Google Gemini Chat Model and WhatsApp Business Cloud integration

This n8n template demonstrates the beginnings of building your own n8n-powered WhatsApp chatbot! Under the hood, utilise n8n's powerful AI features to handle different message types and use an AI agent to respond to the user. A powerful tool for any use-case! How it works Incoming WhatsApp Trigger provides a way to get messages into the workflow. The message received is extracted and sent through 1 of 4 branches for processing. Each processing branch uses AI to analyse, summarize or transcribe the message so that the AI agent can understand it. The supported types are text, image, audio (voice notes) and video. The AI Agent is used to generate a response generally and uses a wikipedia tool for more complex queries. Finally, the response message is sent back to the WhatsApp user using the WhatsApp node. How to use Once you have setup and configured your WhatsApp account, you'll need to activate your workflow to start processing messages. Good to know: Large media files may negatively impact workflow performance. Requirements WhatsApp Buisness account Google Gemini for LLM. Gemini is used specifically because it can accept audio and video files whereas at time of writing, many other providers like OpenAI's GPT, do not. Customising this workflow For performance reasons, consider detecting large audio and video before sending to the LLM. Pre-processing such files may allow your agent to perform better. Go beyond and create rich and engagement customer experiences by responding using images, audio and video instead of just text!

Overview This project is an AI-powered WhatsApp virtual agent built using n8n, designed to handle both text and voice-based customer messages automatically. The workflow integrates Google Gemini, Pinecone, and the WhatsApp Business API to provide intelligent, context-aware responses that feel natural and professional. How It Works Message Detection The workflow begins when a message arrives on WhatsApp. It identifies whether the message is text or voice and routes it accordingly. Voice Message Handling Audio messages are securely downloaded from WhatsApp. The files are converted to Base64 format and sent to the Gemini API for transcription. The transcribed text is then passed to the AI Agent for further processing. AI Agent Processing The LangChain AI Agent acts as the brain of the system. It uses: Google Gemini Chat Model** for natural language understanding and response generation. Pinecone Vector Store** to retrieve company-specific information and product data. Memory Buffer** to remember the last 20 user messages, ensuring context-aware responses. The agent also follows a set of custom communication rules — replying only in approved languages, skipping greetings, and focusing on direct, helpful, and professional responses (e.g., product recommendations, support, or guidance). Knowledge Retrieval The AI Agent connects to a Pinecone database containing detailed company data, such as product catalogs or service FAQs. Using Gemini-generated embeddings, it retrieves the most relevant information for each user query. Response Delivery Once the AI Agent prepares the response, it is instantly sent back to the user via WhatsApp, completing the conversational loop. Who It’s For This system is ideal for businesses seeking to automate their customer communication through WhatsApp. It’s especially valuable for: Product-based companies** with frequent customer inquiries. Service providers** offering 24/7 customer assistance or quote requests. SMBs** looking to scale their communication without hiring additional staff. Tech Stack & Requirements n8n** – Workflow automation and orchestration. WhatsApp Cloud API** – For sending and receiving messages. Google Gemini (PaLM)** – For LLM-based transcription and response generation. Pinecone** – Vector database for product and service knowledge retrieval. LangChain Integration** – For connecting memory, vector store, and reasoning tools. Custom Business Rules** – Configurable within the AI Agent node to manage tone, style, and workflow behavior. Key Features Handles both text and voice messages seamlessly. Responds in multiple languages, including English. Maintains conversation memory per user session. Retrieves accurate company-specific information using vector search. Fully automated, with customizable behavior for different industries or use cases. Setup Instructions Prerequisites Before importing the workflow, ensure you have: An active n8n instance (self-hosted or n8n Cloud). WhatsApp Cloud API credentials** from Meta. Google Gemini API key** with model access (for chat and transcription). Pinecone API key** with a preconfigured vector index containing your company data. Environment Setup Install all required credentials under Settings → Credentials in n8n. Add environment variables (if applicable) for keys like: GOOGLE_API_KEY=your_google_gemini_key PINECONE_API_KEY=your_pinecone_key WHATSAPP_ACCESS_TOKEN=your_whatsapp_token Pinecone Configuration Create a Pinecone index named, for example, products-index. Upload company documents or product details as vector embeddings using Gemini or LangChain utilities. Adjust the retrieval limit in the Pinecone node settings for broader or narrower search responses. WhatsApp API Configuration Set up a WhatsApp Business Account via Meta Developer Dashboard. Create a webhook endpoint URL (n8n’s public URL) to receive WhatsApp messages. Use the WhatsApp Trigger Node to capture messages in real time. AI Agent Customization You can personalize how the AI behaves by editing the system prompt inside the AI Agent node: Modify tone, response length, or product focus. Add new “rules” for language preferences or conversation flow. Include links or custom text output (e.g., quotation formats, product catalog messages). Handling Voice Messages Ensure your WhatsApp Business Account has media message permissions enabled. Verify the HTTP Request node that connects to the Gemini API for transcription is correctly authenticated. You can adjust the transcription model or prompt if you prefer shorter, keyword-based outputs. Testing Send both text and voice messages from a test WhatsApp number. Check response time and message formatting. Use n8n’s execution logs to debug errors (especially for media downloads or API credentials). Customization Options 🧩 AI Behavior Modify the AI Agent’s system message to adapt tone and personality (e.g., sales-oriented, support-driven). Update memory length (default: last 20 messages) for longer or shorter conversations. 🌍 Multi-language Support Add or remove allowed languages in the rules section of the AI Agent node. For multilingual businesses, duplicate the AI Agent path and route messages by language detection. 📦 Industry Adaptation Swap the Pinecone dataset to suit different industries — retail, hospitality, logistics, etc. Replace product data with FAQs, customer records, or support documentation.

Handle WhatsApp customer inquiries with AI and intent routing (Whatsapp Chatbot) An intelligent, fully customizable WhatsApp customer support chatbot template that works for ANY business - whether you sell fashion, electronics, food, furniture, cosmetics, or anything else. This workflow combines pre-built responses for common queries with AI for complex questions, creating a cost-effective 24/7 customer support solution that adapts to your specific products and services. Who it's for This universal template works for ANY business type: E-commerce stores** (fashion, electronics, home goods, beauty, etc.) Local retail shops** (boutiques, grocery stores, bookshops, etc.) Service businesses** (salons, repair services, consultancies, etc.) Restaurants & cafes** (food delivery, reservations, menu inquiries) Any business** using WhatsApp Business API for customer communication What it does This is a UNIVERSAL template - it works for ANY business by simply updating the product categories, company information, and response templates. No coding knowledge required for basic customization! The workflow automates WhatsApp customer support through intelligent routing and AI assistance: Receives WhatsApp messages via WhatsApp Business API webhook trigger Parses message data extracting user info, chat ID, and message text Classifies intent using pattern matching to determine what the customer wants (product inquiry, contact info, support, greeting, etc.) Routes intelligently to the most appropriate response handler: Product inquiries → Pre-built catalog responses with pricing and links Contact information → Static company details (address, phone, hours) Complex queries → AI agent with full company context Maintains conversation context using memory to remember previous messages Sends formatted responses back to the customer via WhatsApp with markdown formatting The hybrid approach (pre-built responses + AI) balances speed, cost, and intelligence - common questions get instant answers while complex queries receive personalized AI assistance. How to set up Requirements You'll need: WhatsApp Business API** access (via Twilio, 360Dialog, Meta Cloud API, or other providers) Google Gemini API key** (for AI responses) - Get API key Google Docs** (optional - for product catalog reference) n8n instance** with WhatsApp nodes installed Setup Steps Configure WhatsApp Business API Sign up with a WhatsApp Business API provider (Twilio, 360Dialog, or Meta) Get your API credentials (phone number ID, access token, webhook verify token) Add credentials to n8n's WhatsApp node Copy the webhook URL from n8n and configure it in your provider's dashboard Customize Company Information Open the "Build AI System Prompt" node Replace all placeholder text with your actual company details: Company name Address and phone numbers Email and website Product categories and brands Policies (COD, warranty, returns, delivery) Store hours Configure Product Responses Edit the "Generate Product Response" node Replace the sample products with your actual catalog: Product names and specifications Prices (update currency if not using INR) Product URLs from your website Add/remove product categories as needed Update Contact Details Edit the "Generate Contact Info Response" node Add your complete contact information Update store hours and addresses Set Up AI Credentials Add your Google Gemini API key to the credential manager (Optional) Connect Google Docs if you want to use a product catalog document Activate and Test Activate the workflow in n8n Send test messages to your WhatsApp Business number Test different intents: greetings, product questions, contact requests Verify responses are accurate and timely WhatsApp Business API Providers Option 1: Meta Cloud API (Official, free for moderate usage) Sign up at: https://developers.facebook.com/ Requires Facebook Business account Best for: Small to medium businesses Option 2: Twilio (Reliable, paid service) Sign up at: https://www.twilio.com/whatsapp Pay-per-message pricing Best for: Businesses needing high reliability Option 3: 360Dialog (WhatsApp-focused) Sign up at: https://www.360dialog.com/ Competitive pricing Best for: WhatsApp-heavy businesses Option 4: MessageBird, Vonage, others Various pricing and features Research and compare based on your needs How it works Intent Classification System The workflow uses keyword pattern matching to classify user intent into these categories: Priority 1: Contact Information (highest priority) Triggers: "where is store", "address", "contact", "phone number" Response: Static contact details Why first: Users asking for contact info need immediate, accurate answers Priority 2: Greetings Triggers: "hi", "hello", "hey", "good morning" Response: Friendly welcome with menu options Helps: Sets a positive tone for the conversation Priority 3: Product Inquiries Triggers: Category keywords (monitor, processor, GPU, RAM, etc.) Response: Pre-built catalog with products, prices, and links Categories: Customizable based on your products Priority 4: AI Fallback Triggers: Everything else (comparisons, complex questions, multi-step queries) Response: Google Gemini AI with company knowledge Features: Conversation memory, personalized recommendations Response Architecture Pre-Built Responses (Fast & Cost-Effective) Instant answers (no API calls) Handles 70-80% of queries Consistent, accurate information No ongoing costs Used for: Product lists, contact info, FAQs AI Agent (Intelligent & Flexible) Handles complex questions Maintains conversation context Provides personalized recommendations Adapts to different query styles Used for: Comparisons, custom builds, technical questions Conversation Memory The workflow uses buffer window memory to remember recent conversation: Stores last 10 messages per user Enables multi-turn conversations AI can reference previous questions Creates more natural interactions Memory is user-specific (isolated by user ID) Message Flow Example User: "Hi" → Intent: greeting → Response: Welcome message with menu User: "Show me monitors" → Intent: product_inquiry (monitors) → Response: Pre-built list of monitors with prices User: "Which one is best for gaming?" → Intent: general_inquiry (complex) → Response: AI analyzes previous context (monitors) and recommends gaming-focused option User: "What's your address?" → Intent: contact_info → Response: Complete contact details How to customize the workflow STEP 1: Customize Product Categories The workflow comes with example categories for multiple business types. Replace them with YOUR categories: For a Fashion Store: const categories = [ { pattern: /(shirt|tshirt|top)/i, category: 'tops' }, { pattern: /(jeans|pants|trousers)/i, category: 'bottoms' }, { pattern: /(dress|gown|kurti)/i, category: 'dresses' }, { pattern: /(shoe|footwear|heels)/i, category: 'shoes' }, ]; For a Grocery Store: const categories = [ { pattern: /(vegetable|veggies)/i, category: 'vegetables' }, { pattern: /(fruit|fruits)/i, category: 'fruits' }, { pattern: /(dairy|milk|cheese)/i, category: 'dairy' }, { pattern: /(snack|chips|biscuit)/i, category: 'snacks' }, ]; For a Beauty/Cosmetics Store: const categories = [ { pattern: /(skincare|cream|serum)/i, category: 'skincare' }, { pattern: /(makeup|lipstick|foundation)/i, category: 'makeup' }, { pattern: /(perfume|fragrance)/i, category: 'perfumes' }, { pattern: /(hair|shampoo|conditioner)/i, category: 'haircare' }, ]; For a Home Furniture Store: const categories = [ { pattern: /(sofa|couch)/i, category: 'sofas' }, { pattern: /(bed|mattress)/i, category: 'bedroom' }, { pattern: /(table|desk|dining)/i, category: 'tables' }, { pattern: /(chair|seating)/i, category: 'chairs' }, ]; For a Restaurant: const categories = [ { pattern: /(pizza|italian)/i, category: 'italian' }, { pattern: /(burger|sandwich)/i, category: 'fast_food' }, { pattern: /(biryani|curry|indian)/i, category: 'indian' }, { pattern: /(dessert|sweet|ice cream)/i, category: 'desserts' }, ]; STEP 2: Customize Product Responses Update the "Generate Product Response" node with YOUR actual products: Example for Fashion Store: if (category === 'tops') { response = Hi ${userName}! Check out our TOPS collection:\\n\\n; response += 👕 Cotton Casual T-Shirt\\n 💰 ₹499\\n 🎨 5 colors available\\n 🔗 yourstore.com/tshirts\\n\\n; response += 👚 Formal Shirt\\n 💰 ₹899\\n 🎉 Buy 2 Get 20% OFF\\n 🔗 yourstore.com/shirts\\n\\n; } Example for Grocery Store: if (category === 'vegetables') { response = Fresh VEGETABLES available, ${userName}:\\n\\n; response += 🥕 Fresh Carrots (1kg)\\n 💰 ₹40\\n 🌱 Organic\\n\\n; response += 🍅 Tomatoes (1kg)\\n 💰 ₹30\\n ✅ Farm Fresh\\n\\n; } Example for Restaurant: if (category === 'italian') { response = Delicious ITALIAN dishes, ${userName}:\\n\\n; response += 🍕 Margherita Pizza\\n 💰 ₹299\\n 👨‍🍳 Chef's Special\\n\\n; response += 🍝 Creamy Alfredo Pasta\\n 💰 ₹349\\n 🔥 Bestseller\\n\\n; } STEP 3: Update Company Information Edit the "Build AI System Prompt" node: For a Boutique: const systemPrompt = `You are a customer service assistant for Elegant Threads Boutique. COMPANY INFORMATION: Business: Women's Designer Clothing Boutique Products: Ethnic wear, western wear, accessories Price Range: ₹1,500 - ₹15,000 Speciality: Custom tailoring available Store Address: Shop 12, Fashion Street, Mumbai Phone: +91 98XXXXXXXX Delivery: Pan-Mumbai, 2-3 days Returns: 7-day no-questions-asked return policy `; For a Tech Store: const systemPrompt = `You are customer support for TechHub Electronics. COMPANY INFORMATION: Business: Consumer Electronics Retailer Products: Smartphones, laptops, accessories, home appliances Price Range: ₹500 - ₹2,00,000 Speciality: Same-day delivery in Delhi NCR Warranty: Extended warranty on all electronics Store: Connaught Place, New Delhi Phone: +91 11-XXXXXXXX `; For a Bakery: const systemPrompt = `You are the assistant for Sweet Delights Bakery. COMPANY INFORMATION: Business: Fresh Baked Goods & Custom Cakes Products: Cakes, pastries, cookies, bread Price Range: ₹50 - ₹3,000 Speciality: Custom cakes for all occasions (24hrs notice) Store: Baker Street, Bangalore Phone: +91 80-XXXXXXXX Delivery: Free above ₹500 within 5km `; Additional Customization Options Change AI Model Replace Google Gemini with other LLM providers: OpenAI GPT-4**: Best for nuanced understanding Anthropic Claude**: Strong at following instructions Llama** (self-hosted): Cost-effective for high volume Simply swap the "Google Gemini Chat Model" node with your preferred model. Add More Intents Extend the intent classification in the "Classify User Intent" node: // Add order tracking if (/track.order|order.status|where.*order/i.test(text)) { intent = 'order_tracking'; } // Add complaint handling if (/complaint|unhappy|problem|issue|refund/i.test(text)) { intent = 'complaint'; } // Add shipping questions if (/shipping|delivery|courier|when.*arrive/i.test(text)) { intent = 'shipping_inquiry'; } Then add corresponding response nodes in the routing switch. Integrate with CRM Connect to HubSpot: Add HubSpot node after intent classification Log every conversation as a ticket Create contacts automatically Track customer journey Connect to Salesforce: Use Salesforce node to create leads Update opportunity stages based on intent Log interactions in Activity History Connect to Airtable: Store conversations in Airtable database Analyze common questions Build knowledge base from real conversations Add Multi-Language Support Method 1: Google Translate API Detect message language Translate to English for processing Translate response back to user's language Method 2: Multilingual AI Add language preference to AI prompt Train AI on multilingual responses Support major languages natively Rich Media Responses Send images: return [{ chatId: chatId, image: 'https://yoursite.com/product.jpg', caption: 'Check out this product!' }]; Send documents: Product catalogs (PDF) Warranty cards Invoice copies Installation guides Send location pins: Store locations Delivery tracking Service centers Human Handoff Logic Add escalation for complex issues: // Check if AI can't help if (complexityScore > 8 || sentiment === 'angry') { // Notify human agent // Transfer conversation // Set status: 'awaiting_agent' } Integrate with: Intercom for live chat handoff Slack for agent notifications Zendesk for ticket creation Connect to Inventory Real-time stock checking: Query your database for availability Show "In Stock" / "Out of Stock" status Suggest alternatives for unavailable products Notify customers when items are restocked Dynamic pricing: Pull current prices from database Apply promotional discounts automatically Show time-sensitive offers Add Analytics Track metrics: Messages per day/week/month Most common intents AI usage vs. pre-built responses Average response time Customer satisfaction scores Integration options: Google Analytics for website tracking Mixpanel for event tracking Custom dashboard in Grafana Google Sheets for simple logging Business Hours Management Add business hours logic: const now = new Date(); const hour = now.getHours(); const isBusinessHours = (hour >= 10 && hour < 20); // 10 AM - 8 PM if (!isBusinessHours) { return [{ response: "We're currently closed. Our hours are 10 AM - 8 PM. We'll respond when we open!" }]; } A/B Testing Responses Test different response styles: Formal vs. casual tone With/without emojis Short vs. detailed answers Different CTAs Track which versions lead to more sales/conversions. Tips for best results Start Simple Begin with 3-5 main intents Add more as you see common patterns Don't over-complicate the initial setup Monitor and Iterate Review conversations weekly Identify missed intents Refine pattern matching Update product information regularly Balance Pre-Built vs. AI Use pre-built for: FAQs, product lists, contact info (fast, cheap) Use AI for: Comparisons, complex queries, personalization (slower, costs money) Aim for 70-80% pre-built, 20-30% AI Optimize Response Times Pre-built responses are instant AI responses take 2-5 seconds Set user expectations ("Let me check that for you...") Test Different Scenarios Happy path (normal inquiries) Edge cases (misspellings, slang) Multi-turn conversations Multiple topics in one message Keep Responses Concise WhatsApp users prefer short messages Use formatting (bold, bullets) for readability Break long responses into multiple messages Maintain Brand Voice Customize AI system prompt with your brand personality Use consistent tone across all responses Include brand-appropriate emojis Handle Failures Gracefully Add error handling for API failures Have fallback responses ready Always offer human contact option Respect Privacy Don't store sensitive information Comply with GDPR/local privacy laws Allow users to delete their data Monitor Costs Track Gemini API usage Set spending alerts Optimize prompt length to reduce token usage Common use cases across industries Fashion & Apparel Store Answer size and fit questions Share new collection arrivals Check stock availability by size/color Process exchange requests Share styling tips Electronics & Tech Store Provide product specifications Compare different models Check warranty information Share installation guides Handle technical support queries Grocery & Food Store Check product availability Share daily fresh stock updates Take bulk orders Provide recipe suggestions Handle delivery slot bookings Beauty & Cosmetics Recommend products for skin types Share ingredient information Explain usage instructions Handle shade/color queries Process return for wrong products Home Furniture Store Share dimensions and specifications Check delivery timelines Provide assembly instructions Schedule store visits Custom furniture inquiries Restaurant & Cafe Share menu and prices Take table reservations Handle takeaway orders Answer dietary restriction questions Share daily specials Jewelry Store Share designs and prices Book appointments for trials Check customization options Verify metal purity/certifications Handle repair inquiries Bookstore Check book availability Take pre-orders for new releases Recommend books by genre Share reading lists Handle exchange requests Important Notes: This workflow requires WhatsApp Business API (not regular WhatsApp Business app) WhatsApp Business API typically requires business verification Message rates and limits vary by provider Test thoroughly before deploying to customers Always provide a way to reach human support Getting Started Tip: Start with just contact info and product inquiries. Once that works smoothly, add AI responses for complex queries. Gradually expand based on actual customer needs you observe in conversations.

Good to know: This workflow creates a WhatsApp chatbot that answers questions using your own PDFs through RAG (Retrieval-Augmented Generation). Every time you upload a document to Google Drive, it is processed into embeddings and stored in Pinecone—allowing the bot to respond with accurate, context-aware answers directly on WhatsApp. Who is this for? Anyone building a custom WhatsApp chatbot. Businesses wanting a private knowledge based assistant Teams that want their documents to be searchable via chat Creators/coaches who want automated Q&A from their PDFs Developers who want a no-code RAG pipeline using n8n What problem is this workflow solving? What this workflow does: ✅ Monitors a Google Drive folder for new PDFs ✅ Extracts and splits text into chunks ✅ Generates embeddings using OpenAI/Gemini ✅ Stores embeddings in a Pinecone vector index ✅ Receives user questions via WhatsApp ✅ Retrieves the most relevant info using vector search ✅ Generates a natural response using an AI Agent ✅ Sends the answer back to the user on WhatsApp How it works: 1️⃣ Google Drive Trigger detects a new or updated PDF 2️⃣ File is downloaded and its text is split into chunks 3️⃣ Embeddings are generated and stored in Pinecone 4️⃣ WhatsApp Trigger receives a user’s question 5️⃣ The question is embedded and matched with Pinecone 6️⃣ AI Agent uses retrieved context to generate a response 7️⃣ The message is delivered back to the user on WhatsApp How to use: Connect your Google Drive account Add your Pinecone API key and index name Add your OpenAI/Gemini API key Connect your WhatsApp trigger + sender nodes Upload a sample PDF to your Drive folder Send a test WhatsApp message to see the bot reply Requirements: ✅ n8n cloud or self-hosted ✅ Google Drive account ✅ Pinecone vector database ✅ OpenAI or Gemini API key ✅ WhatsApp integration (Cloud API or provider) Customizing this workflow: 🟢 Change the Drive folder or add file-type filters 🟢 Adjust chunk size or embedding model 🟢 Modify the AI prompt for tone, style, or restrictions 🟢 Add memory, logging, or analytics 🟢 Add multiple documents or delete old vector entries 🟢 Swap the AI model (OpenAI ↔ Gemini ↔ Groq, etc.)

WhatsApp Dietitian AI Chatbot Workflow Transform your WhatsApp into a professional nutrition consultant with this comprehensive AI-powered dietitian assistant. Built using n8n automation and Google Gemini AI, this workflow provides instant, intelligent nutrition advice to your clients 24/7. 🍽️ What It Does Meal Analysis: Users can send photos of their meals with captions like "analyze this meal" and receive detailed nutritional breakdowns including calories, macronutrients, and personalized recommendations. Nutrition Guidance: Answers questions about general nutrition, dietary restrictions, meal planning, and healthy eating habits with evidence-based information. Meal Recommendations: Suggests customized meals based on specific criteria like calorie targets, dietary preferences (vegan, keto, etc.), or available ingredients. 🚀 Key Features Dual Input Processing**: Handles both text questions and image analysis seamlessly Professional AI Responses**: Uses Google Gemini 2.0 Flash for accurate, contextual nutrition advice WhatsApp Optimized**: Responses formatted specifically for mobile messaging with emojis and clear structure Smart Routing**: Automatically detects message type (text vs image) and processes accordingly Structured Output**: Consistent, professional formatting for all responses Scope Management**: Stays within nutrition expertise and includes appropriate medical disclaimers 🛠️ Technical Stack Platform**: n8n workflow automation AI Model**: Google Gemini 2.0 Flash Integration**: WhatsApp Business API Message Types**: Text messages, images with captions Output**: Structured, conversational responses 📱 Perfect For Nutritionists and dietitians offering remote consultations Health coaches providing 24/7 client support Fitness professionals adding nutrition guidance Wellness businesses expanding their service offerings Anyone wanting to monetize nutrition expertise 🎯 Ready to Deploy This workflow comes with comprehensive documentation, clear setup instructions, and professional prompt engineering. Simply configure your WhatsApp Business API and Google Gemini credentials to start serving clients immediately. Transform your nutrition expertise into an automated, scalable WhatsApp service that works around the clock!

Automatically classify incoming leads based on the sentiment of their message using Google Gemini, store them in Supabase by category, and send tailored WhatsApp messages via the official WhatsApp Cloud API. ✅ Use Case: This workflow is ideal for sales, onboarding, and customer support teams who want to: Understand the tone and urgency of each lead Prioritize hot leads instantly Send smart, automatic WhatsApp replies based on user sentiment 🧠 How it works: Capture lead via a Typeform webhook Clean and structure the data (name, email, message, etc.) Run sentiment analysis using Google Gemini to classify the message as: Positive → Hot Lead Neutral → Warm Lead Negative → Cold Lead Store lead data in Supabase under the corresponding category Merge data to unify flow paths Send WhatsApp message using the official WhatsApp Cloud API, with a custom reply for each sentiment result 🔧 Tools used: Typeform (incoming data) Google Gemini (AI-based sentiment classification) Supabase (database) WhatsApp Cloud API (response automation) 🏷 Tags: AI, Sentiment Analysis, Lead Qualification, Supabase, WhatsApp, Gemini, Typeform, CRM, Automation, Customer Engagement

Detailed Title "Triathlon Coach AI Workflow: Strava Data Analysis and Personalized Training Insights using n8n" Description This n8n workflow enables you to build an AI-driven virtual triathlon coach that seamlessly integrates with Strava to analyze activity data and provide athletes with actionable training insights. The workflow processes data from activities like swimming, cycling, and running, delivers personalized feedback, and sends motivational and performance improvement advice via email or WhatsApp. Workflow Details Trigger: Strava Activity Updates Node:** Strava Trigger Purpose:** Captures updates from Strava whenever an activity is recorded or modified. The data includes metrics like distance, pace, elevation, heart rate, and more. Integration:** Uses Strava API for real-time synchronization. Step 1: Data Preprocessing Node:** Code Purpose:** Combines and flattens the raw Strava activity data into a structured format for easier processing in subsequent nodes. Logic:** A recursive function flattens JSON input to create a clean and readable structure. Step 2: AI Analysis with Google Gemini Node:** Google Gemini Chat Model Purpose:** Leverages Google Gemini's advanced language model to analyze the activity data. Functionality:** Identifies key performance metrics. Provides feedback and insights specific to the type of activity (e.g., running, swimming, or cycling). Offers tailored recommendations and motivational advice. Step 3: Generate Structured Output Node:** Structure Output Purpose:** Processes the AI-generated response to create a structured format, such as headings, paragraphs, and bullet lists. Output:** Formats the response for clear communication. Step 4: Convert to HTML Node:** Convert to HTML Purpose:** Converts the structured output into an HTML format suitable for email or other presentation methods. Output:** Ensures the response is visually appealing and easy to understand. Step 5: Send Email with Training Insights Node:** Send Email Purpose:** Sends a detailed email to the athlete with performance insights, training recommendations, and motivational messages. Integration:** Utilizes Gmail or SMTP for secure and efficient email delivery. Optional Step: WhatsApp Notifications Node:** WhatsApp Business Cloud Purpose:** Sends a summary of the activity analysis and key recommendations via WhatsApp for instant access. Integration:** Connects to WhatsApp Business Cloud for automated messaging. Additional Notes Customization: You can modify the AI prompt to adapt the recommendations to the athlete's specific goals or fitness levels. The workflow is flexible and can accommodate additional nodes for more advanced analysis or output formats. Scalability: Ideal for individual athletes or coaches managing multiple athletes. Can be expanded to include additional metrics or insights based on user preferences. Performance Metrics Handled: Swimming: SWOLF, stroke count, pace. Cycling: Cadence, power zones, elevation. Running: Pacing, stride length, heart rate zones. Implementation Steps Set Up Strava API Key: Log in to Strava Developers to generate your API key. Integrate the API key into the Strava Trigger node. Configure Google Gemini Integration: Use your Google Gemini (PaLM) API credentials in the Google Gemini Chat Model node. Customize Email and WhatsApp Messaging: Update the Send Email and WhatsApp Business Cloud nodes with the recipient’s details. Automate Execution: Deploy the workflow and use n8n's scheduling features or cron jobs for periodic execution. GET n8n Now N8N COURSE n8n Book Developer Notes Author:** Amjid Ali improvements. Resources:** See in Action: Syncbricks Youtube PayPal: Support the Developer Courses : SyncBricks LMS By using this workflow, triathletes and coaches can elevate training to the next level with AI-powered insights and actionable recommendations.

🤖Multi-Agent AI WhatsApp Bot for Service Businesses Transform your salon/service business with this streamlined WhatsApp automation system featuring Claude integration, zero-setup database management, and intelligent conversation handling. How it works Claude MCP Integration** - Direct connection to Claude Sonnet 4 via Model Context Protocol Streamlined 2-Agent System** - Booking Agent and Admin Agent (simplified from 5 for better reliability) GPT-5 Mini Primary** with Gemini 2.5 Flash backup for cost-effective processing Multi-Media Support** - Handles text, voice (Whisper transcription), images, and PDFs with cost extraction Smart Acknowledgments** - "One moment...", "Let me check availability..." during processing Rate Limiting & Spam Protection** - Configurable limits (default: 100 msg/hour) with professional UX Zero-Setup Database Management Autonomous Airtable Creation** - Bot creates all necessary tables automatically Complete CRUD Operations** - Create, edit, delete services and settings via WhatsApp Dynamic Business Configuration** - Modify hours, pricing, services conversationally Friend Booking Support** - "Book for my friend Sarah" functionality Set up steps WhatsApp Business API** setup (detailed instructions included) Airtable Base ID** extraction (store in Redis or hardcode - recommended) Google Calendar** integration for scheduling Redis** for caching, rate limiting, and conversation memory MCP Server** deployment for Claude integration Whatsapp** for notifications Key Features Booking Limit Control** - Default 6 appointments per customer (configurable in workflow) Service Name Matching** - GPT-5 Nano workflow for cost-optimized service recognition 24-Hour Advance Reminders** - Automatic WhatsApp reminders sent at 8 PM Conversation Memory** maintains context across interactions Error Resilience** with backup models and graceful failure handling Perfect for salons, spas, clinics, consulting services, or any appointment-based business. Complete business setup happens through conversational commands - no manual database configuration required.

Template Guide for Employee Shortlisting AI Agent Automation Overview This template automates the process of shortlisting job applicants using ERPNext, n8n, and AI-powered decision-making tools like Google Gemini and OpenAI. It reduces manual effort, ensures fast evaluations, and provides justifiable decisions about applicants. This is ideal for businesses aiming to streamline their recruitment process while maintaining accuracy and professionalism. YouTube Tutorial:** For a full walkthrough of this template, visit: Integrate AI in ERPNext: Automate Recruitment Job Applicant Shortlisting in Seconds! What Does This Template Do? Webhook Integration with ERPNext: Automatically triggers the workflow when a job application is created in ERPNext. Resume Validation: Ensures resumes are attached and correctly processes various file formats like PDF and DOC. AI-Powered Evaluation: Uses AI to compare resumes against job descriptions and provides a: Fit Level (Strong, Moderate, or Weak) Score (0–100) Justification for the decision. Automated Decision Making: Based on AI-generated scores: Candidates with a score of 80 or higher are Accepted. Candidates below 80 are Rejected. Applications missing required fields or attachments are put On Hold. ERPNext Integration: Updates applicant records in ERPNext, including custom fields such as justification, fit level, and scores. Notifications: Notifies candidates via email, WhatsApp, or SMS about their application status. Step-by-Step Guide Step 1: Set Up ERPNext Webhook Go to Webhooks in ERPNext. Create a webhook for the Job Applicant DocType. Set the trigger to Insert. Pin and test the webhook to ensure proper data flow. Step 2: Import the Template into n8n Open your n8n instance. Import the provided workflow template. Check all nodes for proper configuration. Step 3: Configure Credentials Add your ERPNext API credentials to the ERPNext nodes. Add credentials for AI services like OpenAI or Google Gemini. Configure additional services like WhatsApp or email if you plan to use them for notifications. Step 4: Test Resume Validation Test how the workflow handles different file types (e.g., PDF, DOC, JPG). Ensure resumes without the proper format or attachment are flagged and rejected. Step 5: AI Evaluation The AI model (Google Gemini or OpenAI) will evaluate resumes against job descriptions. Customize the AI prompt to suit your job evaluation needs. The output will include a Fit Level, Score, Rating, and Justification. Step 6: Decision Automation The workflow automatically categorizes applicants: Accepted for scores ≥ 80. Rejected for scores < 80. On Hold if essential fields or attachments are missing. Step 7: Update ERPNext Records The workflow updates the Job Applicant record in ERPNext with: Status (Accepted, Rejected, On Hold) AI-generated Fit Level, Score, Rating, and Justification. Step 8: Notify Candidates Configure notification nodes (email, WhatsApp, or SMS). Inform candidates about their application status and include feedback if required. How It Works Trigger: The workflow starts when a job application is submitted in ERPNext. Validation: Checks if the resume is attached and in the correct format. AI Evaluation: Compares the resume with the job description and generates a decision. ERPNext Update: Updates the applicant's record with the decision and justification. Notification: Sends a personalized notification to the candidate. Dos and Don’ts Dos: Customize Prompts:** Tailor the AI prompt to match your specific job evaluation requirements. Test the Workflow:** Run sample data to ensure the process works as intended. Secure Your Credentials:** Keep your API credentials safe and do not share them publicly. Optimize for Different Formats:** Ensure the workflow can handle all types of resumes you expect. Don’ts: Avoid Manual Intervention:** Let the workflow handle most of the tasks to ensure efficiency. Do Not Skip Testing:** Always test the workflow with various scenarios to avoid errors. Do Not Overlook Notifications:** Ensure candidates are notified promptly to maintain professionalism. Customization Options Add logic for more file types (e.g., scanned images using OCR). Enhance the AI prompts to analyze more complex resume data. Integrate additional tools like Slack or Trello for recruitment tracking. Resources GET n8n Now N8N COURSE n8n Book YouTube Tutorial:** For a full walkthrough of this template, visit: SyncBricks YouTube Channel Detailed Guides and Courses:** Learn more about ERPNext and AI-driven automation at: SyncBricks LMS Support If you encounter issues or want to explore more possibilities with AI-driven automation, feel free to reach out: Email:** [email protected] Website:** ERPNext and Other Courses LinkedIn:** Amjid Ali Let me know if you'd like further details or modifications to the guide!

This workflow implements an AI-powered WhatsApp booking assistant for a hair salon. The system allows customers to book, reschedule, or cancel appointments automatically via text or voice messages on WhatsApp. The workflow supports both text and voice messages. An AI agent manages the conversation logic, determines the user's intent, and calls the appropriate tools to perform actions such as checking availability, creating appointments, rescheduling bookings, or canceling events. The system also includes guardrails to filter unsafe or irrelevant inputs and escalation mechanisms to notify the team when a request falls outside supported tasks. Key Advantages ✅ 24/7 Automated Appointment Booking Customers can book, reschedule, or cancel appointments at any time through WhatsApp without requiring manual staff intervention. ✅ Multi-Modal Communication (Text + Voice) The workflow supports both text messages and voice messages. Audio messages are automatically transcribed and processed by the AI assistant. ✅ Intelligent AI Assistant An AI agent manages the conversation, understands user intent, and automatically performs actions such as checking calendar availability or creating appointments. ✅ Real-Time Calendar Integration The assistant connects directly to Google Calendar to: check available time slots create new bookings update existing appointments cancel reservations This ensures real-time accuracy. ✅ Automatic Client Management Customer information such as phone number, name, and service type is stored and updated in Google Sheets, creating a lightweight CRM database. ✅ Conversation Memory The system stores chat history in PostgreSQL, allowing the AI assistant to maintain context during conversations and deliver a more natural experience. ✅ Smart Error Handling and Escalation If the AI cannot handle a request (for example, a question unrelated to appointments), the workflow automatically: notifies the team via email escalates the conversation for human assistance. ✅ Secure and Controlled AI Responses Guardrails are implemented to prevent irrelevant or unsafe responses, ensuring that the assistant follows defined policies and tasks. ✅ Omnichannel Architecture The workflow is designed to work with: WhatsApp messages chatbot interface (chat trigger) This allows the same logic to power multiple communication channels. ✅ Scalable Automation The system is fully automated and can handle multiple simultaneous conversations, reducing operational workload and improving customer service efficiency. How it works Input Handling (WhatsApp & Chat): It listens for incoming messages from either a WhatsApp Trigger or a Chat Trigger. WhatsApp: It processes both text messages and voice notes. If a voice note is received, it automatically downloads the audio, transcribes it using OpenAI (Whisper), and converts it into text for the AI to process. The user's phone number (for WhatsApp) or session ID (for Chat) is stored as a sessionId to maintain conversation context. Guardrails (Security & Policy): Before the message reaches the main AI agent, it passes through a Guardrails node (using Google Gemini). This acts as a safety filter to check for jailbreak attempts or inappropriate content, ensuring the conversation stays within company policies. AI Agent (The Virtual Assistant): The cleaned-up message is sent to the AI Agent ("Virtual Assistant"). The agent is prompted to act as "Emma" and follows strict instructions: Identify User: It first uses the New client tool to check a Google Sheet to see if the user is already registered. Manage Appointments: Based on the user's request (book, reschedule, cancel), it intelligently calls specific tools in the correct order. Date Logic: It is aware of the current date and time to calculate correct future dates (e.g., interpreting "this Thursday"). Tool Execution (Actions): The agent has access to several tools to perform actions: Google Sheets (New client, Add client): To check if a client exists and add new clients to a spreadsheet. Google Calendar (Get events, Create event, Update event, Delete event): To check availability and manage appointments. The Get events tool is configured to look for slots in the next 30 days. Gmail (Send Email): To notify the team if a user asks for something outside the scope (e.g., pricing, product questions). WhatsApp HITL / Chat HITL (Escalation): To hand over the conversation to a human agent for complex requests. Response Delivery: The AI agent's text response is routed back to the user. On WhatsApp: It intelligently handles the response format. If the original message was text, it sends a text reply. If the original message was a voice note, it uses OpenAI's TTS to convert the text reply into an audio message and sends that back. Setup steps To get this workflow running, you need to configure the following credentials and nodes: Configure Credentials: Google Calendar OAuth2: Connect your Google account (used in Calendar nodes). Google Sheets OAuth2: Connect your Google account to access the spreadsheet. Gmail OAuth2: Connect your Google account to send notification emails from [email protected]. WhatsApp API: Connect your WhatsApp Business API credentials (Phone Number ID). OpenAI API (OpenRouter): Provide your API key for audio transcription and text-to-speech. Google Gemini API: Provide your API keys for the main AI model (Google Gemini Chat Model) and the Guardrails model (Google Gemini Chat Model1). Postgres: Configure the connection to your Postgres database for chat memory. Configure Google Sheets: Create a Google Sheet. Update the Document ID in the New client and Add client nodes with your sheet's ID. Ensure the sheet has columns for Phone Number, Client, and Service. Configure Google Calendar: Verify that the calendar ID in the Calendar nodes is correct and accessible. Configure WhatsApp Triggers & Actions: The WhatsApp Trigger node needs to be connected to your WhatsApp Business App. The Send message and Send audio nodes must have the correct Phone Number ID for your WhatsApp Business number. Update Email Recipient: In the Send Email tool (for escalations), change the sendTo email address from [email protected] to the actual email of the team that should receive these notifications. Review AI Prompts: Open the "Virtual Assistant" (AI Agent) node and review the system message. Update the salon name ("Cuts & Styles"), stylist name ("Alex Carter"), and address to match your business. Check the "Guardrails" node to adjust the safety threshold if necessary. 👉 Subscribe to my new YouTube channel. Here I’ll share videos and Shorts with practical tutorials and FREE templates for n8n. Need help customizing? Contact me for consulting and support or add me on Linkedin.

How it works This AI agent manages your Streak CRM via WhatsApp. Send messages to create contacts, add boxes to pipelines, update stages, link contacts to boxes, and retrieve information, add and get tasks all through natural conversation. Setup steps Connect your Streak API credentials (Basic Auth) Configure WhatsApp Business integration Add your Streak pipeline keys to the workflow Test with a simple command like "create contact John Doe" Customization tips Add custom Streak fields to the AI's tool descriptions Modify pipeline stages to match your workflow Adjust AI prompts to recognize your team's terminology Enable additional Streak operations (comments, tasks, files) The agent worked perfectly when you give it access to streak API documentation, to attain even more complex tasks

The original LLM Council concept was introduced by Andrej Karpathy and published as an open-source repository demonstrating multi-model consensus and ranking. This workflow is my adaptation of that original idea, reimplemented and structured as a production-ready n8n template. Original repository - https://github.com/karpathy/llm-council This n8n template implements the LLM Council pattern: a single user question is processed in parallel by multiple large language models, independently evaluated by peer models, and then synthesized into one high-quality, consensus-driven final answer. It is designed for use cases where answer quality, balance, and reduced single-model bias are critical. 📌 Section 1: Trigger & Input ⚡ When Chat Message Received (Chat Trigger) Purpose: Receives a user’s message and initiates the entire workflow. How it works: A user sends a chat message The message is stored as the Original Question The same input is forwarded simultaneously to multiple LLM pipelines Why it matters: Provides a clean, unified entry point for all downstream multi-model logic. 📌 Section 2: Stage 1 — Parallel LLM Responses 🤖 Basic LLM Chains (x4) Models used: Anthropic Claude OpenAI GPT xAI Grok Google Gemini Purpose: Each model independently generates its own response to the same question. Key characteristics: Identical prompt structure for all models Independent reasoning paths No shared context between models Why it matters: Produces diverse perspectives, reasoning styles, and solution approaches. 📌 Section 3: Stage 2 — Response Anonymization 🧾 Set Nodes (Response A / B / C / D) Purpose: Stores model outputs in an anonymized format: Response A Response B Response C Response D Why it matters: Prevents evaluator models from knowing which LLM authored which response, reducing bias during evaluation. 📌 Section 4: Stage 3 — Peer Evaluation & Ranking 📊 Evaluation Chains (Claude / GPT / Grok / Gemini) Purpose: Each model acts as a reviewer and: Analyzes all four anonymized responses Describes strengths and weaknesses of each Produces a strict FINAL RANKING from best to worst Ranking format (strict): FINAL RANKING: Response B Response A Response D Response C Why it matters: Creates multiple independent quality assessments from different model perspectives. 📌 Section 5: Stage 4 — Ranking Aggregation 🧮 Code Node (JavaScript) Purpose: Aggregates all peer rankings by: Parsing ranking positions Calculating average position per response Counting evaluation occurrences Sorting responses by best average score Output includes: Aggregated rankings Best response label Best average score Why it matters: Transforms subjective rankings into a structured, quantitative consensus. 📌 Section 6: Stage 5 — Final Consensus Answer 🧠 Chairman LLM Chain Purpose: One model acts as the Council Chairman and: Reviews all original responses Considers peer rankings and aggregated scores Identifies consensus patterns and disagreements Produces a single, clear, high-quality final answer Why it matters: Delivers a refined response that reflects collective model intelligence rather than a simple average. 📊 Workflow Overview Stage Node / Logic Purpose 1 Chat Trigger Receive user question 2 LLM Chains Generate independent responses 3 Set Nodes Anonymize outputs 4 Evaluation Chains Peer review & ranking 5 Code Node Aggregate rankings 6 Chairman LLM Final synthesized answer 🎯 Key Benefits 🧠 Multi-model intelligence — avoids reliance on a single LLM ⚖️ Reduced bias — anonymized peer evaluation 📊 Quality-driven selection — ranking-based consensus 🔁 Modular architecture — easy to add or replace models 🌍 Language-flexible — input and output languages configurable 🧩 Production-ready logic — clear stages, deterministic ranking 🚀 Ideal Use Cases High-stakes decision support Complex technical or architectural questions Strategy and research synthesis AI assistants requiring higher trust and reliability Comparing and selecting the best LLM-generated answers

This automated n8n workflow transforms raw CSV data into qualified, enriched lead databases with verified emails and AI-generated personalization. It processes uploaded CSV files through multiple validation, enrichment, and sorting stages before delivering organized results via Google Drive, WhatsApp, or Google Sheets. How It Works Stage 1: Data Intake & Normalization Form Submission: User uploads a CSV/XLSX file and selects: Delivery method (Google Drive, WhatsApp, or Google Sheets with processing) Two personalization prompts for AI-generated messages Column Mapping: The workflow automatically recognizes and standardizes 100+ column name variations into consistent fields Deduplication: Removes duplicate entries by website URL and contact name Initial Filtering: Identifies and flags invalid websites (social media profiles, link shorteners) Stage 2: Data Quality Routing The workflow analyzes each record and routes it based on available data: Route A: Invalid Website → Sends directly to "x Website" sheet Route B: No Website → Verifies existing email and categorizes by validity Route C: Valid Website + Email → Proceeds to email verification and enrichment Route D: Valid Website - Email → Scrapes website to find email addresses. Stage 3: Email Discovery & Verification For records needing enrichment: Website Scraping: Fetches HTML content from company websites Email Extraction: Uses regex patterns to identify email addresses AI Selection: GPT-5-NANO chooses the most relevant email from multiple options Dual Verification: Primary check via Reoon API (deliverability, SMTP, safety) Backup verification if primary fails Personal Email Processing: Separately validates personal emails when present Stage 4: Website Intelligence Gathering Parallel to email processing: Extracts HTML title tags for company context Captures meta descriptions for business understanding Pulls H1 headings for content insight Handles scraping failures gracefully with empty placeholders Stage 5: Email Categorization Logic Records are sorted into buckets: +1 Email**: Has exactly one verified email (business OR personal OR newly found) +2 Email**: Has two or more verified emails Single Source Records**: Only business email OR only personal email Stage 6: AI Personalization For records with verified emails: Context Assembly: Combines name, company, job title, website metadata, industry, keywords AI Processing: Sends to GPT-5-NANO or Gemini with user's custom prompts Structured Output: Generates: Cleaned contact name Shortened company name Personalization message 1 (per user prompt) Personalization message 2 (per user prompt) Stage 7: Final Delivery Based on user's initial selection: Google Drive**: Uploads timestamped CSV, sends email with link WhatsApp**: Converts to XLSX and sends document Google Sheets**: Populates separate sheets by category with completion email How To Use Active n8n instance with required credentials: Google Drive API access Google Sheets API access Gmail API access (for notifications) WhatsApp Business API credentials Reoon Email Verifier API keys OpenAI API key (GPT-5-NANO) Optional: Google Gemini API key Setup Steps Configure Google Sheets Destinations Create or use existing Google Sheets for data categorization: +1 Email Sheet**: Update document ID in "+1 Email" node +2 Email Sheet**: Update document ID in "+2 Email" node x Website Sheet**: Update document ID in "x Website Data" node No Website Sheet**: Update document ID in "- Website +- Email +- Phone Number" node Ensure all sheets have matching column headers as defined in the workflow. Set Up Google Drive Folder Create a destination folder in Google Drive Update the folder ID in the "Upload file" node Ensure the service account has write permissions Configure WhatsApp Add your WhatsApp Business Phone Number ID in the "Send CSV" node Update the recipient phone number (format: +country code) Customize Email Notifications Update sender and recipient emails in "Send a message" and "Send a Success Message" nodes Modify email templates as needed Verify API Keys Check that all API credentials are active: Reoon Email Verifier keys (two instances for redundancy) OpenAI API key for GPT-5-NANO All Google API credentials

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

🚀 How It Works Turn your WhatsApp chats into an AI-powered meeting scheduler with Google Gemini, Google Calendar, and Google Sheets. This workflow understands natural language like “Book a meeting with Ali at 3 PM tomorrow”, checks your contacts, avoids overlaps, and updates your calendar automatically all from WhatsApp. It’s a complete AI scheduling system built for founders, teams, and service providers who manage clients over chat. 🔁 Workflow Overview WhatsApp Trigger** → Captures incoming messages in real time Intent Agent (Gemini)** → Detects scheduling intent (create / edit / cancel) Google Sheets** → Finds contact names, emails, and tags Get Events** → Checks existing meetings to prevent conflicts Correction Agent + Intent Check** → Confirms details with AI Calendar Agent (Gemini)** → Executes the calendar action intelligently Create / Update / Delete Event** → Syncs instantly to Google Calendar Response Node** → Sends WhatsApp and email confirmations ⚙️ Quick Setup (⏱ ~15 min) Connect WhatsApp Cloud API – link your WhatsApp Business account Authenticate Google Calendar & Sheets – use Sheets for contacts (Name | Email | Type) Add Google Gemini API Key – used by Intent, Correction, and Calendar agents Customize Prompts – adjust tone and language in the Gemini nodes Test Your Flow – e.g., message “Schedule meeting with Ali at 10 AM Friday” to verify calendar and confirmation replies 💡 All setup details are also documented inside the workflow sticky notes. 🧩 Integrations WhatsApp Cloud API Google Calendar API Google Sheets API Google Gemini (LLM) 💡 Benefits ✅ Automates scheduling directly from WhatsApp ✅ Understands natural language requests ✅ Prevents double-bookings automatically ✅ Sends instant confirmations ✅ Saves hours of manual coordination 👥 Ideal For Entrepreneurs & consultants managing clients on WhatsApp Sales or support teams booking demos and meetings Virtual assistants and AI service providers Anyone who wants a 24/7 AI calendar manager

⚠️ Disclaimer: This workflow uses WhatsApp, Google Calendar, and Gmail nodes that must be configured manually. Who’s it for This workflow is built for professionals, teams, and automation enthusiasts who want to manage their Google Calendar and Gmail directly from WhatsApp, powered by an AI assistant using OpenAI GPT or Google Gemini. It enables users to chat naturally through WhatsApp to schedule meetings, send emails, and check events — all without opening Gmail or Google Calendar. How it works The WhatsApp Trigger node captures incoming messages from users. The AI Agent (powered by Gemini or GPT) interprets user queries and determines the best tool to use. The Simple Memory node keeps context between messages using the user’s phone number. The Google Calendar nodes handle: Listing, creating, and updating events. Checking your availability before scheduling. The Gmail nodes handle: Sending emails. Reading and summarizing recent messages. The Date & Time node converts natural language like “next Monday at 3 PM” into proper ISO time format. The assistant responds via Send WhatsApp Response, sending clear confirmations and replies. Features Manage Gmail and Calendar entirely via WhatsApp. AI-powered understanding of natural language commands. Integrated with Google Meet for automatic conferencing links. Short-term memory for context retention. Fully modular – swap Gemini with OpenAI GPT or any LLM. Setup Steps Configure WhatsApp Cloud API via Meta for Developers. Set up Google Calendar and Gmail OAuth2 credentials. Add your Google API keys and calendar email. Connect your OpenAI or Gemini model credentials. Activate and test the workflow with messages like: “Schedule a meeting tomorrow at 5 PM.” “Check my latest emails.” “Send an email to [email protected] about our project.” Requirements n8n instance (self-hosted or cloud) WhatsApp Business API (Meta Developer Account) Google Workspace or Gmail account OpenAI API key or Google Gemini API key Properly configured webhooks for WhatsApp Trigger Example Prompts “What’s on my calendar this week?” “Email John to confirm our meeting.” “When am I free tomorrow afternoon?” Customization Replace Gemini with OpenAI GPT in the AI Agent node. Adjust memory length for longer or shorter conversations. Add Slack or Teams notification nodes. Modify the prompt personality or response tone. Credits Created by Praneel For detailed setup help, visit praneel.tech/contact

Deploy a Multi-Tool AI Assistant on WhatsApp with Google Gemini Deploy a true AI assistant on WhatsApp. This n8n workflow uses a sophisticated hierarchical agent structure to not only handle conversations but also manage your emails and calendar directly from your chat, all powered by Google Gemini. Key Features Powered by Google Gemini:** Utilizes the advanced capabilities of Google's Gemini models for understanding complex commands and generating natural, human-like responses. Intelligent Task Delegation (Hierarchical Agents):* Features a central Personal Agent* that understands the user's intent and intelligently delegates tasks to specialized sub-agents for email, calendar, or general chat. Full Email & Calendar Management:** Connects directly to your Google Workspace to send emails, create drafts, apply labels, create/update/delete calendar events, check your availability, and more. Context-Aware Conversations:** Employs memory at multiple levels, allowing the assistant to remember the context of your requests for a coherent and intuitive user experience. Seamless WhatsApp Integration:** Connects directly with the WhatsApp Business API to send and receive messages, engaging users on one of the world's most popular messaging platforms. Easy to Deploy & Customize:** Get your assistant running with minimal configuration and easily extend its capabilities by adding new tools or modifying the prompts of the existing agents. How It Works The workflow uses an advanced agent-based model to process incoming messages: The Whatsapp Trigger node listens for and receives new messages sent to your WhatsApp Business number. The message is passed to the main Manager Agent. The Personal Agent analyzes the message to understand the user's intent (e.g., "send an email," "check my schedule," or just "hello"). Based on the intent, it routes the task to the appropriate sub-agent: the Email Tool, the Calendar Tool, or the general Chatbot Model. The selected sub-agent executes the task using its own dedicated tools (e.g., the Email Tool uses Gmail nodes to send a message). The result or response from the sub-agent is passed back to the Send message (WhatsApp) node, which delivers the reply to the user. Prerequisites An active n8n instance. A Meta Business Account and a configured Meta App with the "WhatsApp Business" product added. A Google Gemini API Key. A Google Account with pre-configured OAuth2 credentials in n8n for Gmail and Google Calendar. Step-by-Step Setup Guide Configure WhatsApp Credentials: In your n8n instance, add new "WhatsApp Business" credentials. You will need a Permanent Access Token and a Phone Number ID from your Meta App's "WhatsApp > API Setup" dashboard. Set Up the WhatsApp Trigger: Open the Whatsapp Trigger node. In the "Webhook URL" section, copy the Test URL. Go to your Meta App's dashboard under "WhatsApp > Configuration". Click "Edit" in the Webhooks section. Paste the n8n Test URL into the Callback URL field. Create and enter a Verify token (a simple password of your choice). Enter this same token in the Whatsapp Trigger node in n8n. Subscribe to the messages webhook event. Once verified, copy the Production URL from n8n and paste it into the same Callback URL field in the Meta dashboard. Configure the Google Gemini Nodes: You must add your Google Gemini API Key to the credentials for all the Google Gemini Chat Model nodes. This includes the one in the Chatbot Model, Email Tool, and Calendar Tool. Configure the Google Tools (Email & Calendar): Email Tool:* Open the group of nodes labeled Email Tool*. For every Gmail node (Send Email, Create Draft, Get Labels, etc.), select your pre-configured Google OAuth2 credential. Calendar Tool:* Open the group of nodes labeled Calendar Tool*. For every Google Calendar node (Create Event, Get all event, etc.), select your pre-configured Google OAuth2 credential. Activate and Test: Save and activate the workflow. Send a message to your configured WhatsApp Business number.

WhatsApp AI Assistant for Clinic Appointment Booking Automate your entire appointment lifecycle with an intelligent AI assistant that lives on WhatsApp. This workflow empowers any clinic or independent practitioner to manage bookings, take payments, and send reminders without manual intervention, using Google Sheets as a simple database. This template handles everything from the initial booking conversation to sending the final reminder, allowing you to focus on your patients, not your schedule. Features 🤖 Conversational AI Booking: A Google Gemini-powered agent guides patients through booking, rescheduling, and canceling appointments in a natural, friendly chat. 🗓️ Smart Scheduling: The AI checks for available slots based on your working hours and existing appointments in Google Sheets, preventing double-bookings. 🔔 Automated Reminders: A daily trigger automatically sends WhatsApp reminders to patients for their appointments on that day, reducing no-shows. 💳 Seamless Payments: Integrated with Stripe to handle online payments. The workflow sends a confirmation message upon successful payment. 📊 Centralized Management: Uses a single Google Sheet with separate tabs for Patients, Appointments, and Configuration, making it easy to view and manage all your data. 🔄 Easy Rescheduling & Cancellations: Patients can manage their own bookings through the WhatsApp chat, and all changes are instantly reflected in your Google Sheet. Prerequisites Before you begin, you will need the following accounts and credentials: n8n Account: A running n8n instance (cloud or self-hosted). WhatsApp Business Account: Access to the WhatsApp Cloud API. Google Account: For using Google Sheets and the Google Gemini (AI) API. Stripe Account: To process online payments. n8n Credentials: You must configure credentials in your n8n instance for: WhatsApp Cloud API Google Sheets (OAuth2) Google Gemini API Stripe Setup Instructions Follow these steps carefully to get your automated assistant up and running. Step 1: Set Up Your Google Sheet This workflow relies on a specific Google Sheet structure. Create a new Google Sheet. Rename the sheet to something memorable, like "Clinic Appointments". Create three tabs at the bottom with the exact names: Patients, Appointments, and Config. Set up the columns for each tab as follows (the header names must be an exact match): Patients tab: patient_id, whatsapp_number, name, age, gender Appointments tab: appointment_id, patient_id, whatsapp_number, date, time, payment_method, payment_status, status, stripe_payment_intent Config tab: key, value (Add a row with working_hours as the key and a value like 10:00-18:00) Step 2: Configure the Workflow Nodes Now, you'll link the workflow to your accounts and your new Google Sheet. Update All Google Sheets Nodes: Go through every Google Sheets node in the workflow (e.g., "Get Appointment sheet", "Add Patient", "Google Sheets Trigger") and do the following: Select your Google Sheets credential from the dropdown. In the Document ID field, paste the ID of your Google Sheet. Select the correct sheet (Appointments, Patients, etc.) from the Sheet Name dropdown. Update All WhatsApp Nodes: Go through every WhatsApp node (e.g., "Send message", "WhatsApp Trigger", "Send Payment Confirmation"): Select your WhatsApp credential. Enter your Phone Number ID from your Meta for Developers account. Update AI & Stripe Nodes: In the Google Gemini Chat Model nodes, select your Google Gemini credential. In the Stripe Trigger node, select your Stripe credential. Step 3: Activate the Workflow Click Save to apply your changes. Click the Activate toggle in the top-right corner to turn the workflow on. Your AI appointment assistant is now live! Send a message to your WhatsApp number to begin testing. Customization Change Reminder Time: To change the daily reminder time, open the Schedule Trigger node and adjust the hour from the default of 8 AM. Edit AI Personality: To modify how the AI communicates, edit the system message in the AI Agent node (the one connected to the WhatsApp Trigger). You can change its tone, instructions, or language.

Product Ingredient Safety Analyzer with AI via WhatsApp What does this workflow do? This workflow creates an intelligent WhatsApp bot that analyzes product ingredients and provides instant safety assessments. Users can send either text queries (product names/brands) or images of product labels, and receive AI-powered analysis covering food, cosmetics, personal care, pharmaceuticals, and household products. Who's it for? Health-conscious consumers** wanting to make informed purchasing decisions Parents** checking product safety for their children People with allergies or sensitivities** screening for harmful ingredients Beauty and skincare enthusiasts** verifying cosmetic product safety Wellness coaches or nutritionists** helping clients evaluate products Small business owners** offering product safety consultation services Eco-conscious consumers** checking for environmental toxins Anyone** looking to understand what's in their everyday products What do you need to get started? Required Accounts & APIs: WhatsApp Business API** - For receiving and sending messages Google Cloud Account** - For Document AI (OCR) service Google Gemini API** - For AI-powered ingredient analysis Setup Steps: Configure WhatsApp Business API credentials Enable Google Document AI in your Google Cloud project Create a Document AI processor for OCR Set up Google Gemini API access Configure all credentials in N8N How does this workflow work? User Input Options: Text Messages**: Send product name/brand (e.g., "Dove soap", "Coca Cola") Images**: Upload photos of product ingredient labels Conversational**: Ask questions or request help Processing Flow: For Image Messages: WhatsApp receives image message Extracts and downloads the image Converts image to Base64 format Uses Google Document AI OCR to extract text AI analyzes extracted text + user caption Returns safety assessment via WhatsApp For Text Messages: WhatsApp receives text query AI directly analyzes product name/ingredients Returns safety assessment via WhatsApp AI Analysis Includes: Product type identification (food, cosmetic, pharmaceutical, etc.) Harmful ingredient detection (parabens, sulfates, trans fats, etc.) Beneficial ingredient highlights Clear safety verdict: ✅ SAFE / ⚠️ CAUTION / ❌ AVOID Practical recommendations and alternatives Response Format: The AI provides concise, WhatsApp-friendly messages with: Product category and type Key ingredients found Safety concerns with specific flags Clear recommendation Actionable advice Use Cases Health-conscious consumers** checking food product ingredients Beauty enthusiasts** verifying cosmetic safety Parents** ensuring child product safety People with allergies** screening for harmful ingredients Eco-conscious users** checking for environmental toxins General wellness** making informed purchase decisions Key Features Dual input support**: Text and image processing OCR technology**: Extracts text from product labels Multi-category analysis**: Food, cosmetics, pharmaceuticals, household items Conversational AI**: Handles greetings, help requests, unclear queries Mobile-optimized**: WhatsApp-friendly formatting Instant results**: Real-time safety assessments Educational**: Explains why ingredients are safe or harmful Technical Highlights Smart routing**: Automatically detects message type (text vs image) Structured output**: JSON-formatted AI responses for reliability Product-specific criteria**: Different analysis standards per category Error handling**: Requests clearer images if OCR fails Conversational fallback**: Guides users when information is insufficient Example Interactions User sends image of shampoo bottle: Response: "Hair Care Product Analysis - Contains sulfates and parabens. ⚠️ USE WITH CAUTION. Consider sulfate-free alternatives for healthier hair." User texts "Maggi noodles": Response: "Food Product Analysis - High sodium content, contains MSG and artificial colors. ❌ AVOID REGULAR CONSUMPTION. Occasional treat okay." User texts "Hi": Response: "Hi! I'm your Product Safety Analyzer. Send me a product name or photo of ingredients to check safety!" Benefits Empowers informed decisions**: Know what you're consuming/using Saves research time**: Instant analysis vs manual ingredient lookup Accessible**: Works via familiar WhatsApp interface Comprehensive**: Covers multiple product categories Educational**: Learn about ingredient safety over time Convenient**: Analyze products while shopping Notes OCR works best with clear, well-lit images AI provides general safety information, not medical advice Analysis based on commonly known ingredient safety standards Users should consult professionals for specific health concerns Supports conversational queries for better user experience

Workflow Execution Link: Watch Execution Video Workflow Pre-requisites Step 1: Supabase Setup First, replace the keys in the "Save the embedding in DB" & "Search Embeddings" nodes with your new Supabase keys. After that, run the following code snippets in your Supabase SQL editor: Create the table to store chunks and embeddings: CREATE TABLE public."RAG" ( id bigserial PRIMARY KEY, chunk text NULL, embeddings vector(1024) NULL ) TABLESPACE pg_default; Create a function to match embeddings: DROP FUNCTION IF EXISTS public.matchembeddings1(integer, vector); CREATE OR REPLACE FUNCTION public.matchembeddings1( match_count integer, query_embedding vector ) RETURNS TABLE ( chunk text, similarity float ) LANGUAGE plpgsql AS $$ BEGIN RETURN QUERY SELECT R.chunk, 1 - (R.embeddings <=> query_embedding) AS similarity FROM public."RAG" AS R ORDER BY R.embeddings <=> query_embedding LIMIT match_count; END; $$; Step 2: Create Knowledge Base Create a new Google Doc with the complete knowledge base about your business and replace the document ID in the "Content for the Training" node. Step 3: Get Together AI API Key Get a Together AI API key and paste it into the "Embedding Uploaded document" node and the "Embed User Message" node. Step 4: Setup Meta App for WhatsApp Business Cloud Go to https://business.facebook.com/latest/settings/apps, create an app, and select the use case "Connect with customer through WhatsApp". Copy the Client ID and Client Secret and add them to the first node. Go to that newly created META app in the app dashboard, click on the use case, and then click on "customise...". Go to the API setup, add your number, and also generate an access token on that page. Now paste the access token and the WhatsApp Business Account ID into the send message node. Part A: Document Preparation (One-Time Setup) When clicking ‘Execute workflow’ Type:** manualTrigger Purpose:** Manually starts the workflow for preparing training content. Content for the Training Type:** googleDocs Purpose:** Fetches the document content that will be used for training. Splitting into Chunks Type:** code Purpose:** Breaks the document text into smaller pieces for processing. Embedding Uploaded document Type:** httpRequest Purpose:** Converts each chunk into embeddings via an external API. Save the embedding in DB Type:** supabase Purpose:** Stores both the chunks and embeddings in the database for future use. Part B: Chat Interaction (Realtime Flow) WhatsApp Trigger Type:** whatsAppTrigger Purpose:** Starts the workflow whenever a user sends a WhatsApp message. If Type:** if Purpose:** Checks whether the incoming WhatsApp message contains text. Embend User Message Type:** httpRequest Purpose:** Converts the user’s message into an embedding. Search Embeddings Type:** httpRequest Purpose:** Finds the top matching document chunks from the database using embeddings. Aggregate Type:** aggregate Purpose:** Merges retrieved chunks into one context block. AI Agent Type:** langchain agent Purpose:** Builds the prompt combining user’s message and context. Google Gemini Chat Model Type:** lmChatGoogleGemini Purpose:** Generates the AI response based on the prepared prompt. Send message Type:** whatsApp Purpose:** Sends the AI’s reply back to the user on WhatsApp.

WhatsApp customer service bot (with voice note transcription) handling FAQ, service enquiries and schedule appointments Who’s it for This template is designed for businesses that provide customer support and appointment-based services over WhatsApp. It’s ideal for service providers (e.g., clinics, salons, repair shops, consultants) that want to automate FAQs, share service information, handle voice note inquiries, and schedule appointments without manual effort. How it works / What it does This workflow creates a WhatsApp customer service assistant that: Transcribes voice notes** sent by customers into text for further processing. Answers customer FAQs by looking up a Google Sheet knowledge base. Provides service information (name, description, price) from a Google Sheet. Schedules appointments by: Asking the customer which service they want. Collecting their preferred day and time. Checking Google Calendar for available slots. Offering 3 options and letting the customer choose. Collecting name, email, and phone number. Creating the confirmed appointment in Google Calendar. Sends all customer-facing messages via a WhatsApp integration node. How to set up Connect your tools Link your Google Sheets for FAQs and Services. Connect your Google Calendar account. Configure your WhatsApp integration. Connect a transcription service (e.g., Whisper, Google Speech-to-Text, or another transcription API). Prepare your data FAQs Google Sheet → must contain columns: id | question | answer Services Google Sheet → must contain columns: id | service_name | service_description | price Adjust the flow Update the service names and questions to match your business. Set the correct time zone in the Google Calendar node. Update the WhatsApp integration node with your business account. Configure the transcription node with your chosen API credentials. Requirements Google Sheets (for FAQs and Services) Google Calendar WhatsApp integration in n8n Speech-to-Text API (for transcribing voice notes) How to customize the workflow Adding new FAQs**: Update the Google Sheet with new rows. Changing services**: Modify the Services Google Sheet to reflect updated offerings or prices. Custom messages**: Update the agent_reply node text to reflect your brand tone. Advanced logic**: Add routing for voice-note-only customers, VIP handling, or multilingual support. Notes This template uses multiple external integrations (Google Sheets, Google Calendar, WhatsApp, Speech-to-Text).

Overview 📌 This template is a multimodal WhatsApp assistant that understands text, images, and audio, aggregates media inputs, and returns intelligent replies using Google Gemini. It can fetch knowledge from Google Docs, log conversations into Google Sheets, and respond via WhatsApp — all orchestrated inside n8n. Features ✨ Multimodal input handling: Receives images and audio from WhatsApp, analyzes them, and sends contextual responses. 🖼️🎧 Audio transcription: Converts voice messages to text for analysis. 🔊➡️📝 Image analysis: Extracts objects/labels/text from images to inform responses. 🖼️🔍 Knowledge fetch: Pulls relevant documents from Google Docs for richer answers. 📄📚 Conversation logging: Appends each interaction to Google Sheets for auditing or analytics. 📈 Modular design: Clear subflows for media reception, transcription, image analysis, aggregation, and the AI Agent. ⚙️ Ready for customization: Swap models, change providers, or extend with a vector store. 🔁 Requirements ✅ n8n instance (self-hosted or n8n.cloud) with public webhook access Google Cloud project with these APIs enabled: Vertex AI (Gemini), Cloud Vision API, Cloud Speech-to-Text, Drive & Docs & Sheets 🧠 Google Service Account JSON key (with permissions for above services) 🔐 WhatsApp Business API provider credentials (Twilio, 360dialog, or similar) 📞 (Optional) Pinecone or another vector store if you want embeddings / retrieval augmentation 🗂️ Setup Instructions 🔧 Import the workflow Download the .json from your package and in n8n Editor → Import → From File → select JSON. Save. Create credentials Google Service Account: Create service account in GCP, grant Vertex AI, Vision, Speech, Drive, Docs, Sheets roles, download JSON → create n8n Google Service Account credential and upload JSON. WhatsApp: Add your WhatsApp API credentials (API key/token, phone ID, webhook secret). (Optional) Vector store: Add Pinecone credentials if using embeddings. Configure media receiver nodes WhatsApp Trigger: Ensure webhook URL is set on your WhatsApp provider to forward incoming messages/media to n8n. 🌐 Audio Receiver nodes: point to incoming audio payload path or download URL. 🎧 Image Receiver nodes: point to image URL or attachment field. 🖼️ Transcription & Image Analysis Transcribe Audio: Select Google Speech-to-Text via your Google Service Account credential. Confirm language and sampling settings. 🗣️➡️📝 Analyze Image: Point to Vision API via same Google credential. Choose required outputs (labels, landmarks, OCR). 🔎 Aggregate media Confirm the Aggregate node collects text + transcribed audio + image analysis results into a single payload for the AI Agent. 🧩 AI Agent (Gemini) Open AI Agent node → choose your Google Gemini/Vertex AI credentials. Edit System Prompt to include: how to prioritize image/audio text, where to look up knowledge (Docs), and style/tone. Replace placeholders (business name, policies). ✍️ Knowledge Fetch (Google Docs) Configure Get a document in Google Docs node to point to your knowledge docs folder or specific document IDs. 📂 Conversation Logging Configure Google Sheets node to append rows to your chosen spreadsheet (structure below). 🧾 WhatsApp Reply Map AI Agent output to the WhatsApp Send message node and choose template messaging if needed. 💬 Test end-to-end Activate the workflow, send a text message, an image, and an audio message to your WhatsApp test number. Verify the AI reply and that logs appear in Google Sheets. 🧪 Google Sheet: Conversation Log (suggested columns) 🗒️ Column Type Description Timestamp Date/Time When the message arrived UserID Text WhatsApp user identifier (phone) MessageType Text text / image / audio / mixed MessageText Text Original text or transcribed text ImageAnalysis Text Vision API summary / labels / OCR text AttachmentURL Text Link to image/audio file AIResponse Text Final text reply sent to user Notes Text Any extra flags (e.g., escalation) Customization 🔁 Swap Gemini with another model provider by changing the AI node credentials and prompt structure. 🔄 Add a vector store (Pinecone) to enable retrieval-augmented generation from indexed docs. 🧠 Extend image analysis to OCR for receipts/invoices or barcode detection. 📑 Add an escalation path (send to human) by adding an “If → Escalate” node when confidence is low. 🚨 Suggested Node Renaming (for clarity) 🏷️ Rename generic nodes to explicit names so reviewers and users instantly understand flow: WhatsApp Trigger → WhatsApp Trigger (Inbound) Switch → Message Type Router audio receiver1/2 → Audio Receiver (Download) / Audio Receiver (Fallback) 🎧 Transcribe a recording → Transcribe Audio (Speech-to-Text) 📝 image receiver1/2 → Image Receiver (Download) / Image Receiver (Fallback) 🖼️ Analyze image → Image Analysis (Vision API) 🔍 Aggregate → Aggregate Media Inputs 🧩 AI Agent → Multimodal AI Agent (Gemini) 🤖 Get a document in Google Docs → Fetch Knowledge Doc 📂 Code → Format AI Response 🧾 Send message → WhatsApp – Send Reply 💬 Testing & Going Live 🚀 Ensure n8n webhook is publicly reachable (use an SSL domain/tunnel). 🔒 Test in a sandbox WhatsApp number first. 🧪 Monitor n8n Executions and enable an Error Workflow for graceful failure handling. ⚠️ If you expect high media volume, consider storage/retention policy for attachments. 🗄️ Support & Notes 🤝 I offer setup assistance and will help troubleshoot credential issues or prompt tuning until your workflow is working perfectly. Include contact info and a short support pledge in your template description to build trust. Feel free to ping me anytime—even after launch!👉 Contact: [email protected] | +20 106 180 3236

The "WhatsApp Productivity Assistant with Memory and AI Imaging" is a comprehensive n8n workflow that transforms your WhatsApp into a powerful, multi-talented AI assistant. It's designed to handle a wide range of tasks by understanding user messages, analyzing images, and connecting to various external tools and services. The assistant can hold natural conversations, remember past interactions using a MongoDB vector store (RAG), and decide which tool is best suited for a user's request. Whether you need to check your schedule, research a topic, get the latest news, create an image, or even analyze a picture you send, this workflow orchestrates it all seamlessly through a single WhatsApp chat interface. The workflow is structured into several interconnected components: WhatsApp Trigger & Incoming Message Processing:** This is the entry point, starting when a message (text or image) is received via WhatsApp. A Route Message by Type (Image/Text) node then intelligently routes the message based on its content type. A Typing.... node sends a typing indicator to the user for a better experience. If an image is received, it's downloaded, processed via an HTTP Request, and analyzed by the Analyze image node. The Code1 node then standardizes both text and image analysis output into a single, unified input for the main AI agent. Core AI Agent:** This is the brain of the operation. The AI Agent1 node receives the user's input, maintains short-term conversational memory using Simple Memory, and uses a powerful language model (gpt-oss-120b2 or gpt-oss-120b1) to decide which tool or sub-agent to use. It orchestrates all the other agents and tools. Productivity Tools Agent:** This group of nodes connects the assistant to your personal productivity suite. It includes sub-agents and tools for managing Google Calendar, Google Tasks, and Gmail, allowing you to schedule events, manage to-dos, and read emails. It leverages a language model (gpt-4.1-mini or gemini-2.5-flash) for understanding and executing commands within these tools. Research Tool Agent:** This agent handles all research-related queries. It has access to multiple search tools (Brave Web Search, Brave News Search, Wikipedia, Tavily, and a custom perprlexcia search) to find the most accurate and up-to-date information from the web. It uses a language model (gpt-oss-120b or gpt-4.1-nanoChat Model1) for reasoning. Long-Term Memory Webhook:** A dedicated sub-workflow (Webhook2) that processes conversation history, extracts key information using Extract Memory Info, and stores it in a MongoDB Atlas Vector Store for long-term memory. This allows the AI agent to remember past preferences and facts. Image Generation Webhook: ** A specialized sub-workflow (Webhook3) triggered when a user asks to create an image. It uses a dedicated AI Agent with MongoDB Atlas Vector Store1 for contextual image prompt generation, Clean Prompt Text1 to refine the prompt, an HTTP Request to an external image generation API (e.g., Together.xyz), and then converts and sends the generated image back to the user via WhatsApp. Use Cases Personal Assistant:** Schedule appointments, create tasks, read recent emails, and manage your daily agenda directly from WhatsApp. Information Retrieval:** Ask any factual, news, or research-based question and get real-time answers from various web sources. Creative Content Generation:** Request the AI to generate images based on your descriptions for logos, artwork, or social media content. Smart Communication:** Engage in natural, contextual conversations with an AI that remembers past interactions. Image Analysis:** Send an image and ask the AI to describe its contents or answer questions about it. Pre-conditions Before importing and running this template, you will need: Self-hosted n8n Instance:** This template requires a self-hosted n8n instance as it uses webhooks that need public accessibility. WhatsApp Business Account:** A Meta Developer Account configured for WhatsApp Business Platform API access. MongoDB Atlas Account:** A MongoDB Atlas cluster with a database and collection set up for the vector store. Google Cloud Project:** Configured with API access for Google Calendar, Google Tasks, and Gmail. API Keys/Accounts for:** OpenWeatherMap: For weather forecasts. Groq, OpenRouter, or Vercel AI Gateway: For various Language Models (e.g., gpt-oss-120b, gpt-5-nano, gpt-4o-mini). Mistral Cloud: For embedding models (e.g., codestral-embed-2505). Brave Search: For web and news searches. Tavily API: For structured search results. Together.xyz or similar Image Generation API: For creating images. Perplexity API (or self-hosted instance): For the perprlexcia tool (the current URL http://self hoseted perplexcia/api/search implies a self-hosted or custom endpoint). Publicly Accessible URLs:** Your n8n instance and any custom webhook endpoints (like perprlexcia) must be publicly accessible. Requirements (n8n Credentials) You will need to set up the following credentials within your n8n instance: WhatsApp OAuth account:** For the WhatsApp Trigger node. WhatsApp account:** For Send message2, Send message3, Download media, and Typing.... nodes. Google Palm Api account:** For Analyze image, Google Gemini Chat Model, gemini-2.5-flash, and Google Gemini Chat Model5 nodes. OpenWeatherMap account:** For the Get Weather Forecast node. Groq account:** For gpt-oss-120b node. Google Calendar OAuth2Api account:** For the Google Calendar tools. MongoDB account:** For MongoDB Atlas Vector Store nodes. OpenRouter account:** For gpt-5-nano and gpt-4.1-nanoChat Model1 nodes. Gmail account :** For Get many messages and Get a message nodes (ensure correct Gmail OAuth2 setup for each). Google Tasks account:** For the Google Tasks tools. Bearer Auth account:** For HTTP Request5 (used in media download). Brave Search account:** For Brave Web Search and Brave News Search nodes. Vercel Ai Gateway Api account:** For gpt-4.1-mini, gpt-oss-120b, gpt-oss-120b2, and gpt-4.1-nano nodes. HTTP Header Auth account:** For Tavily web search (create a new one named "Tavily API Key" with Authorization: Bearer YOUR_TAVILY_API_KEY) and HTTP Request (for Together.xyz, e.g., "Together.xyz API Key"). Mistral Cloud account:** For codestral-embed-2505, codestral-embed-, and codestral-embed-2506 nodes.

AI Recipe Generator from Pantry Items using FatSecret API This workflow creates an intelligent WhatsApp cooking assistant that transforms pantry ingredients into personalized recipe suggestions using AI and the FatSecret Recipes API What Makes This Different: AI-Powered Recipe Discovery** - Uses Google Gemini AI to understand user intent and dietary preferences Smart Ingredient Analysis** - Automatically extracts ingredients, dietary restrictions, and cooking constraints FatSecret API Integration** - Leverages comprehensive recipe database with nutritional information WhatsApp Native Experience** - Seamless chat interface for recipe discovery Contextual Memory** - Remembers conversation context for better user experience Intelligent Parameter Mapping** - AI automatically maps user requests to API parameters Key Benefits of AI-Driven Architecture: Natural Language Understanding** - Users can describe what they have in plain English Personalized Recommendations** - Considers dietary restrictions, time constraints, and preferences Eliminates Manual Search** - No need to manually input specific ingredients or filters Scalable Recipe Database** - Access to thousands of recipes through FatSecret API Conversational Interface** - Natural chat flow instead of form-based inputs Smart Context Management** - Remembers previous requests for better follow-up suggestions Who's it for This template is designed for food delivery services, meal planning apps, nutritionists, cooking enthusiasts, and businesses looking to provide intelligent recipe recommendations. It's perfect for companies who want to engage customers through WhatsApp with personalized cooking assistance, helping users discover new recipes based on available ingredients and preferences. How it works / What it does This workflow creates an intelligent WhatsApp cooking assistant that transforms simple ingredient lists into personalized recipe suggestions. The system: Receives WhatsApp messages through webhook triggers Analyzes user input using Google Gemini AI to extract ingredients, dietary needs, and preferences Maps user requests to FatSecret API parameters automatically Searches recipe database based on extracted criteria (ingredients, calories, time, cuisine, etc.) Processes API results to format recipe suggestions with images and nutritional info Maintains conversation context using memory buffer for better user experience Sends formatted responses back to users via WhatsApp Key Innovation: AI-Powered Parameter Extraction - Unlike traditional recipe apps that require users to fill out forms or select from predefined options, this system understands natural language requests and automatically maps them to the appropriate API parameters, making recipe discovery as simple as texting a friend. How to set up Configure WhatsApp Business API Set up WhatsApp Business API credentials Configure webhook endpoints for message reception Set up phone number ID and recipient handling Ensure proper message sending permissions Configure Google Gemini AI Set up Google Gemini (PaLM) API credentials Ensure proper API access and quota limits Configure the AI model for recipe-related conversations Test the AI's understanding of cooking terminology Configure FatSecret API Set up FatSecret OAuth2 API credentials Ensure access to the Recipes Search v3 endpoint Configure proper authentication and rate limiting Test API connectivity and response handling Set up Memory Management Configure the memory buffer for conversation context Set appropriate session key mapping for user identification Adjust context window length based on expected conversation depth Test memory persistence across multiple messages Test the Integration Send test messages through WhatsApp to verify end-to-end functionality Test various ingredient combinations and dietary restrictions Verify recipe suggestions are relevant and properly formatted Check that context memory works across multiple interactions Requirements WhatsApp Business API** account with webhook capabilities Google Gemini AI** API access for natural language processing FatSecret API** credentials for recipe database access n8n instance** with proper webhook and HTTP request capabilities Active internet connection** for real-time API interactions How to customize the workflow Modify Recipe Search Parameters Adjust the number of results returned (currently set to 5) Add more filtering options (cuisine types, cooking methods, difficulty levels) Implement pagination for browsing through more recipe options Add sorting preferences (newest, oldest, calorie-based, popularity) Enhance AI Capabilities Train the AI on specific dietary restrictions or cuisine preferences Add support for multiple languages Implement recipe rating and review integration Add nutritional goal tracking and meal planning features Expand Recipe Sources Integrate with additional recipe APIs (Spoonacular, Edamam, etc.) Add support for user-generated recipes Implement recipe bookmarking and favorites Add shopping list generation from selected recipes Improve User Experience Add recipe step-by-step instructions Implement cooking timer and progress tracking Add recipe sharing capabilities Implement user preference learning over time Business Features Add recipe monetization options Implement affiliate marketing for ingredients Add restaurant delivery integration Implement meal kit subscription services Key Features Natural language processing** - Understands cooking requests in plain English Intelligent parameter mapping** - AI automatically extracts search criteria Comprehensive recipe database** - Access to thousands of recipes via FatSecret API WhatsApp native interface** - Seamless chat experience for recipe discovery Contextual memory** - Remembers conversation history for better recommendations Dietary restriction support** - Handles allergies, preferences, and special diets Nutritional information** - Provides calorie counts and macro details Image integration** - Shows recipe photos when available Technical Architecture Highlights AI-Powered Processing Google Gemini integration** - Advanced natural language understanding Smart parameter extraction** - Automatic mapping of user requests to API calls Contextual memory** - Conversation history management for better user experience Intelligent fallbacks** - Graceful handling of unclear or incomplete requests API Integration Excellence FatSecret Recipes API** - Comprehensive recipe database with nutritional data OAuth2 authentication** - Secure and reliable API access Parameter optimization** - Efficient API calls with relevant search criteria Response processing** - Clean formatting of recipe suggestions WhatsApp Integration Webhook-based triggers** - Real-time message reception Message formatting** - Clean, readable recipe presentations User identification** - Proper session management for multiple users Error handling** - Graceful fallbacks for failed operations Performance Optimizations Efficient API calls** - Single request per user message Memory management** - Optimized conversation context storage Response caching** - Reduced API calls for repeated requests Scalable architecture** - Handles multiple concurrent users Use Cases Food delivery platforms** requiring recipe recommendation engines Meal planning services** needing ingredient-based recipe discovery Nutrition and wellness apps** requiring dietary-specific suggestions Cooking schools** offering personalized recipe guidance Grocery stores** helping customers plan meals around available ingredients Restaurant chains** providing recipe inspiration for home cooking Health coaches** offering personalized meal suggestions Social cooking communities** sharing recipe ideas and inspiration Business Value Customer Engagement** - Interactive recipe discovery increases user retention Personalization** - AI-driven recommendations improve user satisfaction Operational Efficiency** - Automated recipe suggestions reduce manual support Revenue Generation** - Recipe recommendations can drive ingredient sales Brand Differentiation** - AI-powered cooking assistant sets services apart Data Insights** - User preferences provide valuable market intelligence Scalability** - Handles multiple users simultaneously without performance degradation This template revolutionizes recipe discovery by combining the power of AI natural language processing with comprehensive recipe databases, creating an intuitive WhatsApp experience that makes cooking inspiration as simple as having a conversation with a knowledgeable chef friend.

Who's it for Business owners, freelancers, and professionals who use Cal.com or Calendly for scheduling and want instant WhatsApp notifications for all booking activities without constantly checking their email or calendar apps. What it does This workflow automatically monitors your calendar booking events from both Cal.com and Calendly, then sends beautifully formatted WhatsApp messages to notify you of: New bookings with guest details Rescheduled meetings with old vs new times Cancelled appointments Meeting completion notifications (Cal.com only) The AI agent intelligently formats each message with emojis, proper spacing, and all relevant booking information including guest names, emails, dates, times, locations, and notes. How it saves you time Stop checking multiple platforms: Instead of constantly monitoring email notifications, calendar apps, and booking dashboards, get everything instantly on WhatsApp - the app you're already using throughout the day. Immediate awareness: Know about booking changes the moment they happen, not hours later when you finally check your email. This means you can quickly adjust your schedule, prepare for meetings, or reach out to clients if needed. Mobile-first notifications: Since most people check WhatsApp more frequently than email, you'll never miss important booking updates again. Perfect for busy professionals who are often away from their desk. How it works When a booking event occurs on either platform, the workflow captures the data, merges it through an aggregator, then uses Google Gemini AI to generate a professionally formatted WhatsApp message that gets sent instantly to your phone. Requirements Cal.com and/or Calendly account with API access WhatsApp Business API credentials Google API key for Gemini Active webhook endpoints for both calendar services How to customize Update the recipient phone number in the WhatsApp node Modify message templates in the AI Agent's system prompt Add additional calendar platforms by connecting more trigger nodes Customize emoji usage and message formatting to match your brand

Overview Turn WhatsApp chats into instant answers and real-time bookings—all in one n8n workflow. Your AI Agent leverages Gemini embeddings + Pinecone for on-the-fly knowledge retrieval, then logs reservations directly into Google Sheets. Features AI-powered Q&A: Natural-language responses driven by Gemini + Pinecone vector search Seamless Reservations: Book services via WhatsApp; entries auto-append to Google Sheets Auto-Embedding Sub-workflow: Drag-and-drop Google Drive docs get indexed in Pinecone 24-Hour Follow-Up: Automated template messages if no response within a day Personal Support Pledge: Hands-on help until your workflow runs flawlessly Requirements n8n account (self-hosted or n8n.cloud) Google Cloud project with Gemini & Drive APIs enabled Pinecone account (free tier works) Google Sheets account WhatsApp Business API credentials (e.g. Twilio, 360dialog) Setup Instructions Import Workflow Download the .json file from your Gumroad purchase In n8n Editor → Import → From File → select the JSON Add Credentials Google Service Account (Gemini & Drive APIs) Pinecone (API Key + Environment) Google Sheets OAuth2 WhatsApp Business API (HTTP credential or native) Configure Nodes AI Agent: select Gemini credentials; update system prompt with your business name & services Pinecone Loader: point “Google Drive” node to your docs folder Sheets Append: set Spreadsheet ID, sheet name “reservations”, map Timestamp, UserID, Service, Date, Time, Notes WhatsApp Trigger & Send: set webhook URL; choose approved template name Test End-to-End Activate the workflow → send a test WhatsApp message → verify AI reply + new row in your sheet Google Sheet Structure Column Description Timestamp Auto-generated when a user books UserID : Unique WhatsApp user identifier Service : Chosen service or product name Date : Booking date Time : Booking time slot Notes : Any extra information (e.g., special requests) Customization Add New Services: Edit the system prompt’s services list Change Follow-Up Window: Adjust the “24-hour window check” node logic Embed Different Docs: Point the Drive node at any folder of PDFs/TXT 📞 Personal Support Pledge: I’ll work with you (via WhatsApp or email, remote desktop ) until your workflow is running flawlessly—no extra fees, no “good luck” drop‑off. Just send a message via: Email: [email protected] WhatsApp: +20 106 180 3236

This workflow automatically transforms your messy inbox into a neatly organized space while ensuring you never miss a critical message. It connects to your Gmail account and triggers for every new email. Using a powerful AI agent, the workflow first analyzes the email's content, sender, and metadata to classify it and apply the appropriate Gmail label (e.g., "Finance," "Marketing," "Dev Tools"). In parallel, a second AI agent determines if the email is urgent (like a security alert, OTP, or payment reminder) and generates a concise summary. If an email is marked as urgent, the workflow instantly sends a notification with the summary to your Telegram and WhatsApp, allowing you to take immediate action. This workflow is perfect for anyone looking to automate their email management, reduce inbox clutter, and stay on top of important, time-sensitive communications. Step-by-Step Explanation This workflow is designed to intelligently categorize incoming emails and notify you of urgent messages. Here is a breakdown of how it operates: Trigger: New Email Received Node: Gmail Trigger Action: The workflow initiates whenever a new email arrives in your connected Gmail inbox. Fetch Full Email Content Node: Get a message Action: It takes the ID of the new email from the trigger and fetches the complete message body, subject, sender, and headers. AI-Powered Categorization Node: AI Agent2 Action: This AI agent analyzes the full email content. Based on a detailed prompt that includes classification rules (e.g., if the sender is GitHub, classify as "Dev Tools"), it determines the most appropriate category and outputs the corresponding Label ID. Label Management and Application Node: Loop Over Items -> Create Label if Doesn't exist -> Get Existing Labels -> Filter -> Add label to thread Action: This sequence ensures the email gets the correct label. It first attempts to create the Gmail label suggested by the AI. The node is set to continue even if the label already exists. It then fetches a list of all your current Gmail labels. A Filter node finds the exact ID of the label that matches the AI's suggestion. Finally, it applies this label to the email thread, neatly organizing it in your inbox. Urgency Analysis and Summarization Node: AI Agent Action: Concurrently, a second AI agent analyzes the email to determine its urgency (classifying it as "urgent" or "normal") and generates a two-sentence summary. Parse AI Output Node: Code Action: A simple code node cleans up the JSON output from the urgency analysis to ensure it's correctly formatted for the next step. Conditional Notification Logic Node: If Action: This node checks the output from the previous step. It proceeds only if the email's urgency is marked as "urgent." Send Instant Alerts Nodes: Send a text message (Telegram) & Send message (WhatsApp) Action: If an email is deemed urgent, the workflow immediately sends an alert containing the email summary to your specified Telegram chat and WhatsApp number.

This workflow automatically summarizes your team's daily meetings from multiple Google Calendars daily at 9AM and sends the digest to your preferred communication channels. It uses AI to identify and format meeting details, making it easy to see your schedule at a glance. Good to Know Multi-Calendar Support**: This workflow is designed to pull events from any number of Google Calendars you've connected, providing a single, consolidated summary. AI-Powered Summaries**: The AI Agent, powered by Google Gemini, is instructed to format the output with key details like title, time, duration, and a link to join the meeting. This saves you from sifting through calendar invites. How It Works A Schedule Trigger starts the workflow at a set time each day e.g at 9 AM (or any other time you choose). An AI Agent with access to the Google Calendar tool is prompted to fetch today's events from all connected calendars. The Google Calendar nodes retrieve all meetings for the current day. The AI Agent processes this information and generates a clean, structured summary. Finally, the formatted summary is sent to your team's chosen communication platforms: Slack, Discord, and WhatsApp. How to Use Set the Schedule: Adjust the Schedule Trigger to run at a time that works best for your team—for example, every morning before the workday begins. Connect Your Accounts: Add your Google Calendar credentials to connect all the calendars you want to monitor. Choose Your Channels: Connect the appropriate Slack, Discord, and/or WhatsApp nodes and configure them to send the message to your desired channels or groups. Requirements Google Gemini account**: A Google Gemini account is needed for the AI Agent and Chat Model to function. Google Calendar account(s)**: You'll need to connect the Google Calendar accounts you wish to pull data from. Communication platform account(s)**: Credentials for the communication apps you want to use (Slack, Discord, WhatsApp). Customizing This Workflow Modify the Trigger: You can change the **Schedule Trigger to a different interval or even trigger the workflow manually with a webhook. Adjust the AI Prompt**: Fine-tune the AI Agent's prompt to change the summary format, include more details, or even ask it to highlight the most important meetings of the day. Add More Platforms**: Easily add more communication nodes to send the daily summary to other platforms like Microsoft Teams, email, or even a custom CRM.

Who is this for? This workflow is for businesses and individuals who want to automate calendar management via WhatsApp using n8n. It’s ideal for appointment-based services, consultants, and anyone who needs to streamline event scheduling, updates, or cancellations through a simple chat interface. What problem is this workflow solving? Manually managing calendar events is time-consuming and error-prone, especially when clients communicate through messaging apps like WhatsApp. This workflow solves the problem by connecting WhatsApp to Google Calendar, enabling users to manage events directly via chat, reducing administrative overhead and response times. What this workflow does This workflow enables WhatsApp-based interaction with Google Calendar. Users can: Create new events Update existing events Delete events Retrieve a list of scheduled events Optionally, AI (like ChatGPT or Gemini) can be used to interpret natural language inputs, making the interaction even smoother. Setup Add credentials: WhatsApp: Connect your WhatsApp API (OAuth or other supported method). Google Calendar: Add your Google account credentials to allow calendar access. AI (optional): Add credentials for ChatGPT, Gemini, or another language model if using AI for natural language parsing. Import the workflow into n8n and review all nodes. Test the WhatsApp webhook to ensure it’s receiving messages correctly. Connect to your Google Calendar and test event creation and retrieval.