Workflow Templates

🤖 Automated AI News Video Creation and Social Media Publishing Workflow ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 🎯 Overview: This workflow fully automates the creation and social media distribution of AI-generated news videos. It fetches news, crafts captions, generates avatar videos via HeyGen, stores them, and publishes them across Instagram, Facebook, and YouTube via Postiz. 🔄 WORKFLOW PROCESS: News Fetching: Reads the latest news from an RSS feed. AI Captioning: Generates concise, engaging captions using an AI agent (GPT-4o-mini). Video Generation: Creates an AI avatar video using HeyGen with the generated caption. Video Storage: Downloads the video and uploads it to Google Drive for archival. Data Logging: Records all news and video metadata into Google Sheets. Postiz Upload: Uploads the video to Postiz's internal storage for publishing. Social Publishing: Fetches Postiz integrations and routes the video to Instagram, Facebook, and YouTube after platform-specific content cleaning. ⚙️ KEY TECHNOLOGIES: RSS Feeds:** News source. LangChain (n8n nodes):** AI Agent and Chat OpenAI for caption generation. HeyGen API:** AI avatar video creation. Google Drive:** Video file storage. Google Sheets:** Data logging and tracking. Postiz API:** Unified social media publishing platform. ⚠️CRITICAL CONFIGURATIONS: API Keys:** Ensure HeyGen and Postiz API keys are correctly set in credentials and the 'Setup Heygen Parameters' node. HeyGen IDs:** Verify avatar_id and voice_id in 'Setup Heygen Parameters'. Postiz URL:** Confirm https://postiz.yourdomain.com is your correct Postiz instance URL across all HTTP Request nodes. Credentials:** All Google, OpenAI, and Postiz credentials must be properly linked. 📈BENEFITS: Automated content creation and distribution, saving significant time. Consistent branding and messaging across multiple platforms. Centralized logging for tracking and performance analysis. Scalable solution for high-volume content demands.

SEO Content Generation Workflow - n8n Template Instructions Who's it for This workflow is designed for SEO professionals, content marketers, digital agencies, and businesses who need to generate optimized meta tags, H1 headings, and content briefs at scale. Perfect for teams managing multiple clients or large keyword lists who want to automate competitor analysis and SEO content creation while maintaining quality and personalization. How it works The workflow automates the entire SEO content creation process by analyzing your target keywords against top competitors, then generating optimized meta elements and comprehensive content briefs. It uses AI-powered analysis combined with real competitor data to create SEO-friendly content that's tailored to your specific business context. The system processes keywords in batches, performs Google searches, scrapes competitor content, analyzes heading structures, and generates personalized SEO content using your company's database information for maximum relevance. Requirements Required Services and Credentials Google Sheets API**: For reading configuration and updating results Anthropic API**: For AI content generation (Claude Sonnet 4) OpenAI API**: For embeddings and vector search Apify API**: For Google search results Firecrawl API**: For competitor website scraping Supabase**: For vector database (optional but recommended) Template Spreadsheet Copy this template spreadsheet and configure it with your information: Template Link How to set up Step 1: Copy and Configure Template Make a copy of the template spreadsheet Fill in the Client Information sheet: Client name: Your company or client's name Client information: Brief business description URL: Website address Supabase database: Database name (prevents AI hallucination) Tone of voice: Content style preferences Restrictive instructions: Topics or approaches to avoid Complete the SEO sheet with your target pages: Page: Page you're optimizing (e.g., "Homepage", "Product Page") Keyword: Main search term to target Awareness level: User familiarity with your business Page type: Category (homepage, blog, product page, etc.) Step 2: Import Workflow Import the n8n workflow JSON file Configure all required API credentials in n8n: Google Sheets OAuth2 Anthropic API key OpenAI API key Apify API key Firecrawl API key Supabase credentials (if using vector database) Step 3: Test Configuration Activate the workflow Send your Google Sheets URL to the chat trigger Verify that all sheets are readable and credentials work Test with a single keyword row first Workflow Process Overview Phase 0: Setup and Configuration Copy template spreadsheet Configure client information and SEO parameters Set up API credentials in n8n Phase 1: Data Input and Processing Chat trigger receives Google Sheets URL System reads client configuration and SEO data Filters valid keywords and empty H1 fields Initiates batch processing Phase 2: Competitor Research and Analysis Searches Google for top 10 results per keyword Scrapes first 5 competitor websites Extracts heading structures (H1-H6) Analyzes competitor meta tags and content organization Phase 3: Meta Tags and H1 Generation AI analyzes keyword context and competitor data Accesses client database for personalization Generates optimized meta title (65 chars max) Creates compelling meta description (165 chars max) Produces user-focused H1 (70 chars max) Phase 4: Content Brief Creation Analyzes search intent percentages Develops content strategy based on competitor analysis Creates detailed MECE page structure Suggests rich media elements Provides writing recommendations and detail level scoring Phase 5: Data Integration and Updates Combines all generated content into unified structure Updates Google Sheets with new SEO elements Preserves existing data while adding new content Continues batch processing for remaining keywords How to customize the workflow Adjusting AI Models Replace Anthropic Claude with other LLM providers Modify system prompts for different content styles Adjust character limits for meta elements Modifying Competitor Analysis Change number of competitors analyzed (currently 5) Adjust scraping parameters in Firecrawl nodes Modify heading extraction logic in JavaScript nodes Customizing Output Format Update Google Sheets column mapping in Code node Modify structured output parser schema Change batch processing size in Split in Batches node Adding Quality Controls Insert validation nodes between phases Add error handling and retry logic Implement content quality scoring Extending Functionality Add keyword research capabilities Include image optimization suggestions Integrate social media content generation Connect to CMS platforms for direct publishing Best Practices Test with small batches before processing large keyword lists Monitor API usage and costs across all services Regularly update system prompts based on output quality Maintain clean data in your Google Sheets template Use descriptive node names for easier workflow maintenance Troubleshooting API Errors**: Check credential configuration and usage limits Scraping Failures**: Firecrawl nodes have error handling enabled Empty Results**: Verify keyword formatting and competitor availability Sheet Updates**: Ensure proper column mapping in final Code node Processing Stops**: Check batch processing limits and timeout settings

Generate AI Viral Videos with VEO3 and Auto-Publish to TikTok Who is this for? This workflow is for content creators, marketers, and social media managers who want to consistently produce viral-style short videos and publish them automatically to TikTok — without manual editing or uploading. What problem is this workflow solving? / Use case Creating short-form video content that stands out takes time: ideation, scriptwriting, video generation, and publishing. This workflow automates the entire pipeline — from idea generation to TikTok upload — enabling you to scale your content strategy and focus on creativity rather than repetitive tasks. What this workflow does Generates viral video ideas** daily using GPT-5 Creates structured prompts** for before/after transformation videos Renders cinematic vertical videos** with VEO3 (9:16 format) Saves ideas and metadata** into Google Sheets for tracking Uploads videos automatically to TikTok** via Blotato integration Updates status in Google Sheets** once the video is live The result: a fully automated daily viral video publishing system. Setup Google Sheets Connect your Google Sheets account. Create a sheet with columns for idea, caption, environment, sound, production, and final_output. OpenAI Add your OpenAI API credentials (for GPT-5 mini / GPT-4.1 mini). VEO3 (Kie API) Set up your API key in the HTTP Request node (Generate Video with VEO3). Blotato Connect your Blotato account for TikTok publishing. Schedule Trigger Adjust the Start Daily Content Generation node to fit your preferred posting frequency. How to customize this workflow to your needs Platforms**: Extend publishing to YouTube Shorts or Instagram Reels by duplicating the TikTok step. Frequency**: Change the Schedule Trigger to post multiple times per day or only a few times per week. Creative Style**: Modify the system prompts to align with your brand’s style (cinematic, minimalist, neon, etc.). Tracking**: Enhance the Google Sheets logging with engagement metrics by pulling TikTok analytics via Blotato. This workflow helps you build a hands-free AI-powered content engine, turning raw ideas into published viral videos every day. 📄 🎥 Watch This Tutorial: Step by Step 📄 Documentation: Notion Guide Need help customizing? Contact me for consulting and support : Linkedin / Youtube

Jotform AI-Powered Loan Application & Pre-Approval Automation System Transform manual loan processing into same-day pre-approvals - achieving 50% faster closings, 90% reduction in manual review time, and automated underwriting decisions with AI-powered financial analysis and instant applicant notifications. What This Workflow Does Revolutionizes mortgage and loan processing with AI-driven financial analysis and automated decision workflows: 📝 Digital Application Capture - Jotform collects complete applicant data, income, employment, and loan details 🤖 AI Financial Analysis - GPT-4 calculates debt-to-income ratio, loan-to-value ratio, and approval likelihood 💳 Automated Credit Assessment - Instant credit score evaluation and payment history analysis 📊 Risk Scoring - AI assigns 1-100 risk scores based on multiple financial factors ✅ Intelligent Routing - Automatic pre-approval, conditional approval, or denial based on lending criteria 📧 Instant Notifications - Applicants receive approval letters within minutes of submission 👔 Underwriter Alerts - Pre-approved loans automatically route to loan officers with complete analysis 📋 Document Tracking - Required documents list generated based on application specifics 📅 Closing Scheduling - Approved loans trigger closing coordination workflows 📈 Complete Audit Trail - Every application logged with financial metrics and decision rationale Key Features AI Underwriting Analyst: GPT-4 evaluates loan applications across 10+ financial dimensions including debt ratios, risk assessment, and approval recommendations Debt-to-Income Calculation: Automatically calculates DTI ratio and compares against lending standards (43% threshold for qualified mortgages) Loan-to-Value Analysis: Evaluates down payment adequacy and property value against loan amount requested Credit Score Integration: Simulated credit assessment (ready for real credit bureau API integration like Experian, Equifax, TransUnion) Approval Likelihood Scoring: AI predicts approval probability as high/medium/low based on complete financial profile Risk Assessment: 1-100 risk score considers income stability, debt levels, credit history, and employment status Interest Rate Recommendations: AI suggests appropriate rate ranges based on applicant qualifications Conditional Approval Logic: Identifies specific requirements needed for final approval (additional documentation, debt paydown, etc.) Multi-Path Routing: Different workflows for pre-approved (green path), conditional (yellow path), and denied (red path) applications Monthly Payment Estimates: AI calculates estimated mortgage payments including principal, interest, taxes, and insurance Employment Verification Tracking: Flags employment status and stability in approval decision Document Requirements Generator: Custom list of required documents based on applicant situation and loan type Underwriter Dashboard Integration: Pre-approved applications automatically notify underwriters with complete financial summary Applicant Communication: Professional, branded emails for every outcome (pre-approval, conditional, denial) Alternative Options for Denials: Denied applicants receive constructive guidance on improving qualifications Compliance Ready: Decision rationale documented for regulatory compliance and audit requirements Perfect For Mortgage Lenders: Banks and credit unions processing home loan applications (purchase, refinance, HELOC) Commercial Lenders: Business loan and commercial real estate financing institutions Auto Finance Companies: Car dealerships and auto loan providers needing instant credit decisions Personal Loan Providers: Fintech companies and online lenders offering consumer loans Credit Unions: Member-focused financial institutions streamlining loan approval processes Mortgage Brokers: Independent brokers managing applications for multiple lenders Hard Money Lenders: Alternative lenders with custom underwriting criteria Student Loan Services: Educational financing with income-based qualification What You'll Need Required Integrations Jotform - Loan application form (free tier works, Pro recommended for file uploads) Create your form for free on Jotform using this link: https://www.jotform.com OpenAI API - GPT-4 for AI financial analysis and underwriting decisions (approximately 0.30-0.50 USD per application) Gmail - Automated notifications to applicants and underwriters Google Sheets - Loan application database and pipeline tracking Optional Integrations (Recommended for Production) Credit Bureau APIs - Experian, Equifax, or TransUnion for real credit pulls Document Management - DocuSign, HelloSign for e-signatures and document collection Property Appraisal APIs - Automated valuation models for property verification Calendar Integration - Calendly or Google Calendar for closing date scheduling CRM Systems - Salesforce, HubSpot for lead management and follow-up Loan Origination Software (LOS) - Encompass, Calyx, BytePro integration Quick Start Import Template - Copy JSON and import into n8n Add OpenAI Credentials - Set up OpenAI API key (GPT-4 required for accurate underwriting) Create Jotform Loan Application: Full Name (q3_fullName) Email (q4_email) Phone (q5_phone) Social Security Number (q6_ssn) - encrypted field Monthly Income (q7_monthlyIncome) - number field Monthly Debts (q8_monthlyDebts) - number field (credit cards, car loans, student loans) Loan Amount Requested (q9_loanAmount) - number field Down Payment (q10_downPayment) - number field Property Value (q11_propertyValue) - number field Employment Status (q12_employmentStatus) - dropdown (Full-time, Part-time, Self-employed, Retired) Additional fields: Date of Birth, Address, Employer Name, Years at Job, Property Address Configure Gmail - Add Gmail OAuth2 credentials (same for all 4 Gmail nodes) Setup Google Sheets: Create spreadsheet with "Loan_Applications" sheet Replace YOUR_GOOGLE_SHEET_ID in workflow 16 columns auto-populate: timestamp, applicationId, applicantName, email, phone, loanAmount, downPayment, monthlyIncome, monthlyDebts, creditScore, dtiRatio, ltvRatio, riskScore, approvalStatus, monthlyPayment, interestRate Customize Approval Criteria (Optional): Edit "Check Approval Status" node Adjust credit score minimum (default: 680) Modify DTI threshold (default: 43%) Set LTV requirements Configure Credit Integration: Replace "Simulate Credit Check" node with real credit bureau API Or keep simulation for testing/demo purposes Brand Email Templates: Update company name, logo, contact information Customize approval letter formatting Add compliance disclosures as required Set Underwriter Email: Update underwriter contact in "Notify Underwriter" node Add CC recipients for loan ops team Test Workflow - Submit test applications with different scenarios: High income, low debt (should pre-approve) Moderate income, high debt (should conditional) Low income, excessive debt (should deny) Compliance Review - Have legal/compliance team review automated decision logic Go Live - Deploy form on website, share with loan officers, integrate with marketing Customization Options Loan Type Variations: Customize for conventional, FHA, VA, USDA, jumbo, or commercial loans Custom Underwriting Rules: Adjust DTI limits, credit minimums, LTV requirements per loan product Manual Review Triggers: Flag edge cases for manual underwriter review before automation Document Upload Integration: Add Jotform file upload fields for paystubs, tax returns, bank statements Income Verification APIs: Integrate with Plaid, Finicity, or Argyle for automated income verification Employment Verification: Connect to The Work Number or other employment databases Property Appraisal Automation: Integrate AVMs (Automated Valuation Models) from CoreLogic, HouseCanary Co-Borrower Support: Add fields and logic for joint applications with multiple income sources Business Loan Customization: Modify for business financials (revenue, EBITDA, business credit scores) Rate Shopping: Integrate rate tables to provide real-time interest rate quotes Pre-Qualification vs Pre-Approval: Create lighter version for soft credit pull pre-qualification Conditional Approval Workflows: Automated follow-up sequences for document collection Closing Coordination: Integrate with title companies, attorneys, closing services Regulatory Compliance: Add TRID timeline tracking, adverse action notices, HMDA reporting Multi-Language Support: Translate forms and emails for Spanish, Chinese, other languages Expected Results Same-day pre-approval - Applications processed in minutes vs 3-5 days manual review 50% faster closings - Streamlined process reduces time from application to closing 90% reduction in manual review time - AI handles initial underwriting, humans only review exceptions 95% applicant satisfaction - Instant decisions and clear communication improve experience 75% reduction in incomplete applications - Required fields force complete submission 60% fewer applicant calls - Automated status updates reduce "where's my application" inquiries 100% application tracking - Complete audit trail from submission to final decision 40% increase in loan officer productivity - Focus on high-value activities, not data entry 80% decrease in approval errors - Consistent AI analysis eliminates human calculation mistakes 30% improvement in compliance - Automated documentation and decision rationale for audits Pro Tips Test with Multiple Scenarios: Submit applications with various income/debt combinations to validate routing logic works correctly Adjust DTI Thresholds for Loan Type: Conventional mortgages: 43% max. FHA loans: 50% max. Auto loans: 35-40% max. Personal loans: 40-45% max. Credit Score Tiers Matter: Build rate sheets with score tiers (740+: prime, 680-739: near-prime, 620-679: subprime, below 620: denied or hard money) Income Verification Priorities: W-2 employees (easy), self-employed (complex), commission/bonus heavy (average 2 years), rental income (75% counts), gig economy (difficult) Document Checklist Customization: Vary required docs by loan type, amount, and risk profile to avoid over-documentation for low-risk loans Conditional Approval vs Outright Denial: When in doubt, use conditional - gives applicants path to approval and keeps them in pipeline Adverse Action Notices: For denials, include specific reasons (per FCRA requirements) and instructions for disputing credit report errors Pre-Qualification vs Pre-Approval: Pre-qual uses soft credit pull (no impact on score), pre-approval uses hard pull (official decision) Co-Borrower Logic: When DTI is high, automatically suggest co-borrower as option to strengthen application Rate Lock Automation: Pre-approved applications should include rate lock expiration date (typically 30-60 days) Property Appraisal Triggers: Auto-order appraisals for pre-approved mortgage applications to keep process moving Underwriter Dashboard: Build Google Sheets dashboard with filters for underwriters to sort by approval status, loan amount, date Compliance Monitoring: Regular audits of AI decisions to ensure no discriminatory patterns (disparate impact analysis) Customer Service Integration: Link application IDs to support tickets so agents can quickly pull up loan status Marketing Attribution: Track lead sources in form to measure which marketing channels produce best-quality applicants Learning Resources This workflow demonstrates advanced automation: AI Agents for Financial Analysis: Multi-dimensional loan qualification using BANT-style underwriting criteria Complex Conditional Logic: Multi-path routing with nested IF conditions for approval/conditional/denial workflows Financial Calculations: Automated DTI, LTV, DSCR, and payment estimation algorithms Risk Scoring Models: Comprehensive risk assessment combining credit, income, debt, and employment factors Decision Documentation: Complete audit trail with AI reasoning for regulatory compliance Email Customization: Dynamic content generation based on approval outcomes and applicant situations Data Pipeline Design: Structured data flow from application through analysis to decision and notification Simulation vs Production: Credit check node designed for easy swap from simulation to real API integration Parallel Processing: Simultaneous logging and notification workflows for efficiency Workflow Orchestration: Coordination of multiple decision points and communication touchpoints Questions or customization? The workflow includes detailed sticky notes explaining each analysis component and decision logic. Template Compatibility ✅ n8n version 1.0+ ✅ Works with n8n Cloud and Self-Hosted ✅ Production-ready for financial institutions ✅ Fully customizable for any loan type Compliance Note: This template is designed for demonstration and automation purposes. Always consult with legal counsel to ensure compliance with TILA, RESPA, ECOA, FCRA, and applicable state lending regulations before deploying in production.

This template sets up a scheduled automation that scrapes the latest news from The Hindu website, uses a Google Gemini AI Agent to filter and analyze the content for relevance to the Competitive Exams like UPSC Civil Services Examination (CSE) syllabus, and compiles a structured daily digest directly into a Google Sheet. It saves hours of manual reading and note-taking by providing concise summaries, subject categorization, and explicit UPSC importance notes. Who’s it for This workflow is essential for: UPSC/CSE Aspirants who require a curated, focused, and systematic daily current affairs digest. Coaching Institutes aiming to instantly generate structured, high-quality study material for their students. Educators and Content Creators focused on Governance, Economy, International Relations, and Science & Technology. How it works / What it does This workflow runs automatically every morning (scheduled for 7 AM by default) to generate a ready-to-study current affairs document. Scraping: The Schedule Trigger fires an HTTP Request to fetch the latest news links from The Hindu's front page. Data Curation: The HTML and Code in JavaScript nodes work together to extract and pair every article URL with its title. Content Retrieval: For each identified link, a second HTTP Request node fetches the entire article body. AI Analysis and Filtering: The AI Agent uses a detailed prompt and the Google Gemini Chat Model to perform two critical tasks: Filter: It filters out all irrelevant articles (e.g., sports results, local crime) to keep only the 5-6 most important UPSC-relevant pieces (Polity, Economy, IR, etc.). Analyze: For the selected articles, it generates a Brief Summary, identifies the Main Subject, and clearly articulates Why it is Important for the UPSC Exam. Storage: The AI Agent calls the integrated Google Sheets Tool to automatically append the structured, analyzed data into your designated Google Sheet, creating your daily ready-made notes. Requirements To deploy this workflow, you need: n8n Account: (Cloud or self-hosted). Google Gemini API Key: For connecting the Google Gemini Chat Model and powering the AI Agent. Google Sheets Credentials: For reading/writing the final compiled digest. Target Google Sheet: A spreadsheet with the following columns: Date, URL, Subject, Brief Summary, and What is Important. How to set up Credentials Setup:** Connect your Google Gemini and Google Sheets accounts via the n8n Credentials Manager. Google Sheet Linking:* In the *Append row in sheet and Append row in sheet in Google Sheets1 nodes, replace the **placeholder IDs and GIDs with the actual ID and sheet name of your dedicated UPSC notes spreadsheet. Scheduling:* Adjust the time in the *Schedule Trigger: Daily at 7 AM node** if you want the daily analysis to run at a different hour. AI Customization (Optional):* You can refine the System Message in the *AI Agent: Filter & Analyze UPSC News node** to focus the analysis on specific exam phases (e.g., Prelims only) or adjust the priority of subjects.

SEO Content Generation Workflow (Basic Version) - n8n Template Instructions Who's it for This workflow is designed for SEO professionals, content marketers, digital agencies, and businesses who need to generate optimized meta tags, H1 headings, and content briefs at scale. Perfect for teams managing multiple clients or large keyword lists who want to automate competitor analysis and SEO content creation without the complexity of vector databases. How it works The workflow automates the entire SEO content creation process by analyzing your target keywords against top competitors, then generating optimized meta elements and comprehensive content briefs. It uses AI-powered analysis combined with real competitor data to create SEO-friendly content that's tailored to your specific business context. The system processes keywords in batches, performs Google searches, scrapes competitor content, analyzes heading structures, and generates personalized SEO content using your company information for maximum relevance. Requirements Required Services and Credentials Google Sheets API**: For reading configuration and updating results Anthropic API**: For AI content generation (Claude Sonnet 4) Apify API**: For Google search results Firecrawl API**: For competitor website scraping Template Spreadsheet Copy this template spreadsheet and configure it with your information: Template Link How to set up Step 1: Copy and Configure Template Make a copy of the template spreadsheet Fill in the Client Information sheet: Client name: Your company or client's name Client information: Brief business description URL: Website address Tone of voice: Content style preferences Restrictive instructions: Topics or approaches to avoid Complete the SEO sheet with your target pages: Page: Page you're optimizing (e.g., "Homepage", "Product Page") Keyword: Main search term to target Awareness level: User familiarity with your business Page type: Category (homepage, blog, product page, etc.) Step 2: Import Workflow Import the n8n workflow JSON file Configure all required API credentials in n8n: Google Sheets OAuth2 Anthropic API key Apify API key Firecrawl API key Step 3: Test Configuration Activate the workflow Send your Google Sheets URL to the chat trigger Verify that all sheets are readable and credentials work Test with a single keyword row first Workflow Process Overview Phase 0: Setup and Configuration Copy template spreadsheet Configure client information and SEO parameters Set up API credentials in n8n Phase 1: Data Input and Processing Chat trigger receives Google Sheets URL System reads client configuration and SEO data Filters valid keywords and empty H1 fields Initiates batch processing Phase 2: Competitor Research and Analysis Searches Google for top 10 results per keyword using Apify Scrapes first 5 competitor websites using Firecrawl Extracts heading structures (H1-H6) from competitor pages Analyzes competitor meta tags and content organization Processes markdown content to identify heading hierarchies Phase 3: Meta Tags and H1 Generation AI analyzes keyword context and competitor data using Claude Incorporates client information for personalization Generates optimized meta title (65 characters maximum) Creates compelling meta description (165 characters maximum) Produces user-focused H1 (70 characters maximum) Uses structured output parsing for consistent formatting Phase 4: Content Brief Creation Analyzes search intent percentages (informational, transactional, navigational) Develops content strategy based on competitor analysis Creates detailed MECE page structure with H2 and H3 sections Suggests rich media elements (images, videos, infographics, tables) Provides writing recommendations and detail level scoring (1-10 scale) Ensures SEO optimization while maintaining user relevance Phase 5: Data Integration and Updates Combines all generated content into unified structure Updates Google Sheets with new SEO elements Preserves existing data while adding new content Continues batch processing for remaining keywords Key Differences from Advanced Version This basic version focuses on core SEO functionality without additional complexity: No Vector Database**: Removes Supabase integration for simpler setup Streamlined Architecture**: Fewer dependencies and configuration steps Essential Features Only**: Core competitor analysis and content generation Faster Setup**: Reduced time to deployment Lower Costs**: Fewer API services required How to customize the workflow Adjusting AI Models Replace Anthropic Claude with other LLM providers in the agent nodes Modify system prompts for different content styles or languages Adjust character limits for meta elements in the structured output parser Modifying Competitor Analysis Change number of competitors analyzed (currently 5) by adding/removing Scrape nodes Adjust scraping parameters in Firecrawl nodes for different content types Modify heading extraction logic in JavaScript Code nodes Customizing Output Format Update Google Sheets column mapping in the final Code node Modify structured output parser schema for different data structures Change batch processing size in Split in Batches node Adding Quality Controls Insert validation nodes between workflow phases Add error handling and retry logic to critical nodes Implement content quality scoring mechanisms Extending Functionality Add keyword research capabilities with additional APIs Include image optimization suggestions Integrate social media content generation Connect to CMS platforms for direct publishing Best Practices Setup and Testing Always test with small batches before processing large keyword lists Monitor API usage and costs across all services Regularly update system prompts based on output quality Maintain clean data in your Google Sheets template Content Quality Review generated content before publishing Customize system prompts to match your brand voice Use descriptive node names for easier workflow maintenance Keep competitor analysis current by running regularly Performance Optimization Process keywords in small batches to avoid timeouts Set appropriate retry policies for external API calls Monitor workflow execution times and optimize bottlenecks Troubleshooting Common Issues and Solutions API Errors Check credential configuration in n8n settings Verify API usage limits and billing status Ensure proper authentication for each service Scraping Failures Firecrawl nodes have error handling enabled to continue on failures Some websites may block scraping - this is normal behavior Check if competitor URLs are accessible and valid Empty Results Verify keyword formatting in Google Sheets Ensure competitor websites contain the expected content structure Check if meta tags are properly formatted in system prompts Sheet Update Errors Ensure proper column mapping in final Code node Verify Google Sheets permissions and sharing settings Check that target sheet names match exactly Processing Stops Review batch processing limits and timeout settings Check for errors in individual nodes using execution logs Verify all required fields are populated in input data Template Structure Required Sheets Client Information: Business details and configuration SEO: Target keywords and page information Results Sheet: Where generated content will be written Expected Columns Keywords**: Target search terms Description**: Brief page description Type de page**: Page category Awareness level**: User familiarity level title, meta-desc, h1, brief**: Generated output columns This streamlined version provides all essential SEO content generation capabilities while being easier to set up and maintain than the advanced version with vector database integration.

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 1. Start Simple Begin with 3-5 main intents Add more as you see common patterns Don't over-complicate the initial setup 2. Monitor and Iterate Review conversations weekly Identify missed intents Refine pattern matching Update product information regularly 3. 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 4. Optimize Response Times Pre-built responses are instant AI responses take 2-5 seconds Set user expectations ("Let me check that for you...") 5. Test Different Scenarios Happy path (normal inquiries) Edge cases (misspellings, slang) Multi-turn conversations Multiple topics in one message 6. Keep Responses Concise WhatsApp users prefer short messages Use formatting (bold, bullets) for readability Break long responses into multiple messages 7. Maintain Brand Voice Customize AI system prompt with your brand personality Use consistent tone across all responses Include brand-appropriate emojis 8. Handle Failures Gracefully Add error handling for API failures Have fallback responses ready Always offer human contact option 9. Respect Privacy Don't store sensitive information Comply with GDPR/local privacy laws Allow users to delete their data 10. 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.

How it works This workflow enriches and personalizes your lead profiles by integrating HubSpot contact data, scraping social media information, and using AI to generate tailored outreach emails. It streamlines the process from contact capture to sending a personalized email — all automatically. The system fetches new or updated HubSpot contacts, verifies and enriches their Twitter/LinkedIn data via Phantombuster, merges the profile and engagement insights, and finally generates a customized email ready for outreach. Step-by-step 1. Trigger & Input HubSpot Contact Webhook: Fires when a contact is created or updated in HubSpot. Fetch Contact: Pulls the full contact details (email, name, company, and social profiles). Update Google Sheet: Logs Twitter/LinkedIn usernames and marks their tracking status. 2. Validation Validate Twitter/LinkedIn Exists: Checks if the contact has a valid social profile before proceeding to scraping. 3. Social Media Scraping (via Phantombuster) Launch Profile Scraper & 🎯 Launch Tweet Scraper: Triggers Phantombuster agents to fetch profile details and recent tweets. Wait Nodes: Ensures scraping completes (30–60 seconds). Fetch Profile/Tweet Results: Retrieves output files from Phantombuster. Extract URL: Parses the job output to extract the downloadable .json or .csv data file link. 4. Data Download & Parsing Download Profile/Tweet Data: Downloads scraped JSON files. Parse JSON: Converts the raw file into structured data for processing. 5. Data Structuring & Merging Format Profile Fields: Maps stats like bio, followers, verified status, likes, etc. Format Tweet Fields: Captures tweet data and associates it with the lead’s email. Merge Data Streams: Combines tweet and profile datasets. Combine All Data: Produces a single, clean object containing all relevant lead details. 6. AI Email Generation & Delivery Generate Personalized Email: Feeds the merged data into OpenAI GPT (via LangChain) to craft a custom HTML email using your brand details. Parse Email Content: Cleans AI output into structured subject and body fields. Sends Email: Automatically delivers the personalized email to the lead via Gmail. Benefits Automated Lead Enrichment — Combines CRM and real-time social media data with zero manual research. Personalized Outreach at Scale — AI crafts unique, relevant emails for each contact. Improved Engagement Rates — Targeted messages based on actual social activity and profile details. Seamless Integration — Works directly with HubSpot, Google Sheets, Gmail, and Phantombuster. Time & Effort Savings — Replaces hours of manual lookup and email drafting with an end-to-end automated flow.

This template crawls a website from its sitemap, deduplicates URLs in Supabase, scrapes pages with Crawl4AI, cleans and validates the text, then stores content + metadata in a Supabase vector store using OpenAI embeddings. It’s a reliable, repeatable pipeline for building searchable knowledge bases, SEO research corpora, and RAG datasets. ⸻ Good to know • Built-in de-duplication via a scrape_queue table (status: pending/completed/error). • Resilient flow: waits, retries, and marks failed tasks. • Costs depend on Crawl4AI usage and OpenAI embeddings. • Replace any placeholders (API keys, tokens, URLs) before running. • Respect website robots/ToS and applicable data laws when scraping. How it works Sitemap fetch & parse — Load sitemap.xml, extract all URLs. De-dupe — Normalize URLs, check Supabase scrape_queue; insert only new ones. Scrape — Send URLs to Crawl4AI; poll task status until completed. Clean & score — Remove boilerplate/markup, detect content type, compute quality metrics, extract metadata (title, domain, language, length). Chunk & embed — Split text, create OpenAI embeddings. Store — Upsert into Supabase vector store (documents) with metadata; update job status. Requirements • Supabase (Postgres + Vector extension enabled) • Crawl4AI API key (or header auth) • OpenAI API key (for embeddings) • n8n credentials set for HTTP, Postgres/Supabase How to use Configure credentials (Supabase/Postgres, Crawl4AI, OpenAI). (Optional) Run the provided SQL to create scrape_queue and documents. Set your sitemap URL in the HTTP Request node. Execute the workflow (manual trigger) and monitor Supabase statuses. Query your documents table or vector store from your app/RAG stack. Potential Use Cases This automation is ideal for: Market research teams collecting competitive data Content creators monitoring web trends SEO specialists tracking website content updates Analysts gathering structured data for insights Anyone needing reliable, structured web content for analysis Need help customizing? Contact me for consulting and support: LinkedIn

This workflow is designed for B2B professionals to automatically identify and summarize business opportunities from a company's website. By leveraging Bright Data's Web Unblocker and advanced AI models from OpenRouter, it scrapes relevant company pages ("About Us", "Team", "Contact"), analyzes the content for potential pain points and needs, and synthesizes a concise, actionable report. The final output is formatted for direct use in documents, making it an ideal tool for sales, marketing, and business development teams to prepare for prospecting calls or personalize outreach. Who's it for This template is ideal for: B2B Sales Teams:** Quickly find and qualify leads by identifying specific business needs before a cold call. Marketing Agencies:** Develop personalized content and value propositions based on a prospect's public website information. Business Development Professionals:** Efficiently research potential partners or clients and discover collaboration opportunities. Entrepreneurs:** Gain a competitive edge by understanding a competitor's strategy or a potential client's operations. How it works The workflow is triggered by a chat message, typically a URL from an n8n chat application. It uses Bright Data to scrape the website's sitemap and extract all anchor links from the homepage. An AI agent analyzes the extracted URLs to filter for pages relevant to company information (e.g., "about-us," "team," "contact"). The workflow then scrapes the content of these specific pages. A second AI agent summarizes the content of each page, looking for business opportunities related to AI-powered automation. The summaries are merged and a final AI agent synthesizes them into a single, cohesive report, formatted for easy reading in a Google Doc. How to set up Bright Data Credentials: Sign up for a Bright Data account and create a Web Unblocker zone. In n8n, create new Bright Data API credentials and copy your API key. OpenRouter Credentials: Create an account on OpenRouter and get your API key. In n8n, create new OpenRouter API credentials and paste your key. Chat Trigger Node: Configure the "When chat message received" node. Copy the production webhook URL to integrate with your preferred chat platform. Requirements An active n8n instance. A Bright Data account with a Web Unblocker zone. An OpenRouter account with API access. How to customize this workflow AI Prompting:** Edit the "systemMessage" parameters in the "AI Agent", "AI Agent1", and "AI Agent2" nodes to change the focus of the opportunity analysis. For example, modify the prompts to search for specific technologies, industry jargon, or different types of business challenges. Model Selection:** The workflow uses openai/o4-mini and openai/gpt-5. You can change these to other models available on OpenRouter by editing the model parameter in the OpenRouter Chat Model nodes. Scraping Logic:** The extract url node uses a regular expression to find `` tags. This can be modified or replaced with an HTML Extraction node to target different elements or content on a website. Output Format:** The final output is designed for Google Docs. You can modify the last "AI Agent2" node's prompt to generate the output in a different format, such as a simple JSON object or a markdown list. Phil | Inforeole 🇫🇷 Contactez nous pour automatiser vos processus

Your Cold Email is Now Researched. This pipeline finds specific bottlenecks on prospect websites and instantly crafts an irresistible pitch 🎯 Problem Statement Traditional high-volume cold email outreach is stuck on generic personalization (e.g., "Love your website!"). Sales teams, especially those selling high-value AI Receptionists, struggle to efficiently find the one Unique Operational Hook (like manual scheduling dependency or high call volume) needed to make the pitch relevant. This forces reliance on expensive, slow manual research, leading to low reply rates and inefficient spending on bulk outreach tools. ✨ Solution This workflow deploys a resilient Dual-AI Personalization Pipeline that runs on a batch basis. It uses the Filter (Qualified Leads) node as a cost-saving Quality Gate to prevent processing bad leads. It executes a Targeted Deep Dive on successful leads, using GPT-4 for analytical insight extraction and Claude Sonnet for coherent, human-like copy generation. The entire process outputs campaign-ready data directly to Google Sheets and sends a critical QA Draft via Gmail. ⚙️ How It Works (Multi-Step Execution) 1\. Ingestion and Cost Control (The Quality Gate) Trigger and Ingestion:* The workflow starts via a *Manual Trigger, pulling leads directly from **Get All Leads (Google Sheets). Cost Filtering:* The *Filter (Qualified Leads)** node removes leads that lack a working email or website URL. Execution Isolation:* The *Loop Over Leads* node initiates individual processing. The *Capture Lead Data (Set)** node immediately captures and locks down the original lead context for stability throughout the loop. Hybrid Scraping:* The *Scrape Site (HTTP Request)* and *Extract Text & Links (HTML)* nodes execute the *Hybrid Scraping* strategy, simultaneously capturing *website text* and *external links**. Data Shaping & Status:* The *Filter Social & Status (Code)* node is the control center. It filters links, bundles the context, and critically, assigns a *status** of 'Success' or 'Scrape Fail'. Cost Control Branch:* The *If (IF node)* checks this status. Items with 'Scrape Fail' bypass all AI steps (saving *100% of AI token costs) and jump directly to **Log Final Result. Successful items proceed to the AI core. 2\. Dual-AI Coherence & Dispatch (The Executive Output) Analytical Synthesis:* The *Summarize Website (OpenAI)* node uses *GPT-4* to synthesize the full context and extract the *Unique Operational Hook** (e.g., manual booking overhead). Coherent Copy Generation:* The *Generate Subject & Body (Anthropic)* node uses the *Claude Sonnet* model to generate the subject and the multi-line body, guaranteeing *coherence** by creating both simultaneously in a single JSON output. Final Parsing:* The *Parse AI Output (Code)* node reliably strips markdown wrappers and extracts the clean *subject* and *body** strings. Final Delivery:* The data is logged via *Log Final Result (Google Sheets), and the completed email is sent to the user via **Create a draft (Gmail) for final Quality Assurance before sending. 🛠️ Setup Steps Before running the workflow, ensure these credentials and data structures are correctly configured: Credentials Anthropic:** Configure credentials for the Language Model (Claude Sonnet). OpenAI:** Configure credentials for the Analytical Model (GPT-4/GPT-4o). Google Services:* Set up OAuth2 credentials for *Google Sheets* (Input/Output) and *Gmail** (Draft QA and Completion Alert). Configuration Google Sheet Setup:* Your input sheet must include the columns *email, **website\_url, and an empty Icebreaker column for initial filtering. HTTP URL:* Verify that the *Scrape Site** node's URL parameter is set to pull the website URL from the stabilized data structure: ={{ $json.website\_url }}. AI Prompts:** Ensure the Anthropic prompt contains your current Irresistible Sales Offer and the required nested JSON output structure. ✅ Benefits Coherence Guarantee:* A single *Anthropic** node generates both the subject and body, guaranteeing the message is perfectly aligned and hits the same unique insight. Maximum Cost Control:* The *IF node* prevents spending tokens on bad or broken websites, making the campaign highly *budget-efficient**. Deep Personalization:* Combines *website text* and *social media links**, creating an icebreaker that implies thorough, manual research. High Reliability:* Uses robust *Code nodes** for data structuring and parsing, ensuring the workflow runs consistently under real-world conditions without crashing. Zero-Risk QA:* The final *Gmail (Create a draft)** step ensures human review of the generated copy before any cold emails are sent out.

Categorise and route emails with GPT 5 This workflow demonstrates how to use AI text classifier to classify incoming emails, and uses a multi-agent architecture to respond for each email category respectively. Use cases Business owners with a lot of incoming emails, or anyone who has huge influx of emails How it Works Any incoming emails will be read by the text classifier powered by GPT 5, and routed according to the defined categories where respective agents will take next steps. Workflow is triggered when an email comes in GPT will read email's "subject","from" and "content" to route it accurately to respective designated categories For customer support enquiries, customer support agent will take knowledge from the pinecone vector database about FAQs and policies, reply via gmail, and label the email as "Customer Support" For finance-related queries, finance agent will label email as "Finance" and assess if email is about making payment or receiving from customers. If payment-related, email will be sent to the payments team to take action. If receipts-related, email will be sent to the receivables team to take action. User will be notified via telegram after any email is sent. For sales/leads enquiries, leads agent will label the email as "Sales Opportunities", take knowledge from the pinecone vector database about the business to generate a response and draft into gmail and user will be notified via telegram to review and send. If there is lack of information for agent to generate a response, user will be notified of this via telegram as well. Any internal team member emails will be routed to the internal agent. The agent will label message as "Internal" and send user a summary of the email message via telegram. How to set up Set up Telegram bot via Botfather. See setup instructions here Setup OpenAI API for transcription services (Credits required) here Set up Openrouter account. See details here Set up Pinecone database. See details here Customization Options Other than Gmail, it is possible to connect to Outlook as well. Other than Pinecone vector database, there are other vector database that should serve the same purpose eg. supabase, qdrant, weviate Requirements Gmail account Telegram bot Pinecone account Open router account