $45,000 • Installation & Training Package - $8,000 • Extended 3-Year Warranty - $3,500 Total Investment: $56,500 Given the scope of your project, I'd like to extend our Q1 promotion pricing, which provides: 15% discount on equipment ($6,750 savings) Free installation supervision ($2,000 value) Expedited 6-week delivery This brings your total to $48,750 - a savings of $7,750. I'm available for a brief call to address any technical questions or help facilitate internal approvals. [Accept Quote & Proceed] Best regards, Robert Martinez Senior Sales Engineer Industrial Solutions Inc. Direct: (555) 123-4567 🛠️ Troubleshooting & Best Practices Common Issues & Solutions API Rate Limiting Implement exponential backoff for API requests Stagger workflow execution times across different stores Monitor API usage and upgrade plans as needed Cache frequently accessed data to reduce API calls Email Deliverability Challenges Use authenticated SMTP services with proper SPF/DKIM setup Monitor sender reputation and email engagement metrics Implement opt-out mechanisms and respect unsubscribe requests Segment email lists and avoid over-emailing customers False Positive Recoveries Extend grace periods for complex checkout processes Implement more sophisticated abandonment detection logic Add customer behavior analysis before triggering recovery Create exception rules for technical checkout failures Optimization Strategies Recovery Timing Optimization A/B test different grace period durations (30 min, 1 hour, 3 hours) Analyze customer behavior patterns to optimize sending times Consider time zone differences for global customer bases Implement seasonal timing adjustments for holidays and events Content Personalization Enhancement Continuously refine AI prompts based on successful recoveries Implement dynamic discount strategies based on cart value Create customer segment-specific messaging approaches Add urgency elements for time-sensitive or limited inventory items Performance Measurement Track recovery rates, revenue impact, and customer satisfaction Implement cohort analysis for long-term customer value impact Monitor email engagement metrics and optimize accordingly Calculate true ROI including customer acquisition costs and lifetime value 📈 Success Metrics Recovery Performance Indicators Recovery Rate**: Percentage of abandoned carts successfully recovered Revenue Recovery**: Total dollar amount recovered from abandoned purchases Email Engagement**: Open rates, click rates, and conversion rates Time to Recovery**: Average time from abandonment to completed purchase Business Impact Measurements ROI Calculation**: Revenue recovered vs workflow operational costs Customer Retention**: Impact on long-term customer relationships Average Order Value**: Effect on overall purchase values post-recovery Operational Efficiency**: Automation savings vs manual recovery efforts 📞 Questions & Support Need help implementing your AI Cart Recovery Agent? 📧 E-commerce Automation Expert Support Email**: Yaron@nofluff.online Response Time**: Within 24 hours on business days Specialization**: E-commerce automation, cart recovery optimization, AI email personalization 🎥 Comprehensive Implementation Resources YouTube Channel**: https://www.youtube.com/@YaronBeen/videos Complete setup guides for major e-commerce platforms Advanced AI email personalization techniques Recovery campaign optimization strategies Integration tutorials for Shopify, WooCommerce, and custom platforms Performance tracking and analytics implementation 🤝 E-commerce Automation Community LinkedIn**: https://www.linkedin.com/in/yaronbeen/ Connect for ongoing e-commerce automation support and consulting Share your cart recovery success stories and ROI achievements Access exclusive templates for different industry verticals Join discussions about e-commerce automation trends and innovations 💬 Support Request Guidelines Include in your support message: Your e-commerce platform and current cart abandonment rates Average order values and customer segments you serve Current recovery processes and conversion challenges Integration requirements with existing marketing tools Specific technical errors or workflow execution issues

Automated Content Idea Generation and Expansion with Google Gemini and Google Sheets This n8n workflow automates the process of generating content ideas based on a user-defined topic, then expands each idea into a more detailed content piece (like a blog post) using Google Gemini, and finally saves all the generated data (idea title, description, and full content) into a Google Sheet. It's a powerful tool for streamlining content creation workflows. This workflow includes: Generation of multiple content ideas from a single topic. Expansion of each idea into detailed content using AI. Storage of ideas and generated content in a structured Google Sheet. Sticky Notes within the workflow for inline documentation and setup guidance. Prerequisites n8n Instance: You need a running n8n instance (self-hosted or cloud). Google AI Account: Access to Google AI (Gemini). You will need an API key. Google Account: Access to Google Sheets. You will need to create or use an existing spreadsheet with specific column headers. Installation and Setup Import the Workflow: Copy the entire JSON code provided. In your n8n instance, go to "Workflows". Click "New" -> "Import from JSON". Paste the JSON code and click "Import". Configure Credentials: Google AI (Gemini): Find the "Google Gemini Chat Model for Content Idea Generator" node and the "Google Gemini Chat Model for Content Generation" node. Click on the "Credentials" field in both nodes (it will likely show a placeholder name like "Google Gemini(PaLM) Api account"). Click "Create New". Select "Google AI API". Enter your Google AI API Key. Save the credential. (You can reuse the same credential for both nodes). Google Sheets: Find the "Google Sheets" node. Click on the "Credentials" field (it will likely show a placeholder name like "Google Sheets account"). Click "Create New". Select "Google Sheets OAuth2 API". Follow the steps to connect your Google Account and grant n8n access to Google Sheets. Save the credential. Configure Google Sheets Node: Open the "Google Sheets" node settings. Spreadsheet ID: Replace the placeholder value with the actual ID of your Google Sheet. You can find the Spreadsheet ID in the URL of your Google Sheet (it's the long string of characters between /d/ and /edit). Sheet Name: Select or enter the name or GID of the sheet within your spreadsheet where you want to save the data (e.g., Sheet1 or gid=0). Columns: Ensure your Google Sheet has columns named title, description, and content. The node is configured to map the generated data to these specific column headers. Save the node settings. Review Sticky Notes: Look at the Sticky Notes placed around the workflow canvas. They provide helpful context and reminders for setup, required Google Sheet columns, and the AI models used. How to Use Activate the Workflow: Toggle the workflow switch to "Active". Trigger the Workflow: Since this workflow uses a "When clicking ‘Execute workflow’" node as the trigger, you can run it directly from the n8n editor. Click the "Execute Workflow" button. The workflow will start automatically. Set the Topic: Open the "Set the input fields" node. Modify the topic value to the subject you want to generate content ideas about. Save the node settings. Monitor Execution: Watch the workflow execute. The nodes will light up as they process. The "Loop Over Items" node will show multiple executions as it processes each generated idea. Check Results: The generated content ideas (title, description) and the expanded content will be written as new rows in the Google Sheet you configured. Each row will correspond to one generated idea and its content. This workflow provides a robust starting point for AI-assisted content creation. You can customize the AI prompts in the "Content Idea Generator" and "LLM Content Generator" nodes to refine the output style and format, or integrate additional steps like sending notifications or further processing the generated content.

🔧 How It Works Telegram Trigger – Listens for incoming messages from users via your Telegram bot. Watch Full Step-by-step Guide Video here: https://www.youtube.com/watch?v=GzWO7_1lyI8 AI Agent – Processes the message to determine the user's intent (booking or canceling) and extracts necessary details like date, time, and participant names. Google Calendar Node – Depending on the intent: Booking: Creates a new event in Google Calendar with the extracted details. Canceling: Searches for the specified event and deletes it from the calendar. Telegram Node – Sends a confirmation message back to the user, informing them of the successful booking or cancellation. 🧠 Why This is Useful Managing appointments can be time-consuming. This workflow automates the process, allowing users to schedule or cancel meetings effortlessly through a simple chat interface. It's ideal for: Solopreneurs managing their own schedules. Small businesses coordinating meetings with clients. Anyone looking to streamline their appointment management process. 🪜 Setup Instructions Set Up Telegram Bot: Create a new bot using BotFather on Telegram. Obtain the API token and set up the Telegram Trigger node in n8n with this token. OpenAI Platform API required for OpenAI Chat Model Connect to Google Calendar For the full video tutorial, watch here: https://youtu.be/GzWO7_1lyI8

Overview Transform your LLM into a powerful GitHub automation specialist with this n8n workflow template. In a world where multiple MCP servers can overwhelm LLMs with context, this streamlined solution provides a dedicated GitHub Agent that handles all GitHub API operations through a single, specialized tool. When you need GitHub operations like creating repositories, managing issues, or handling pull requests, your LLM can make one simple call to the GitHub Agent. This agent specializes exclusively in GitHub MCP server operations, offloading all contextual complexity and providing clean, efficient GitHub automation. ✨ Features Single MCP Server Trigger** - One tool and one parameter to handle all GitHub API interactions Specialized GitHub Agent** - Dedicated AI agent with direct GitHub MCP Server connection Self-Executing Workflow** - "When Executed by Another Workflow" trigger enables seamless workflow chaining Scalable Architecture** - Ready to integrate with unlimited GitHub tools and operations Context Optimization** - Reduces LLM token usage by delegating GitHub complexity to a specialized agent Flexible Request Processing** - Handles any GitHub operation through natural language requests 🎯 Use Cases Repository Management** - Create, clone, and manage repositories programmatically Issue Tracking** - Automate issue creation, updates, and management workflows Pull Request Automation - Streamline code review and merge processes GitHub Actions Integration** - Trigger and monitor CI/CD workflows Team Collaboration** - Automate notifications and team management tasks Documentation Updates** - Automatically update README files and documentation 🏗️ Workflow Architecture Node Breakdown: MCP Server Trigger - Receives requests with GitHub operation parameters Set GitHub Username - Configures GitHub user context for API calls OpenAI Chat Model - Powers the intelligent GitHub agent with contextual understanding Simple Memory - Maintains conversation context and operation history GitHub AI Agent - Specialized Tools Agent with direct GitHub MCP Server access [MCP Server Trigger] → [Set GitHub Username] → [GitHub AI Agent] ↓ [OpenAI Chat Model] ← [Simple Memory] ← [GitHub API Operations] 📋 Requirements Essential Prerequisites: ✅ OpenAI API Key - For AI Agent and Chat Model functionality ✅ GitHub Username Configuration - Edit the "Set GitHub Username" node with your GitHub username for API calls ✅ n8n Version - Compatible with n8n 2024+ releases ✅ MCP Server Setup - Existing GitHub MCP server configuration Recommended Setup: GitHub Personal Access Token with appropriate permissions Basic understanding of n8n workflow configuration Familiarity with GitHub API operations 🚀 Setup Instructions Step 1: Import and Configure Import the workflow template into your n8n instance Navigate to the Set GitHub Username node Replace the placeholder with your actual GitHub username Step 2: API Keys Setup Configure your OpenAI API key in the Chat Model node Ensure your GitHub credentials are properly configured in n8n Test the connection to verify API access Step 3: MCP Server Integration Connect your existing GitHub MCP server to the workflow Verify the MCP Server Trigger is properly configured Test with a simple GitHub operation (e.g., "List my repositories") Step 4: Deploy and Test Activate the workflow in your n8n instance Test with various GitHub operations to ensure functionality Monitor execution logs for any configuration issues 🔧 Customization Options Agent Behavior Modify the Chat Model prompt** to adjust agent personality and response style Configure memory settings** to control conversation context retention Adjust timeout settings** for long-running GitHub operations GitHub Operations Extend supported operations** by adding new GitHub API endpoints Configure repository filters** to limit scope of operations Set up notification preferences** for important GitHub events Integration Points Webhook triggers** for real-time GitHub event processing Scheduled operations** for regular repository maintenance Cross-workflow triggers** for complex automation chains 💡 Pro Tips Start Simple**: Begin with basic operations like repository listing before attempting complex workflows Monitor Token Usage**: The specialized agent approach significantly reduces OpenAI API costs Batch Operations**: Group related GitHub operations in single requests for efficiency Error Handling**: The agent provides detailed error messages for troubleshooting 🤝 Support and Community Documentation**: Official n8n Documentation Community Forum**: n8n Community Issues & Contributions**: Feel free to suggest improvements or report issues 📄 License This workflow template is provided under the MIT License. You're free to use, modify, and redistribute with attribution. Created by: William Lettieri Version: 1.0 Last Updated: May 28, 2025 Compatibility: n8n 2024+

PromptCraft AI – Telegram Image Generator 🚀 How It Works PromptCraft AI is an n8n automation that transforms simple image ideas sent through Telegram into stunning AI-generated images using OpenAI's DALL·E (or other image models). 🔁 Workflow Overview: Telegram Trigger: Listens for messages from a user on Telegram. Prompt Expansion: The message is transformed into a rich image description using GPT (OpenAI Chat Model). Image Generation: The prompt is passed to OpenAI's image API to generate a high-quality image. Send Image: The final image is sent back to the user on Telegram. (Optional) Log image titles and links to Google Drive and Google Sheets. ⚙️ Setup Instructions 📋 Prerequisites [ ] n8n installed (Self-hosted or via n8n.cloud) [ ] Telegram bot token (via @BotFather) [ ] OpenAI API key (platform.openai.com) [ ] Google Sheets & Drive OAuth2 credentials (optional) 🧠 Step-by-Step Configuration 1. 📥 Import the Workflow Go to n8n → click Import → upload PromptCraft_AI_Template.json 2. 🔐 Set Up Credentials In Credentials, add the following: Telegram API → Paste your bot token OpenAI API → Paste your OpenAI API key (Optional) Google Sheets OAuth2, Google Drive OAuth2 3. 🔄 Replace Placeholders Open each node that requires credentials: Replace REPLACE_OPENAI_API_KEY with your actual OpenAI API key Replace REPLACE_TELEGRAM_API_ID and credential names as needed (Optional) Update Google Drive Folder ID & Sheet ID in respective nodes 4. ✅ Activate the Workflow Turn on the Telegram Trigger node. Deploy and activate the full workflow. 5. ✉️ Test It Out Send your Telegram bot a message like: > a knight riding a robotic horse in the future Receive the generated image back in Telegram! 💡 Pro Tips Use detailed or imaginative inputs for better outputs. Fine-tune the GPT prompt for specific visual styles. Extend with Google Vision, image upscaling, or watermarking. 🛟 Support For setup assistance or custom feature requests, feel free to contact me @dimejicole21@gmail.com Happy Prompting! 🖼✨

Smart Customer Support AI Agent with Gmail and Telegram Who is this for? This workflow is perfect for: Small to medium businesses** looking to automate customer support E-commerce stores** handling order inquiries and customer questions SaaS companies** providing technical support to users Service providers** managing appointment bookings and general inquiries Startups** wanting to provide 24/7 customer service without hiring full-time staff Agencies** managing client communications across multiple channels What problem is this workflow solving? Customer support is essential but resource-intensive. Common challenges include: Slow response times** leading to frustrated customers Repetitive questions** consuming valuable staff time Inconsistent responses** across different support agents Limited availability** outside business hours Scaling support costs** as business grows Context loss** when customers switch between channels This workflow eliminates these pain points by providing instant, consistent, and intelligent responses 24/7. What this workflow does Core Functionality Multi-Channel Monitoring: Simultaneously watches Gmail and Telegram for customer inquiries Intelligent Processing: Uses AI to understand customer intent and context Knowledge Base Integration: Accesses your company's FAQ and support information Contextual Responses: Provides personalized, helpful replies maintaining conversation history Smart Escalation: Automatically escalates complex issues to human agents Comprehensive Logging: Tracks all interactions for analytics and improvement AI Agent Capabilities Natural Language Understanding**: Comprehends customer questions in plain English Context Awareness**: Remembers previous conversations with each customer Knowledge Retrieval**: Searches your knowledge base for accurate information Response Generation**: Creates professional, brand-appropriate responses Escalation Decision**: Identifies when human intervention is needed Multi-Channel Support**: Handles Gmail and Telegram with channel-specific formatting Automation Features Auto-Response**: Replies to customers within seconds Email Management**: Marks processed emails as read Conversation Threading**: Maintains context in email threads and Telegram chats Error Handling**: Gracefully handles failures with admin notifications Analytics Tracking**: Logs interactions for performance monitoring Setup Prerequisites Active Google Workspace or Gmail account Telegram account for bot creation OpenAI API access Google Sheets access n8n instance (cloud or self-hosted) Step 1: Credential Setup Gmail OAuth2 Configuration Go to Google Cloud Console Create new project or select existing one Enable Gmail API Create OAuth 2.0 credentials Add authorized redirect URIs for n8n In n8n: Settings → Credentials → Add Gmail OAuth2 Enter Client ID and Client Secret Complete OAuth flow Telegram Bot Setup Message @BotFather on Telegram Create new bot with /newbot command Choose bot name and username Copy the bot token In n8n: Settings → Credentials → Add Telegram Enter bot token Set webhook URL in bot settings OpenAI API Configuration Sign up at OpenAI Platform Generate API key in API Keys section In n8n: Settings → Credentials → Add OpenAI Enter API key Choose appropriate model (gpt-4o-mini recommended) Google Sheets Setup Use existing Google account from Gmail setup In n8n: Settings → Credentials → Add Google Sheets OAuth2 Complete authorization flow Step 2: Google Sheets Preparation Create three Google Sheets in your Google Drive: Knowledge Base Sheet Sheet Name**: "Knowledge Base" Columns**: ID, Category, Question/Topic, Answer/Response, Keywords, Last_Updated Import sample data from the Knowledge Base example Customize with your company's FAQs and policies Escalation Tracker Sheet Sheet Name**: "Escalations" Columns**: Timestamp, Customer_Name, Customer_Contact, Inquiry_Summary, Escalation_Reason, Priority, Status, Assigned_To This will be auto-populated by the AI agent Interaction Log Sheet Sheet Name**: "Interaction Log" Columns**: Timestamp, Channel, Customer_Name, Customer_Contact, Inquiry_Subject, Customer_Message, AI_Response, Response_Time, Status This tracks all customer interactions for analytics Step 3: Workflow Configuration Import Template Copy the workflow JSON from the template In n8n: Import workflow from JSON Replace placeholder Sheet IDs with your actual Google Sheet IDs Update Sheet References Open each Google Sheets node Select your created sheets from the dropdown Verify column mappings match your sheet structure Customize AI Prompts Edit the "Customer Support AI Agent" node Update system message with: Your company name and description Brand voice and tone guidelines Specific policies and procedures Escalation criteria Configure Error Notifications (Optional) Set up Slack webhook or email notifications Update error notification node with your webhook URL Customize error message format Step 4: Testing Test Gmail Integration Send test email to your support Gmail account Check workflow execution in n8n Verify response is sent and email marked as read Check interaction logging in Google Sheets Test Telegram Integration Send message to your Telegram bot Verify bot responds appropriately Test conversation memory with follow-up messages Check escalation functionality with complex request Test Knowledge Base Ask questions covered in your knowledge base Verify AI retrieves and uses correct information Test with variations of the same question Ensure responses are consistent and helpful How to customize this workflow to your needs Brand Voice Customization Update the AI system prompt to include: Your company's tone (formal, casual, friendly) Key phrases and terminology you use Brand personality traits Communication style preferences Knowledge Base Expansion Add industry-specific FAQs Include product documentation Add troubleshooting guides Create category-specific responses Escalation Rules Customize when to escalate by modifying the AI agent instructions: Billing disputes over $X amount Technical issues requiring developer help Angry or dissatisfied customers Requests outside standard services Legal or compliance questions Additional Channels Extend the workflow to support: Slack**: Add Slack triggers and response nodes WhatsApp**: Integrate WhatsApp Business API Web Chat**: Add webhook triggers for website chat Discord**: Connect Discord bot integration Analytics Enhancement Add sentiment analysis to customer messages Implement customer satisfaction scoring Create automated reporting dashboards Set up alert thresholds for escalation rates Integration Opportunities CRM Integration**: Connect to HubSpot, Salesforce, or Pipedrive Ticketing System**: Link to Zendesk, Freshdesk, or Jira Service Desk E-commerce Platform**: Integrate with Shopify, WooCommerce, or Magento Calendar Booking**: Connect to Calendly or Acuity for appointment scheduling Advanced Features Multi-language Support**: Add translation capabilities Voice Messages**: Integrate speech-to-text for Telegram voice notes Image Recognition**: Process customer screenshots for technical support Proactive Outreach**: Send follow-up messages based on customer behavior Workflow Maintenance Daily Tasks Review escalation queue Monitor error notifications Check response quality in interaction log Weekly Reviews Analyze customer interaction patterns Update knowledge base with new common questions Review escalation reasons and optimize AI prompts Monthly Optimization Export interaction data for detailed analysis Calculate key metrics (response time, resolution rate, escalation rate) Update AI model parameters based on performance Expand knowledge base with seasonal or trending topics Key Metrics to Track Response Time**: Average time from customer message to AI response Resolution Rate**: Percentage of inquiries resolved without escalation Customer Satisfaction**: Based on follow-up surveys or sentiment analysis Escalation Rate**: Percentage of conversations requiring human intervention Channel Performance**: Effectiveness of Gmail vs Telegram vs other channels Knowledge Base Usage**: Which topics are accessed most frequently Peak Hours**: When customers contact support most often Troubleshooting Common Issues Gmail not triggering**: Check OAuth permissions and API quotas Telegram bot not responding**: Verify bot token and webhook configuration AI responses seem off**: Review and update system prompts Escalations not logging**: Check Google Sheets permissions and column mapping High escalation rate**: Expand knowledge base and refine AI instructions Performance Optimization Monitor OpenAI API usage and costs Adjust AI model temperature for response consistency Optimize knowledge base for faster searches Set appropriate conversation memory limits This workflow provides a solid foundation for automated customer support that can be extensively customized to match your specific business needs and grow with your company.

Set Up ElevenLabs Voice Chat Agent using Graph RAG Knowledge Graphs as Experts This workflow creates an AI voice chatbot agent that has access to several knowledge bases at the same time (used as "experts"). These knowledge bases are provided using the InfraNodus GraphRAG using the knowledge graphs and providing high-quality responses without the need to set up complex RAG vector store workflows. We use ElevenLabs to set up a voice agent that can be embedded to any website or used via their API. The advantages of using GraphRAG instead of the standard vector stores for knowledge are: Easy and quick to set up (no complex data import workflows needed) and to update with new knowledge A knowledge graph has a holistic overview of your knowledge base Better retrieval of relations between the document chunks = higher quality responses Ability to reuse in other n8n workflows How it works This template uses the n8n AI agent node as an orchestrating agent that decides which tool (knowledge graph) to use based on the user's prompt. The user's prompt is received from the ElevenLabs Conversational AI agent via an n8n Webhook, which also takes care of the voice interaction. The response from n8n is then sent to the Webhook, which is polled by the ElevenLabs voice agent. This agent processes the response and provides the final answer. Here's a description step by step: The user submits a question using ElevenLabs voice interface The question is sent via the knowledge_base tool in ElevenLabs to the n8n Webhook with the POST request containing the user's prompt and sessionID for Chat Memory node in n8n. The n8n AI agent node checks a list of tools it has access to. Each tool has a description of the knowledge auto-generated by InfraNodus (we call each tool an "expert"). The n8n AI agent decides which tool should be used to generate a response. It may reformulate user's query to be more suitable for the expert. The query is then sent to the InfraNodus HTTP node endpoint, which will query the graph that corresponds to that expert. Each InfraNodus GraphRAG expert provides a rich response that takes the whole context into account and provides a response from each expert (graph) along with a list of relevant statements retrieved using a combination or RAG and GraphRAG. The n8n AI Agent node integrates the responses received from the experts to produce the final answer. The final answer is sent back to the Webhook endpoint ElevenLabs conversational AI agent picks up the response arriving from the knowledge_base tool via the webhook and then condenses it for conversational format and transforms text into voice. How to use You need an InfraNodus GraphRAG API account and key to use this workflow. Create an InfraNodus account Get the API key at https://infranodus.com/api-access and create a Bearer authorization key for the InfraNodus HTTP nodes. Create a separate knowledge graph for each expert (using PDF / content import options) in InfraNodus For each graph, go to the workflow, paste the name of the graph into the body name field. Keep other settings intact or learn more about them at the InfraNodus access points page. Once you add one or more graphs as experts to your flow, add the LLM key to the OpenAI node and launch the workflow You will also need to set up an ElevenLabs account and to set up a conversational AI agent there. See the Post note in the n8n workflow for a complete step-by-step description or our support article on setting up ElevenLabs AI voice agent Once the voice AI agent is ready, you might want to combine it with a text AI chatbot workflow so your users have a choice between the text and voice interaction. In that case, you may be interested to use our free open-source website popup chat widget popupchat.dev where you can create an embed code to add to your blog or website and allow the user to choose between the text and voice interaction. Requirements An InfraNodus account and API key An OpenAI (or any other LLM) API key An ElevenLabs account FAQ 1. How many "experts" should I aim for? We recommend to aim for the number of experts as the optimal number of people in a team, which is usually 2-7. If you add more experts, your AI orchestrating agent will have troubles choosing the most suitable "expert" tool for the user's query. You can mitigate this by specifying in the AI agent description that it can choose maximum 3-7 experts to provide a response. 2. Why use InfraNodus GraphRAG and not standard vector store for knowledge? First, vector stores are complex to set up and to update. You'd need a separate workflow for that, decide on the vector dimensions, add metadata to your knowledge, etc. With InfraNodus, you have a complete RAG / GraphRAG solution under the hood that is easy to set up and provides high-quality responses that takes the overall structure and the relations between your ideas into account. 3 Why not use ElevenLabs' own knowledge? One of the reasons is that you want your knowledge base to be in one place so you can reuse it in other n8n workflows. Another reason is that you will not have such a good separation between the "experts" when you converse with the agent. So the answers you get will be based on top matches from all the books / articles you upload, while with the InfraNodus GraphRAG setup you can better control which graphs are consulted as experts and have an explicit way to display this data. Customizing this workflow You can use this same workflow with a Telegram bot, so you can interact with it using Telegram. There are many more customizations available on our GitHub repo for n8n workflows. Check out the complete setup guide for this workflow at https://support.noduslabs.com/hc/en-us/articles/20318967066396-How-to-Build-a-Text-Voice-AI-Agent-Chatbot-with-n8n-Elevenlabs-and-InfraNodus Also check out the video tutorial with a demo: