Workflow Templates

VEXA: AI-Powered Meeting Intelligence I'll be honest, I built this because I was getting lazy in meetings and missing key details. I started with a simple VEXA integration for transcripts, then added AI to pull out summaries and tasks. But that just solved part of the problem. The real breakthrough came when we integrated Mem0, creating a persistent memory of every conversation. Now, you can stop taking notes and actually focus on the person you're talking to, knowing a system is tracking everything that matters. This is the playbook for how we built it. How It Works This isn't just one workflow; it's a two-part system designed to manage the entire meeting lifecycle from start to finish. Bot Management: It starts when you flick a switch in your CRM (Baserow). A command deploys or removes an AI bot from Google Meet. No fluff—it's there when you need it, gone when you don't. The workflow uses a quick "digital sticky note" in Redis to remember who the meeting is with and instantly updates the status in your Baserow table. AI Analysis & Memory: Once the meeting ends, VEXA sends the transcript over. Using the client ID (thank god for redis) , we feed the conversation to an AI model (OpenAI). It doesn't just summarize; it extracts actionable next steps and potential risks. All this structured data is then logged into a memory layer (Mem0), creating a permanent, searchable record of every client conversation. Setup Steps: Your Action Plan This is designed for rapid deployment. Here's what you do: Register Webhook: Run the manual trigger in the workflow once. This sends your n8n webhook URL to VEXA, telling it where to dump transcripts after a call. Connect Your CRM: Copy the vexa-start webhook URL from n8n. Paste it into your Baserow automation so it triggers when you set the "Send Bot" field to Start_Bot. Integrate Your Tools: Plug your VEXA, Mem0, Redis, and OpenAI API credentials into n8n. Use the Baserow Template: I've created a free Baserow template to act as your control panel. Grab it here: https://baserow.io/public/grid/t5kYjovKEHjNix2-6Rijk99y4SDeyQY4rmQISciC14w. It has all the fields you need to command the bot. Requirements An active n8n instance or cloud account. Accounts for VEXA.ai, Mem0.ai, Baserow, and OpenAI. A Redis database . Your Baserow table must have these fields: Meeting Link, Bot Name, Send Bot, and Status. Next Steps: Getting More ROI This workflow is the foundation. The real value comes from what you build on top of it. Automate Follow-ups:** Use the AI-identified next steps to automatically trigger follow-up emails or create tasks in your project management tool. Create a Unified Client Memory:** Connect your email and other communication platforms. Use Mem0 to parse and store every engagement, building a complete, holistic view of every client relationship. Build a Headless CRM:** Combine these workflows to build a fully AI-powered system that handles everything from lead capture to client management without any manual data entry. Copy the workflow and stop taking notes

This workflow deploys a fully customizable AI chatbot that can be embedded on any website, from custom-coded sites to platforms like WordPress. The chatbot is powered by n8n, uses Supabase for memory and RAG, and integrates SerpAPI, Google Calendar, SMTP, and Google Sheets to automate responses, collect leads, and follow up intelligently. Unlike typical widgets, this bot captures name and email before chatting, enabling personalized, human-like conversations and smart lead tracking. Check demo here 🎯 Core Features 💡 Universal Embedding – Works on any site (custom HTML or WordPress) using a single embed snippet. 🧠 AI Agent Node + RAG – Powered by Gemini (or any AI model) with Supabase as memory for contextual replies. 🌐 SerpAPI Integration – Lets the agent search the internet for real-time information. 📅 Google Calendar & Sheets – Logs leads, appointments, and chat summaries. 📧 SMTP Node – Sends personalized follow-up emails directly to new leads. 🪪 Lead Capture – Requires users to enter their name and email before chatting, creating personalized sessions. ⚙️ How It Works Chat Trigger: The widget sends user input to your n8n webhook set to production mode. AI Processing: The AI Agent node handles the response logic with memory and RAG context from Supabase. Integrations: SerpAPI → Real-time search. Google Calendar & Sheets → Stores lead data and events. SMTP Node → Sends automatic thank-you or follow-up emails. Response: The chatbot replies instantly on your website, maintaining session memory. 🧩 Quick Setup Steps Fork or use the Open Source Repo: The widget script is hosted via CDN from your GitHub repo and is fully editable. Embed the Widget: Copy and paste the following snippet into your site’s <head> or footer (or use a plugin like Insert Headers and Footers on WordPress): <link href="https://cdn.jsdelivr.net/npm/@n8n/chat/dist/style.css" rel="stylesheet" /> <script> window.ChatWidgetConfig = { webhook: { url: '', // production webhook URL route: 'general' }, branding: { logo: '', // your logo URL name: 'CustomCX Agent', welcomeText: 'Hi 👋, how can we help?', responseTimeText: 'We typically respond right away', }, style: { primaryColor: '#854fff', secondaryColor: '#6b3fd4', position: 'right', backgroundColor: '#ffffff', fontColor: '#333333', } }; </script> <script src="https://cdn.jsdelivr.net/gh/shadrack-ago/n8n/widget.js?v=2.6"></script> Connect Integrations: Add your Supabase, SerpAPI, Google, and SMTP credentials in n8n. Update your webhook URL in the script above. Deploy: Activate the workflow, refresh your site, and start chatting with your AI assistant. 🚀 Why Use This Template Works with any website or CMS. Captures and stores qualified leads automatically. Open source — easily modify, brand, or extend it. Seamlessly integrates AI, CRM, and communication tools.

Never miss a workflow failure Automatically capture, analyze, and debug n8n workflow errors using Claude Sonnet 4 with real-time documentation lookup via Context7 MCP server. Why this works better Documentation-first AI analysis Context7 searches official n8n docs before diagnosing. Claude Sonnet 4 only responds after finding relevant documentation—no hallucinations. Complete error intelligence Every error stored in Supabase with full context: stack traces, execution data, workflow structure, AI analysis. Track patterns across all workflows. Production-ready emails Professional HTML with inline code snippets, proper formatting, and one-click execution links. What happens Root cause - Plain English explanation Specific fix - Exact field names and values Prevention tip - Avoid future errors Execution link - One-click debug access Statistics - Error frequency tracking How it works Error → Your workflow fails Capture → Full context retrieved Research → Context7 searches n8n Analysis → AI diagnoses with context Email → Formatted alert delivered Record → Error stored in database Requirements Supabase** - Free tier works OpenRouter** - $5 credit Context7** - Free API available SMTP** - For email delivery n8n API** - Must be enabled Setup: 15 minutes Overview Complete instructions with SQL script included in workflow sticky notes. Activate: Settings → Error Workflow → Select this workflow Customize Reduce cost: Remove workflow_json and execution_data from prompt Change output: Swap email node for Telegram/Slack/Discord—expressions provided in notes FAQ Works with community nodes? Yes. Context7 searches all n8n documentation. Handles sensitive data? Remove workflow_json and execution_data from prompt to exclude content. Customizable design? Yes. HTML template in "Build HTML" node is fully editable.

Description: Don't just get a recipe. Get a Strategy. (Speed / Healthy / Creative) 🍳🤖 This workflow solves the "What should I eat?" problem by using Google Gemini to generate 3 distinct recipe variations simultaneously based on your fridge leftovers. It demonstrates advanced n8n concepts like Array Processing and Data Aggregation. Key Features: Array Processing: Demonstrates how to handle JSON lists (Gemini outputs an array -> n8n splits it -> API calls run for each item). Aggregation: Shows how to combine processed items back into a single summary email. Visual Enrichment: Automatically searches for recipe images using Google Custom Search. How it works: Input: Enter ingredients via the Form Trigger. Generate: Gemini creates 3 JSON objects: "Speed (5min)", "Healthy", and "Creative". Process: The workflow iterates through the 3 recipes, searching for images and logging data to Google Sheets. Aggregate: The results are combined into one HTML comparison table. Deliver: You receive an email with 3 options to choose from. Setup Requirements: Google Sheets: Create a sheet named Recipes with headers: date, ingredients, style, recipe_name, recipe_text, image_url. Credentials: Google Gemini API, Google Custom Search (API Key & Engine ID), Gmail, Google Sheets. Configuration: Enter your IDs in the "1. Configuration" node.

How It Works This workflow automates end-to-end supply chain visibility and logistics coordination for manufacturers, distributors, and retailers managing complex multi-tier supply networks. Designed for supply chain planners, logistics managers, and operations directors, it solves the challenge of tracking inventory across procurement, warehousing, and transportation while optimizing decisions for cost, speed, and risk mitigation. The system schedules regular data collection from procurement and warehouse/transportation systems, consolidates supply chain data, analyzes patterns through dual AI agents (Signal Monitoring identifies anomalies and trends, Coordination Agent orchestrates optimization decisions), routes findings by risk level (critical/marginal/acceptable), triggers action-specific responses (critical issues send Slack alerts, escalation emails, and compliance audit logs with approval workflows; acceptable conditions generate standard reports), and maintains complete traceability. Organizations achieve 50% reduction in stockouts, optimize logistics costs by 30%, enable proactive disruption management, and maintain real-time visibility across global supply networks. Setup Steps Connect Schedule Trigger for monitoring frequency Configure procurement system APIs with order and supplier data access credentials Link warehouse management systems (WMS) and transportation platforms (TMS) for inventory and shipment tracking Add AI model API keys to Signal Monitoring and Coordination Agent nodes Define optimization parameters in agent prompts Configure Slack webhooks for critical supply chain alerts to operations teams Set up email credentials for escalation workflows Prerequisites Supply chain system API access (ERP, WMS, TMS), AI service accounts. Use Cases Inventory optimization across multi-tier networks, predictive stockout prevention Customization Modify agent prompts for industry-specific constraints (perishable goods, hazmat regulations) Benefits Reduces stockouts by 50% and optimizes logistics costs by 30%

How It Works A scheduled process aggregates content from eight distinct data sources and standardizes all inputs into a unified format. AI models perform sentiment scoring, detect conspiracy or misinformation signals, and generate trend analyses across domains. An MCDN routing model prioritizes and channels insights to the appropriate workflows. Dashboards visualize real-time analytics, trigger KPIs based on thresholds, and compile comprehensive market-intelligence reports for stakeholders. Setup Steps Data Sources: Connect news APIs, social media platforms, academic databases, code repositories, and documentation feeds. AI Analysis: Configure OpenAI models for sentiment analysis, conspiracy detection, and trend scoring. Dashboards: Integrate analytics platforms and enable automated email or reporting outputs. Storage: Configure a database for historical records, trend archives, and competitive-intelligence storage. Prerequisites Multi-source API credentials; OpenAI API key; dashboard platform access; email service; code repository access; academic database credentials Use Cases Competitive intelligence monitoring; market trend analysis; technology landscape tracking; product strategy research; misinformation filtering Customization Adjust sentiment thresholds; add/remove data sources; modify analysis rules; extend AI models Benefits Reduces research time 80%; consolidates market intelligence; improves decision accuracy

This AI Blog Generator is an advanced n8n-powered automation workflow that leverages Google Gemini and Google Sheets to generate SEO-friendly blog articles for Shopify products. It automates the entire process — from fetching product data to creating structured HTML content — with zero manual effort. 💡 Key Advantages Our AI Blog Generator offers five core advantages that make it the perfect solution for automated content creation: 🔗 Shopify Product Sync** — Automatically pulls product data (titles, descriptions, images, etc.) via Shopify API. ✍️ SEO Blog Generation** — Gemini generates blog titles, meta descriptions, and complete articles using product information. 🗂️ Structured Content Output** — Creates well-formatted HTML with headers and bullet points for seamless Shopify blog integration. 📄 Google Sheets Integration** — Tracks blog creation and prevents duplicate publishing using a centralized Google Sheet. 📤 Shopify Blog API Integration** — Publishes the generated blog to Shopify with a single API call. ⚙️ How It Works The workflow follows a systematic 8-step process that ensures quality and efficiency: Step-by-Step Process Manual Trigger – Start the workflow via a test trigger or scheduler. Fetch Products from Shopify – Retrieves all product details, including images and descriptions. Fix Input Format – Organizes and updates the input table using Code and Google Sheet nodes. Filter Duplicates – Ensures no previously used rows are processed again. Limit Control – Processes one row at a time and loops until all blogs are posted. Gemini AI Generation – Creates SEO-friendly blog content in HTML format from product data. HTML Structure Fix – Adjusts content for JSON compatibility by cleaning unsupported HTML tags. Article API Posting – Sends finalized blog content to Shopify for publishing or drafting. 🛠️ Setup Steps Required Node Configuration To implement this workflow, you'll need to configure the following n8n nodes: Trigger Node:** Start the workflow instantly. Shopify Node:** Fetch product details. Google Sheet Node:** Store input/output data and track blog creation status. Code Node:** Format data as required. Filter Node:** Remove used rows to avoid duplication. Limit Node:** Process one blog at a time. Agent Node:** Sends prompt to Gemini and returns parsed SEO-ready content. HTTP Node:** Posts content to Shopify via the API. 🔐 Credentials Required Authentication Setup Before running the workflow, ensure you have the following credentials configured: Shopify Access Token** – For fetching products and posting blogs Gemini API Key** – For AI-powered blog generation Google Sheets OAuth** – For logging and tracking workflow data 👤 Ideal For Target Users This automation workflow is specifically designed for: Ecommerce teams** automating blogs for hundreds of products Shopify store owners** boosting organic traffic effortlessly Marketing teams** building scalable, AI-driven content workflows 💬 Bonus Tip Extensibility Features The workflow is fully modular and highly customizable. You can easily extend it for: Internal linking** between related products Multi-language translation** for global markets Social media sharing** automation Email marketing** integration All extensions can be implemented within the same n8n flow, making it a comprehensive content automation solution.

What Problem Does It Solve? Customers often ask product questions or prices in comments. Businesses waste time replying manually, leading to delays. Some comments only need a short thank-you reply, while others need a detailed private response. This workflow solves these by: Replying with a friendly public comment. Sending a private message with details when needed. Handling compliments, complaints, and unclear comments in a consistent way. How to Configure It Facebook Setup Connect your Facebook Page credentials in n8n. Add the webhook URL from this workflow to your Facebook App/Webhook settings. AI Setup Add your Google Gemini API key (or swap for OpenAI/Claude). The included prompt is generic — you can edit it to match your brand tone. Optional Logging If you want to track processed messages, connect a Notion database or another CRM. How It Works Webhook catches new Facebook comments. AI Agent analyzes the comment and categorizes it (question, compliment, complaint, unclear, spam). Replying: For questions/requests → public reply + private message with full details. For compliments → short thank-you reply. For complaints → apology reply + private message for clarification. For unclear comments → ask politely if they need help. For spam/offensive → ignored (no reply). Replies and messages are sent instantly via the Facebook Graph API. Customization Ideas Change the AI prompt to match your brand voice. Add forwarding to Slack/Email if a human should review certain replies. Log conversations in Notion, Google Sheets, or a CRM for reporting. Expand to Instagram or WhatsApp with small adjustments. If you need any help Get In Touch

[Meta] Multi-Format Documentation Generator for N8N Creators (+More) One-Line Description Transform n8n workflow JSON into five ready-to-publish documentation formats including technical guides, social posts, and marketplace submissions. Detailed Description What it does: This workflow takes an exported n8n workflow JSON file and automatically generates a complete documentation package with five distinct formats: technical implementation guide, LinkedIn post, Discord community snippet, detailed use case narrative, and n8n Creator Commons submission documentation. All outputs are compiled into a single Google Doc for easy access and distribution. Who it's for: n8n creators** preparing workflows for the template library or community sharing Automation consultants** documenting client solutions across multiple channels Developer advocates** creating content about automation workflows for different audiences Teams** standardizing workflow documentation for internal knowledge bases Key Features: Parallel AI generation** - Creates all five documentation formats simultaneously using Claude, saving 2+ hours of manual writing Automatic format optimization** - Each output follows platform-specific best practices (LinkedIn character limits, Discord casual tone, n8n marketplace guidelines) Single Google Doc compilation** - All documentation consolidated with clear section separators and automatic workflow name detection JSON upload interface** - Simple form-based trigger accepts workflow exports without technical setup Smart content adaptation** - Same workflow data transformed into technical depth for developers, engaging narratives for social media, and searchable descriptions for marketplaces Ready-to-publish outputs** - No editing required—each format follows platform submission guidelines and style requirements How it works: User uploads exported n8n workflow JSON through a web form interface Five AI agents process the workflow data in parallel, each generating format-specific documentation (technical guide, LinkedIn post, Discord snippet, use case story, marketplace listing) All outputs merge into a formatted document with section headers and separators Google Docs creates a new document with auto-generated title from workflow name and timestamp Final document populates with all five documentation formats, ready for copying to respective platforms Setup Requirements Prerequisites: Anthropic API** (Claude AI) - Powers all documentation generation; requires paid API access or credits Google Docs API** - Creates and updates documentation; free with Google Workspace account n8n instance** - Cloud or self-hosted with AI agent node support (v1.0+) Estimated Setup Time: 20-25 minutes (15 minutes for API credentials, 5-10 minutes for testing with sample workflow) Installation Notes API costs**: Each workflow documentation run uses ~15,000-20,000 tokens across five parallel AI calls (approximately $0.30-0.50 per generation at current Claude pricing) Google Docs folder**: Update the folderId parameter in the "Create a document" node to your target folder—default points to a specific folder that won't exist in your Drive Testing tip**: Use a simple 3-5 node workflow for your first test to verify all AI agents complete successfully before processing complex workflows Wait node purpose**: The 5-second wait between document creation and content update prevents Google Docs API race conditions—don't remove this step Form URL**: After activation, save the form trigger URL for easy access—bookmark it or share with team members who need to generate documentation Customization Options Swappable integrations: Replace Google Docs with Notion, Confluence, or file system storage by swapping final nodes Switch from Claude to GPT-4, Gemini, or other LLMs by changing the language model node (may require prompt adjustments) Add Slack/email notification nodes after completion to alert when documentation is ready Adjustable parameters: Modify AI prompts in each agent node to match your documentation style preferences or add company-specific guidelines Add/remove documentation formats by duplicating or deleting agent nodes and updating merge configuration Change document formatting in the JavaScript code node (section separators, headers, metadata) Extension possibilities: Add automatic posting to LinkedIn/Discord by connecting their APIs after doc generation Create version history tracking by appending to existing docs instead of creating new ones Build approval workflow by adding human-in-the-loop steps before final document creation Generate visual diagrams by adding Mermaid chart generation from workflow structure Create multi-language versions by adding translation nodes after English generation Category Development Tags documentation n8n content-generation ai claude google-docs workflow automation-publishing Use Case Examples Marketplace contributors**: Generate complete n8n template submission packages in minutes instead of hours of manual documentation writing across multiple format requirements Agency documentation**: Automation consultancies can deliver client workflows with professional documentation suite—technical guides for client IT teams, social posts for client marketing, and narrative case studies for portfolio Internal knowledge base**: Development teams standardize workflow documentation across projects, ensuring every automation has consistent technical details, use case examples, and setup instructions for team onboarding

How it works This workflow runs on a daily schedule and automatically sends follow-up reminders to candidates who have received an application link but have not yet applied. It checks Airtable for eligible records, calculates how much time has passed since outreach was sent, and decides whether to send a first reminder, second reminder, or no message. All decision logic is handled in a single Code node, which outputs a simple routing value. This makes the workflow easy to understand and prevents fragile conditional logic. Each reminder is sent only once. After a reminder is sent, the workflow updates Airtable with a corresponding “sent” flag so the same reminder cannot be sent again on future runs. Setup steps Connect your Airtable account and select the table containing candidate records. Ensure Airtable includes a timestamp field indicating when outreach was sent. Ensure checkbox fields exist for each reminder (for example, “Reminder 1 Sent” and “Reminder 2 Sent”). Connect your email provider (Brevo) and SMS provider. Set the Cron node to run once per day at your preferred time. Initial setup typically takes 10–15 minutes. When to use this template You want automated follow-ups without manual chasing You need to avoid sending duplicate reminders You want Airtable to remain the source of truth

Who’s it for This template is built for WooCommerce store owners, eCommerce managers, and automation agencies who want to manage store operations directly from Telegram using an AI assistant. It’s ideal for users looking to save time, automate support, and access store data conversationally. How it works When a user sends a message via Telegram, the workflow triggers an AI agent that understands the request using a chat model with memory. Based on the intent, the agent executes the appropriate action such as retrieving orders, fetching product data, updating product information, logging data into Google Sheets, or sending email notifications. How to set up Connect your Telegram bot credentials Add your WooCommerce API keys Connect Google Sheets for data storage Connect your Gmail account Configure your OpenRouter or OpenAI API key Test the workflow via Telegram commands Requirements WooCommerce store with API access Telegram bot token Google Sheets account Gmail credentials OpenRouter or OpenAI API key How to customize You can expand this agent by adding tools like order creation, refund processing, CRM integrations, shipping updates, or advanced reporting. The AI prompt can also be modified to match your store operations.

📊 Description Automate patient pre-arrival intake, AI risk assessment, and real-time doctor alerts in one seamless healthcare workflow. ⏰📧 This automation sends scheduled intake reminders before appointments, analyzes submitted patient data using AI, and flags high-risk cases instantly via Slack. Powered by Azure OpenAI, it evaluates symptoms, allergies, and medical history to generate structured risk levels and doctor preparation notes. Reduce manual triage work, improve patient safety, and ensure physicians are fully prepared before every visit. 🤖🚨 🔄 What This Template Does ⏰ Runs hourly to fetch upcoming appointments from Google Calendar. 📧 Sends pre-arrival intake emails to patients via Gmail. 📊 Monitors new intake form submissions in Google Sheets. 🤖 Analyzes symptoms and medical history using Azure OpenAI (GPT-4o-mini). 🧹 Parses and normalizes structured AI output for consistency. 📝 Stores risk level and doctor notes back into Google Sheets. 🚨 Sends instant Slack alerts if a patient is classified as High risk. ✅ Key Benefits ✅ Automates pre-visit intake collection with zero manual follow-up ✅ Uses AI-powered risk triage to support clinical decision-making ✅ Flags high-risk or urgent cases instantly ✅ Reduces front-desk workload and manual screening time ✅ Improves patient safety through structured early assessment ✅ Ensures doctors are prepared before appointments begin ⚙️ Features Google Calendar hourly appointment trigger Gmail automated intake reminder emails Google Sheets real-time form monitoring Azure OpenAI GPT-4o-mini risk assessment engine Structured JSON AI output with confidence scoring Automatic data normalization and formatting Conditional risk triage logic (Low / Medium / High / Emergency) Slack instant doctor notifications for critical cases 🔐 Requirements Google Calendar OAuth2 credentials Gmail OAuth2 credentials Google Sheets OAuth2 credentials Azure OpenAI API credentials (GPT-4o-mini deployment) Slack OAuth2 credentials 🎯 Target Audience Private clinics and healthcare providers Telemedicine platforms Medical practices handling high patient volume Healthcare automation consultants and digital health startups