Workflow Templates

This workflow contains community nodes that are only compatible with the self-hosted version of n8n. Intelligent Document Monitoring and Alert System This workflow creates an automated monitoring system that watches for new PDF reports across multiple sources, extracts key insights using AI, and sends formatted alerts to your team via Slack or email. By combining PDF Vector's parsing capabilities with GPT-powered analysis, teams can stay informed about critical documents without manual review, ensuring important information never gets missed. Target Audience & Problem Solved This template is designed for: Finance teams** monitoring quarterly reports and regulatory filings Compliance officers** tracking policy updates and audit reports Research departments** alerting on new publications and preprints Operations teams** monitoring supplier reports and KPI documents Executive assistants** summarizing board materials and briefings It solves the problem of information overload by automatically processing incoming documents, extracting only the most relevant insights, and delivering them in digestible formats to the right people at the right time. Prerequisites n8n instance with PDF Vector node installed PDF Vector API credentials with parsing capabilities OpenAI API key for insight extraction Slack workspace admin access (for Slack alerts) SMTP credentials (for email alerts) FTP/Cloud storage access for document sources Minimum 50 API credits for continuous monitoring Step-by-Step Setup Instructions Configure Document Sources Set up FTP credentials in n8n for folder monitoring Or configure Google Drive/Dropbox integration Define the folder paths to monitor Set file naming patterns to watch (e.g., "report.pdf") Set Up API Integrations Add PDF Vector credentials in n8n Configure OpenAI credentials with appropriate model access Set up Slack app and add webhook URL Configure SMTP settings for email alerts Configure Monitoring Schedule Open the "Check Every 15 Minutes" node Adjust frequency based on your needs: // For hourly checks: "interval": 60 // For real-time monitoring (every 5 min): "interval": 5 Customize Alert Channels Slack Setup: Create dedicated channels (#reports, #alerts) Configure webhook for each channel Set up user mentions for urgent alerts Email Setup: Define recipient lists by document type Configure email templates Set up priority levels for subject lines Define Alert Rules Modify the "Extract Key Insights" prompt for your domain Set conditions for high-priority alerts Configure which metrics trigger notifications Define sentiment thresholds Implementation Details The workflow implements a comprehensive monitoring pipeline: Source Monitoring: Polls multiple sources for new PDFs Intelligent Parsing: Uses LLM-enhanced parsing for complex documents Insight Extraction: AI analyzes content for key information Priority Classification: Determines alert urgency based on content Multi-Channel Delivery: Sends formatted alerts via configured channels Audit Trail: Logs all processed documents for compliance Customization Guide Adding Custom Document Types: Extend the routing logic for specific document types: // In "Route by Document Type" node: const documentTypes = { 'invoice': /invoice|bill|payment/i, 'contract': /contract|agreement|terms/i, 'report': /report|analysis|summary/i, 'compliance': /audit|compliance|regulatory/i }; Customizing Insight Extraction: Modify the AI prompt for domain-specific analysis: // Financial documents: "Extract: 1) Revenue figures 2) YoY growth 3) Risk factors 4) Guidance changes" // Compliance documents: "Extract: 1) Policy changes 2) Deadlines 3) Required actions 4) Penalties" // Research papers: "Extract: 1) Key findings 2) Methodology 3) Implications 4) Future work" Advanced Alert Formatting: Create rich Slack messages with interactive elements: // Add buttons for quick actions: { "type": "actions", "elements": [ { "type": "button", "text": { "type": "plain_text", "text": "View Full Report" }, "url": documentUrl }, { "type": "button", "text": { "type": "plain_text", "text": "Mark as Read" }, "action_id": "mark_read" } ] } Implementing Alert Conditions: Add sophisticated filtering based on content: // Alert only if certain conditions are met: if (insights.metrics.revenue_change < -10) { priority = 'urgent'; alertChannel = '#executive-alerts'; } if (insights.findings.includes('compliance violation')) { additionalRecipients.push('legal@company.com'); } Adding Document Comparison: Track changes between document versions: // Compare with previous version: const previousDoc = await getLastVersion(documentType); const changes = compareDocuments(previousDoc, currentDoc); if (changes.significant) { alertMessage += \n⚠️ Significant changes detected: ${changes.summary}; } Alert Features: Monitor multiple document sources (FTP, cloud storage, email) Extract key metrics and findings with AI Send rich, formatted notifications Track document processing history Conditional alerts based on content analysis Multi-channel alert routing Use Cases: Financial report monitoring Compliance document tracking Research publication alerts Customer report distribution Board material summarization Regulatory filing notifications Advanced Configuration Performance Optimization: Implement caching to avoid reprocessing Use batch processing for multiple documents Set up parallel processing for different sources Security Considerations: Encrypt sensitive document storage Implement access controls for different alert channels Audit log all document access

Advanced Form Submission to CRM Automation with International Phone Support Who's it for Sales teams, marketing professionals, and business owners who need sophisticated lead management with international phone number support, automated CRM record creation, intelligent duplicate detection, and multi-channel team notifications. What it does This advanced workflow automatically processes form submissions from your website and creates a complete, intelligent CRM structure in Pipedrive. It transforms raw form data into organized sales records including companies, contacts, deals, and relevant notes while handling international phone number formatting and providing real-time team notifications via Discord and WhatsApp messaging. How it works The workflow follows an intelligent automation process with four distinct scenarios: Form Trigger: Captures form submissions from your website (Webflow in this example) Advanced Phone Processing: Automatically detects and formats international phone numbers with proper country codes for 20+ countries including France, Belgium, Switzerland, Germany, Spain, Italy, Morocco, Algeria, Tunisia, and more Intelligent CRM Logic: Uses a sophisticated 4-scenario approach: Scenario A: Existing Organization + Existing Person - Links records and creates new deal Scenario B: Existing Organization + New Person - Creates person, links to organization, creates deal Scenario C: New Organization + Existing Person - Creates organization, links person, creates deal Scenario D: New Organization + New Person - Creates complete new structure from scratch Enhanced Data Management: Adds lead source tracking, custom properties, and conditional data enhancement Multi-Channel Communication: Sends formatted alerts to Discord and personalized WhatsApp messages to leads Requirements Webflow account (or any platform that supports webhook triggers) Pipedrive CRM account with proper API credentials Team notification service: Discord, Slack, Microsoft Teams, email service, or any webhook-compatible notification tool WhatsApp Business API access for lead messaging International phone number handling capability How to set up Step 1: Configure your form trigger Default setup: The template uses Webflow Form Trigger with site ID configuration Alternative platforms: Replace with webhook trigger for other platforms (WordPress, custom websites, etc.) Webhook configuration: Set up your website's form to send data to the n8n webhook URL Form fields: Ensure your form captures the necessary fields: Prénom (First Name) Nom (Last Name) Entreprise (Company) Mail professionnel (Professional Email) Téléphone pro (Professional Phone) URL du site internet (Website URL) Message Step 2: Configure API credentials Set up the following credentials in n8n: Webflow OAuth2: For form trigger authentication (or webhook authentication for other platforms) Pipedrive API: For CRM record creation and management - ensure proper permissions for organizations, persons, deals, and notes Discord Bot API: For team notifications with guild and channel access WhatsApp Business API: For automated lead messaging with phone number ID configuration Step 3: Customize international phone formatting The "international dialing code" node automatically handles: European countries: France (+33), Belgium (+32), Switzerland (+41), Germany (+49), Spain (+34), Italy (+39), Portugal (+351) North African countries: Morocco (+212), Algeria (+213), Tunisia (+216) Global coverage: US/Canada (+1), UK (+44), and many Asian countries Fallback handling: Defaults to French formatting for unrecognized patterns Error management: Uses +330000000000 as fallback for invalid numbers Step 4: Configure Pipedrive settings Adjust Pipedrive-specific settings in deal creation nodes: Deal pipeline stage: Currently set to default stage (customize for your pipeline) Deal ownership: Configure owner_id for appropriate team member assignment Currency settings: Adjust currency code for your business region Custom properties: Lead source automatically set to "Growth AI" (customize as needed) Step 5: Set up team notifications Configure your preferred notification system: Discord (default): Set guild ID: 1377297267014504520, channel ID: 1380469490139009106 Alternative platforms: Replace Discord node with Slack, Teams, email, or custom webhook Message formatting: Customize notification content and structure Multi-channel setup: Add multiple notification nodes for different channels Step 6: Configure WhatsApp messaging Set up automated lead engagement: Phone number ID: Configure WhatsApp Business API phone number (currently: 752773604591912) Message personalization: Uses prospect's first name and customizable content International compatibility: Works with formatted international phone numbers Message templates: Customize welcome messages and follow-up content How to customize the workflow Form platform integration Webflow: Use the existing Webflow trigger with site ID configuration WordPress: Replace with webhook trigger and configure Contact Form 7, Gravity Forms, or WPForms Custom websites: Set up webhook trigger with your form's POST endpoint Landing page builders: Configure webhook integration (Unbounce, Leadpages, Instapage, etc.) Form field mapping: Adjust the "Data refinement" node for your specific form structure Advanced CRM customization Pipeline management: Configure different stage IDs for various lead sources Lead scoring: Add conditional logic for deal values based on form responses Custom fields: Map additional form fields to Pipedrive custom properties Multiple pipelines: Route different form types to different sales pipelines Ownership rules: Implement round-robin or territory-based assignment logic International phone number expansion The phone formatting system supports extensive customization: Additional countries: Add new country patterns to the JavaScript code Regional preferences: Modify default formatting rules for specific regions Validation rules: Implement stricter phone number validation Carrier detection: Add mobile vs. landline detection logic Notification enhancements Multi-platform notifications: Send to Discord, Slack, Teams, and email simultaneously Conditional notifications: Route different lead types to different channels Rich formatting: Add embeds, attachments, or rich text formatting Escalation rules: Implement priority-based notification routing Integration expansion: Connect to internal tools or third-party notification services Data validation and enrichment Email validation: Add email verification steps before CRM creation Company enrichment: Integrate with data enrichment services (Clearbit, ZoomInfo, Apollo) Duplicate detection: Enhanced logic to check for existing contacts across multiple fields Lead qualification: Implement sophisticated scoring based on form responses and external data Data cleaning: Add standardization for company names, job titles, and other fields Advanced conditional logic features Intelligent scenario routing The workflow uses sophisticated logic to determine the correct processing path: Organization detection: Exact matching search for existing companies Person identification: Full name matching within relevant organization contexts Relationship preservation: Maintains proper links between organizations, persons, and deals Data consistency: Ensures no duplicate records while preserving historical relationships Smart data handling Enhanced conditional processing includes: Phone number intelligence: Automatic international formatting with country detection Message processing: Creates deal notes only when message field contains meaningful content URL handling: Adds website URLs as separate notes when provided Empty field management: Gracefully handles incomplete form submissions Custom property management: Adds lead source tracking and other metadata Error handling and resilience Graceful failures: Workflow continues even if individual steps fail Data validation: Comprehensive checks for required fields before processing Notification reliability: Ensures team is notified even if some CRM operations fail Logging capabilities: Detailed error tracking for troubleshooting Rollback mechanisms: Ability to handle partial failures without data corruption Results interpretation CRM structure created For each form submission, the workflow creates: Organization record: Complete company information with proper formatting Person record: Contact information linked to correct organization with phone formatting Deal record: Sales opportunity with appropriate stage, owner, and metadata Enhanced notes: Separate notes for messages and website URLs when provided Proper relationships: Full linking between organization, person, and deal records Custom tracking: Lead source attribution and other custom properties Team notifications and engagement Comprehensive communication includes: Discord notifications: Formatted team alerts with complete prospect information WhatsApp engagement: Personalized messages to leads with international number support Immediate alerts: Real-time notifications for instant follow-up capability Formatted display: Clean, organized presentation of all prospect data Multi-channel flexibility: Easy adaptation to any notification platform Advanced use cases International lead generation Global forms: Handle submissions from multiple countries with proper phone formatting Multi-language support: Process forms in different languages with consistent data structure Regional routing: Route leads to appropriate regional sales teams based on phone country codes Currency handling: Automatic currency assignment based on detected country Sophisticated lead management Lead scoring: Advanced qualification based on company size, industry, and message content Progressive profiling: Build complete prospect profiles over multiple interactions Engagement tracking: Monitor response rates and optimize messaging Attribution analysis: Track lead sources and optimize marketing spend Enterprise integration Custom CRM fields: Map to complex Pipedrive custom field structures Multiple pipelines: Route leads to different sales processes based on criteria Team assignment: Intelligent routing based on territory, expertise, or workload Compliance handling: Ensure data processing meets regional privacy requirements Workflow architecture details Processing phases Form capture and data extraction: Webflow trigger processes submitted data International phone formatting: Advanced JavaScript processing for global numbers Organization discovery: Intelligent search and creation logic Person management: Sophisticated duplicate detection and relationship management Deal creation: Context-aware opportunity generation with proper associations Enhanced communication: Multi-channel notifications and lead engagement Performance characteristics Processing time: Typically completes within 10-15 seconds for complex scenarios Reliability: Built-in error handling ensures high success rates Scalability: Handles high-volume form submissions without performance degradation Flexibility: Easy customization for different business requirements and CRM configurations Limitations and considerations Platform dependencies: Currently optimized for Webflow and Pipedrive but adaptable Phone number coverage: Supports 20+ countries but may need expansion for specific regions CRM limitations: Requires proper Pipedrive API permissions and rate limit considerations Form structure: Field mapping requires customization for different form designs Language considerations: Currently configured for French field names but easily adaptable Notification dependencies: Requires proper configuration of Discord and WhatsApp APIs for full functionality

This workflow transforms your Meta Ads creatives into a rich dataset of actionable insights. It's designed for data-driven marketers, performance agencies, and analysts who want to move beyond basic metrics and understand the specific visual and textual elements that drive ad performance. By automatically analyzing every video and image with Google's powerful AI (Video Intelligence and Vision APIs), it systematically deconstructs your creatives into labeled data, ready for correlation with campaign results. Use Case You know some ads perform better than others, but do you know why? Is it the presence of a person, a specific object, the on-screen text, or the spoken words in a video? Answering these questions manually is nearly impossible at scale. This workflow automates the deep analysis process, allowing you to: Automate Creative Analysis:** Stop guessing and start making data-backed decisions about your creative strategy. Uncover Hidden Performance Drivers:** Identify which objects, themes, text, or spoken phrases correlate with higher engagement and conversions. Build a Structured Creative Database:** Create a detailed, searchable log of every element within your ads for long-term analysis and trend-spotting. Save Countless Hours:** Eliminate the tedious manual process of watching, tagging, and logging creative assets. How it Works The workflow is triggered on a schedule and follows a clear, structured path: 1. Configuration & Ad Ingestion: The workflow begins on a schedule (e.g., weekly on Monday at 10 AM). It starts by fetching all active ads from a specific Meta Ads Campaign, which you define in the Set Campaign ID node. 2. Intelligent Branching (Video vs. Image): An IF node inspects each creative to determine its type. Video creatives** are routed to the Google Video Intelligence API pipeline. Image creatives** are routed to the Google Vision API pipeline. 3. The Video Analysis Pipeline: For each video, the workflow gets a direct source URL, downloads the file, and converts it to a Base64 string. It then initiates an asynchronous analysis job in the Google Video Intelligence API, requesting LABEL_DETECTION, SPEECH_TRANSCRIPTION, and TEXT_DETECTION. A loop with a wait timer periodically checks the job status until the analysis is complete. Finally, a Code node parses the complex JSON response, structuring the annotations (like detected objects with timestamps or full speech transcripts) into clean rows. 4. The Image Analysis Pipeline: For each image, the file is downloaded, converted to Base64, and sent to the Google Vision API. It requests a wide range of features, including label, text, logo, and object detection. A Code node parses the response and formats the annotations into a standardized structure. 5. Data Logging & Robust Error Handling: All successfully analyzed data from both pipelines is appended to a primary Google Sheet. The workflow is built to be resilient. If an error occurs (e.g., a video fails to be processed by the API, or an image URL is missing), a detailed error report is logged to a separate errors sheet in your Google Sheet, ensuring no data is lost and problems are easy to track. Setup Instructions To use this template, you need to configure a few key nodes. 1. Credentials: Connect your Meta Ads account. Connect your Google account. This account needs access to Google Sheets and must have the Google Cloud Vision API and Google Cloud Video Intelligence API enabled in your GCP project. 2. The Set Campaign ID Node: This is the primary configuration step. Open this Set node and replace the placeholder value with the ID of the Meta Ads campaign you want to analyze. 3. Google Sheets Nodes: You need to configure two Google Sheets nodes: Add Segments data:** Select your spreadsheet and the specific sheet where you want to save the successful analysis results. Ensure your sheet has the following headers: campaign_id, ad_id, creative_id, video_id, file_name, image_url, source, annotation_type, label_or_text, category, full_transcript, confidence, start_time_s, end_time_s, language_code, processed_at_utc. Add errors:** Select your spreadsheet and the sheet you want to use for logging errors (e.g., a sheet named "errors"). Ensure this sheet has headers like: error_type, error_message, campaign_id, ad_id, creative_id, file_name, processed_at_utc. 4. Activate the Workflow: Set your desired frequency in the Run Weekly on Monday at 10 AM (Schedule Trigger) node. Save and activate the workflow. Further Ideas & Customization This workflow provides the "what" inside your creatives. The next step is to connect it to performance. Build a Performance Analysis Workflow:** Create a second workflow that reads this Google Sheet, fetches performance data (spend, clicks, conversions) for each ad_id from the Meta Ads API, and merges the two datasets. This will allow you to see which labels correlate with the best performance. Create Dashboards:** Use the structured data in your Google Sheet as a source for a Looker Studio or Tableau dashboard to visualize creative trends. Incorporate Generative AI:** Add a final step that sends the combined performance and annotation data to an LLM (like in the example you provided) to automatically generate qualitative summaries and recommendations for each creative. Add Notifications:** Use the Slack or Email nodes to send a summary after each run, reporting how many creatives were analyzed and if any errors occurred.

How it works This workflow automatically monitors competitor product prices stored in Google Sheets. It scrapes product pages, extracts pricing and offer data using AI, and compares it with historical values. Based on changes, it updates records and generates a market intelligence report. The workflow then emails the report and resets data for the next execution cycle. Step-by-step Step 1: Database sync** Schedule Trigger – Runs the workflow at a scheduled time. Get row(s) in sheet – Fetches competitor data and product URLs. Step 2: Scraping** Loop Over Items – Processes each competitor entry. HTTP Request3 – Retrieves raw HTML using ScraperAPI. Clean Content – Cleans and prepares text for AI processing. Step 3: Price extraction** AI Agent1 – Extracts product name, price, and offers. Groq Chat Model1 – Provides AI extraction capability. current Price and offer – Converts AI output into structured data. If2 – Checks if it's the first recorded entry. First time price and offer added – Stores initial values. If1 – Compares current vs previous price and offers. Updated current price and offer in sheet – Updates if changes detected. If No changes then update – Updates sheet even when no change is found. Step 4: Analysis** Get row(s) in sheet1 – Retrieves updated dataset. Data Aggregator – Builds structured market comparison data. AI Agent – Generates strategic insights and recommendations. Groq Chat Model – Powers the analysis output. Update row in sheet – Saves AI-generated summary in sheet. Step 5: Reporting** Edit Fields1 – Formats the report into HTML email layout. Send a message – Sends the final report via Gmail. Step 6: Reset** Get row(s) in sheet2 – Retrieves final processed data. Update row in sheet1 – Moves current data to history and clears fields. Why use this? Ensures all price scenarios (change or no change) are handled properly Keeps your Google Sheets always updated with accurate data Provides AI-powered competitive intelligence automatically Sends clean, formatted reports without manual effort Maintains structured historical tracking for better decision-making

🔧 AI-Powered Auto-Maintenance System for n8n Transform your n8n instance management with this advanced automation system featuring artificial intelligence-driven workflow selection. This template provides comprehensive maintenance operations with smart filtering capabilities. ✨ Key Features 🤖 Artificial Intelligence Engine Multi-criteria scoring system for intelligent workflow selection Semantic analysis for business-critical pattern recognition Automated decision-making with configurable thresholds 🎯 Core Maintenance Operations Security Audits**: Automated vulnerability scanning with Google Sheets reporting Smart Pause/Resume**: Intelligent workflow suspension during maintenance windows AI Backup Creation**: Selective duplication of high-value workflows Intelligent Export**: Comprehensive system backups with metadata 🔐 Enterprise Security Token-based authentication with request validation Protected workflow safeguards (never modifies critical systems) Comprehensive error handling and logging ⚡ Automation & Scheduling Configurable maintenance schedules (daily, weekly, monthly) Webhook-driven operations for external integration Real-time monitoring and statistics 🎯 Perfect For DevOps Teams**: Streamline n8n maintenance operations Enterprise Users**: Manage large-scale workflow environments System Administrators**: Automated security and backup management Advanced Users**: Leverage AI for intelligent workflow management 🚀 Quick Setup Import the template Configure 4 credentials (n8n API, Google Sheets, Google Drive, Webhook Auth) Set your security token and Google Sheet ID Activate and enjoy automated maintenance! 🧠 AI Intelligence Highlights The system evaluates workflows using 6+ criteria including activity status, complexity, priority tags, business criticality, and recent updates. Workflows are automatically scored and selected based on intelligent thresholds. Selection Logic: Duplicate threshold: ≥3 points (smart backup selection) Export threshold: ≥5 points (comprehensive backup) System workflows always protected 📊 Includes 25+ configured nodes with emoji naming 4 detailed markdown documentation cards Pre-configured schedules and examples Comprehensive error handling Statistical reporting and monitoring Perfect for organizations looking to implement intelligent, automated n8n maintenance with minimal manual intervention.

Introduction Automate price monitoring for e-commerce competitors—ideal for retailers, analysts, and pricing teams. Scrapes competitor sites, extracts pricing/stock data via AI, detects changes, and sends instant alerts for dynamic pricing strategies. How It Works Scrapes competitor URLs via Firecrawl and Apify, extracts data with AI, detects price/stock changes, logs to Google Sheets, and sends Telegram alerts. Workflow Template Trigger → Scrape URL → AI Extract → Parse → Merge Historical → Detect Changes → Update Sheets + Send Telegram Alert Workflow Steps Trigger & Scrape → Manual/scheduled trigger → Firecrawl + Apify fetch competitor data AI Processing → Claude extracts product details → Parses and structures data Change Detection → Reads historical prices → Merges with current data → Identifies updates Output → Logs alerts to Sheets → Updates historical data → Sends Telegram notification Setup Instructions 1. Firecrawl API Get key from dashboard → Add to n8n 2. Apify API Get key from console → Add to n8n → Configure actors 3. AI Model (Claude/OpenAI) Get API key → Add to n8n 4. Google Sheets OAuth2 Create OAuth2 in Google Cloud Console → Authorize in n8n → Enable API 5. Telegram Bot Create via BotFather → Get token & chat ID → Add to n8n 6. Spreadsheet Setup Create Sheet with required columns → Copy ID → Paste in workflow Prerequisites Self-hosted n8n, Firecrawl account, Apify account, Claude/OpenAI API key, Google account (Sheets OAuth2),Telegram bot Customization Add more URLs, adjust scraping intervals, change detection thresholds, switch to Slack/email alerts, integrate databases Benefits Saves 2+ hours daily, real-time tracking, automated alerts, historical analysis, multi-source scraping

Intelligent chatbot with custom knowledge base Who's it for Businesses, developers, and organizations who need a customizable AI chatbot for internal documentation access, customer support, e-commerce assistance, or any use case requiring intelligent conversation with access to specific knowledge bases. What it does This workflow creates a fully customizable AI chatbot that can be deployed on any platform supporting webhook triggers (websites, Slack, Teams, etc.). The chatbot accesses a personalized knowledge base stored in Supabase and can perform advanced actions like sending emails, scheduling appointments, or updating databases beyond simple conversation. How it works The workflow combines several powerful components: Webhook Trigger: Accepts messages from any platform that supports webhooks AI Agent: Processes user queries with customizable personality and instructions Vector Database: Searches relevant information from your Supabase knowledge base Memory System: Maintains conversation history for context and traceability Action Tools: Performs additional tasks like email sending or calendar booking Technical architecture Chat trigger connects directly to AI Agent Language model, memory, and vector store all connect as tools/components to the AI Agent Embeddings connect specifically to the Supabase Vector Store for similarity search Requirements Supabase account and project AI model API key (any LLM provider of your choice) OpenAI API key (for embeddings - this is covered in Cole Medin's tutorial) n8n built-in PostgreSQL access (for conversation memory) Platform-specific webhook configuration (optional) How to set up Step 1: Configure your trigger The template uses n8n's default chat trigger For external platforms: Replace with webhook trigger and configure your platform's webhook URL Supported platforms: Any service with webhook capabilities (websites, Slack, Teams, Discord, etc.) Step 2: Set up your knowledge base For creating and managing your vector database, follow this comprehensive guide: Watch Cole Medin's tutorial on document vectorization This video shows how to build a complete knowledge base on Supabase The tutorial covers document processing, embedding creation, and database optimization Important: The video explains the OpenAI embeddings configuration required for vector search Step 3: Configure the AI agent Define your prompt: Customize the agent's personality and role Example: "You are the virtual assistant for example.com. Help users by answering their questions about our products and services." Select your language model: Choose any AI provider you prefer (OpenAI, Anthropic, Google, etc.) Set behavior parameters: Define response style, tone, and limitations Step 4: Connect Supabase Vector Store Add the "Supabase Vector Store" tool to your agent Configure your Supabase project credentials Mode: Set to "retrieve-as-tool" for automatic agent integration Tool Description: Customize description (default: "Database") to describe your knowledge base Table configuration: Specify the table containing your knowledge base (example shows "growth_ai_documents") Ensure your table name matches your actual knowledge base structure Multiple tables: You can connect several tables for organized data structure The agent will automatically decide when to search the knowledge base based on user queries Step 5: Set up conversation memory (recommended) Use "Postgres Chat Memory" with n8n's built-in PostgreSQL credentials Configure table name: Choose a name for your chat history table (will be auto-created) Context Window Length: Set to 20 messages by default (adjustable based on your needs) Benefits: Conversation traceability and analytics Context retention across messages Unique conversation IDs for user sessions Stored in n8n's database, not Supabase How to customize the workflow Basic conversation features Response style: Modify prompts to change personality and tone Knowledge scope: Update Supabase tables to expand or focus the knowledge base Language support: Configure for multiple languages Response length: Set limits for concise or detailed answers Memory retention: Adjust context window length for longer or shorter conversation memory Advanced action capabilities The chatbot can be extended with additional tools for: Email automation: Send support emails when users request assistance Calendar integration: Book appointments directly in Google Calendar Database updates: Modify Airtable or other databases based on user interactions API integrations: Connect to external services and systems File handling: Process and analyze uploaded documents Platform-specific deployments Website integration Replace chat trigger with webhook trigger Configure your website's chat widget to send messages to the n8n webhook URL Handle response formatting for your specific chat interface Slack/Teams deployment Set up webhook trigger with Slack/Teams webhook URL Configure response formatting for platform-specific message structures Add platform-specific features (mentions, channels, etc.) E-commerce integration Connect to product databases Add order tracking capabilities Integrate with payment systems Configure support ticket creation Results interpretation Conversation management Chat history: All conversations stored in n8n's PostgreSQL database with unique IDs Context tracking: Agent maintains conversation flow and references previous messages Analytics potential: Historical data available for analysis and improvement Knowledge retrieval Semantic search: Vector database returns most relevant information based on meaning, not just keywords Automatic decision: Agent automatically determines when to search the knowledge base Source tracking: Ability to trace answers back to source documents Accuracy improvement: Continuously refine knowledge base based on user queries Use cases Internal applications Developer documentation: Quick access to technical guides and APIs HR support: Employee handbook and policy questions IT helpdesk: Troubleshooting guides and system information Training assistant: Learning materials and procedure guidance External customer service E-commerce support: Product information and order assistance Technical support: User manuals and troubleshooting Sales assistance: Product recommendations and pricing FAQ automation: Common questions and instant responses Specialized implementations Lead qualification: Gather customer information and schedule sales calls Appointment booking: Healthcare, consulting, or service appointments Order processing: Take orders and update inventory systems Multi-language support: Global customer service with language detection Workflow limitations Knowledge base dependency: Quality depends on source documentation and embedding setup Memory storage: Requires active n8n PostgreSQL connection for conversation history Platform restrictions: Some platforms may have webhook limitations Response time: Vector search may add slight delay to responses Token limits: Large context windows may increase API costs Embedding costs: OpenAI embeddings required for vector search functionality

Who's it for Marketing teams, business intelligence professionals, competitive analysts, and executives who need consistent industry monitoring with AI-powered analysis and automated team distribution via Discord. What it does This intelligent workflow automatically monitors multiple industry topics, scrapes and analyzes relevant news articles using Claude AI, and delivers professionally formatted intelligence reports to your Discord channel. The system provides weekly automated monitoring cycles with personalized bot communication and comprehensive content analysis. How it works The workflow follows a sophisticated 7-phase automation process: Scheduled Activation: Triggers weekly monitoring cycles (default: Mondays at 9 AM) Query Management: Retrieves monitoring topics from centralized Google Sheets configuration News Discovery: Executes comprehensive Google News searches using SerpAPI for each configured topic Content Extraction: Scrapes full article content from top 3 sources per topic using Firecrawl AI Analysis: Processes scraped content using Claude 4 Sonnet for intelligent synthesis and formatting Discord Optimization: Automatically segments content to comply with Discord's 2000-character message limits Automated Delivery: Posts formatted intelligence reports to Discord channel with branded "Claptrap" bot personality Requirements Google Sheets account for query management SerpAPI account for Google News access Firecrawl account for article content extraction Anthropic API access for Claude 4 Sonnet Discord bot with proper channel permissions Scheduled execution capability (cron-based trigger) How to set up Step 1: Configure Google Sheets query management Create monitoring sheet: Set up Google Sheets document with "Query" sheet Add search topics: Include industry keywords, competitor names, and relevant search terms Sheet structure: Simple column format with "Query" header containing search terms Access permissions: Ensure n8n has read access to the Google Sheets document Step 2: Configure API credentials Set up the following credentials in n8n: Google Sheets OAuth2: For accessing query configuration sheet SerpAPI: For Google News search functionality with proper rate limits Firecrawl API: For reliable article content extraction across various websites Anthropic API: For Claude 4 Sonnet access with sufficient token limits Discord Bot API: With message posting permissions in target channel Step 3: Customize scheduling settings Cron expression: Default set to "0 9 * * 1" (Mondays at 9 AM) Frequency options: Adjust for daily, weekly, or custom monitoring cycles Timezone considerations: Configure according to team's working hours Execution timing: Ensure adequate processing time for multiple topics Step 4: Configure Discord integration Set up Discord delivery settings: Guild ID: Target Discord server (currently: 919951151888236595) Channel ID: Specific monitoring channel (currently: 1334455789284364309) Bot permissions: Message posting, embed suppression capabilities Brand personality: Customize "Claptrap" bot messaging style and tone Step 5: Customize content analysis Configure AI analysis parameters: Analysis depth: Currently processes top 3 articles per topic Content format: Structured markdown format with consistent styling Language settings: Currently configured for French output (easily customizable) Quality controls: Error handling for inaccessible articles and content How to customize the workflow Query management expansion Topic categories: Organize queries by industry, competitor, or strategic focus areas Keyword optimization: Refine search terms based on result quality and relevance Dynamic queries: Implement time-based or event-triggered query modifications Multi-language support: Add international keyword variations for global monitoring Advanced content processing Article quantity: Modify from 3 to more articles per topic based on analysis needs Content filtering: Add quality scoring and relevance filtering for article selection Source preferences: Implement preferred publisher lists or source quality weighting Content enrichment: Add sentiment analysis, trend identification, or competitive positioning Discord delivery enhancements Rich formatting: Implement Discord embeds, reactions, or interactive elements Multi-channel distribution: Route different topics to specialized Discord channels Alert levels: Add priority-based messaging for urgent industry developments Archive functionality: Create searchable message threads or database storage Integration expansions Slack compatibility: Replace or supplement Discord with Slack notifications Email reports: Add formatted email distribution for executive summaries Database storage: Implement persistent storage for historical analysis and trending API endpoints: Create webhook endpoints for third-party system integration AI analysis customization Analysis templates: Create topic-specific analysis frameworks and formatting Competitive focus: Enhance competitor mention detection and analysis depth Trend identification: Implement cross-topic trend analysis and strategic insights Summary levels: Create executive summaries alongside detailed technical analysis Advanced monitoring features Intelligent content curation The system provides sophisticated content management: Relevance scoring: Automatic ranking of articles by topic relevance and publication authority Duplicate detection: Prevents redundant coverage of the same story across different sources Content quality assessment: Filters low-quality or promotional content automatically Source diversity: Ensures coverage from multiple perspectives and publication types Error handling and reliability Graceful degradation: Continues processing even if individual articles fail to scrape Retry mechanisms: Automatic retry logic for temporary API failures or network issues Content fallbacks: Uses article snippets when full content extraction fails Notification continuity: Ensures Discord delivery even with partial content processing Results interpretation Intelligence report structure Each monitoring cycle delivers: Topic-specific summaries: Individual analysis for each configured search query Source attribution: Complete citation with publication date, source, and URL Structured formatting: Consistent presentation optimized for quick scanning Professional analysis: AI-generated insights maintaining factual accuracy and business context Performance analytics Monitor system effectiveness through: Processing metrics: Track successful article extraction and analysis rates Content quality: Assess relevance and usefulness of delivered intelligence Team engagement: Monitor Discord channel activity and report utilization System reliability: Track execution success rates and error patterns Use cases Competitive intelligence Market monitoring: Track competitor announcements, product launches, and strategic moves Industry trends: Identify emerging technologies, regulatory changes, and market shifts Partnership tracking: Monitor alliance formations, acquisitions, and strategic partnerships Leadership changes: Track executive movements and organizational restructuring Strategic planning support Market research: Continuous intelligence gathering for strategic decision-making Risk assessment: Early warning system for industry disruptions and regulatory changes Opportunity identification: Spot emerging markets, technologies, and business opportunities Brand monitoring: Track industry perception and competitive positioning Team collaboration enhancement Knowledge sharing: Centralized distribution of relevant industry intelligence Discussion facilitation: Provide common information baseline for strategic discussions Decision support: Deliver timely intelligence for business planning and strategy sessions Competitive awareness: Keep teams informed about competitive landscape changes Workflow limitations Language dependency: Currently optimized for French analysis output (easily customizable) Processing capacity: Limited to 3 articles per query (configurable based on API limits) Platform specificity: Configured for Discord delivery (adaptable to other platforms) Scheduling constraints: Fixed weekly schedule (customizable via cron expressions) Content access: Dependent on article accessibility and website compatibility with Firecrawl API dependencies: Requires active subscriptions and proper rate limit management for all integrated services

Load Jira open issues with comments into Pinecone + RAG Agent (Direct Tool or MCP) Who’s it for This workflow is designed for support teams, data engineers, and AI developers who want to centralize Jira issue data into a vector database. It collects open issues and their associated comments, converts them into embeddings, and loads them into Pinecone for semantic search, retrieval-augmented generation (RAG), or AI-powered support bots. It’s also published as an MCP tool, so external applications can query the indexed issues directly. How it works The workflow automates Jira issue extraction, comment processing, and vector storage in Pinecone. Importantly, the Pinecone index is recreated at every run so that it always reflects the current set of unresolved tickets. Trigger – A schedule trigger runs the workflow at defined times (e.g., 8, 11, 14, and 17 on weekdays). Issue extraction with pagination – Calls the Jira REST API to fetch open issues matching a JQL query (unresolved cases created in the last year). Pagination is fully handled: issues are retrieved in batches of 25, and the workflow continues iterating until all open issues are loaded. Data transformation – Extracts key fields (issue ID, key, summary, description, product, customer, classification, status, registration date). Comments integration – Fetches all comments for each issue, filters out empty/irrelevant ones (images, dots, empty markdown), and merges them with the issue data. Text cleaning – Converts HTML descriptions into clean plain text for processing. Embedding generation – Uses the OpenAI Embeddings node to vectorize text. Vector storage with index recreation – Loads embeddings and metadata into Pinecone under the jira namespace and the openissues index. The namespace is cleared at every run to ensure the index contains only unresolved tickets. Document chunking – Splits long issue texts into smaller chunks (512 tokens, 50 overlap) for better embedding quality. MCP publishing – Exposes the Pinecone index as an MCP tool (openissues), enabling external systems to query Jira issues semantically. How to set up Jira – Configure a Jira account and generate a token. Update the Jira node with credentials and adjust the JQL query if needed. OpenAI – Set up an OpenAI API key for embeddings. Configure embedding dimensions (default: 512). Pinecone – Create an index (e.g., openissues) with matching dimensions (512). Configure Pinecone API credentials and namespace (jira). The index will be cleared automatically at every run before reloading unresolved issues. Schedule – Adjust the cron expression in the Schedule Trigger to fit your update frequency. Optional MCP – If you want to query Jira issues via MCP, configure the MCP trigger and tool nodes. Requirements Jira account with API access and permissions to read issues and comments. OpenAI API key with access to the embedding model. Pinecone account with an index created (dimensions = 512). n8n instance with credentials set up for Jira, OpenAI, and Pinecone. How to customize the workflow JQL query**: Modify it to control which issues are extracted (e.g., by project, type, or time window). Pagination size**: Adjust the maxResults parameter (default 25) if you want larger or smaller batches per iteration. Metadata fields**: Add or remove fields in the “Extract Relevant Info” code node. Chunk size**: Adjust chunk size/overlap in the Document Chunker for different embedding strategies. Embedding model**: Switch to a different embedding provider if preferred. Vector store**: Replace Pinecone with another supported vector database if needed. Downstream use**: Extend with notifications, dashboards, or AI assistants that consume the vector data. AI Chatbot for Jira open tickets with SLA insights Who’s it for This workflow is designed for commercial teams, customer support, and service managers who need quick, conversational access to unresolved Jira tickets. It enables them to check whether a client has open issues, see related details, and understand SLA implications without manually browsing Jira. How it works Chat interface** – Provides a web-based chat that team members can use to ask natural language questions such as: “Are there any issues from client ACME?” “Do we have tickets that have been open for a long time?” AI Agent** – Powered by OpenAI, it interprets questions and queries the Pinecone vector store (openissues index, jira namespace). Memory** – Maintains short-term chat history for more natural conversations. Ticket retrieval** – Uses Pinecone embeddings (dimension = 512) to fetch unresolved tickets enriched with metadata: Issue key, description, customer, product, severity color, status, AM contract type, and SLA. SLA integration** – Service levels (Basic, Advanced, Full Service, with optional Fast Support) are provided via the SLA node. The agent explains which SLA applies based on ticket severity, registration date, and contract type. AI response** – Returns a friendly, collaborative summary of all tickets found, including: Ticket identifier Description Customer and product Severity level (Red, Yellow, Green, White) Ticket status Contract level and SLA explanation Setup Configure Jira → Pinecone index (openissues, 512 dimensions) already populated with unresolved tickets. Provide OpenAI API credentials. Ensure the SLA node includes the correct service-level definitions. Adjust chat branding (title, subtitle, CSS) if desired. Requirements Jira account with API access. Pinecone account with an index (openissues, dimensions = 512). OpenAI API key. n8n instance with LangChain and chatTrigger nodes enabled. How to customize Change the SLA node text if your service levels differ. Adjust the chat interface design (colors, title, subtitle). Expand metadata in Pinecone (e.g., add project type, priority, or assigned team). Train with additional examples in the system message to refine AI behavior.

👤 Who’s it for This workflow is designed for employees who need to submit expense claims for business trips. It automates the process of extracting data from receipts/invoices, logging it to a Google Sheet, and notifying the finance team via email. Ideal users: Employees submitting business trip expense claims HR or Admins reviewing travel-related reimbursements Finance teams responsible for processing claims ⚙️ How it works / What it does Employee submits a form with trip information (name, department, purpose, dates) and uploads one or more receipts/invoices (PDF). Uploaded files are saved to Google Drive for record-keeping. Each PDF is passed to a DocClaim Assistant agent, which uses GPT-4o and a structured parser to extract structured invoice data. The data is transformed and formatted into a standard JSON structure. Two parallel paths are followed: Invoice records are appended to a Google Sheet for centralized tracking. A detailed HTML email summarizing the trip and expenses is generated and sent to the finance department for claim processing. 🛠 How to set up Create a form to capture: Employee Name Department Trip Purpose From Date / To Date Receipt/Invoice File Upload (multiple PDFs) Configure file upload node to store files in a specific Google Drive folder. Set up DocClaim Agent using: GPT-4o or any LLM with document analysis capability Output parser for standardizing extracted receipt data (e.g., vendor, total, tax, date) Transform extracted data into a structured claim record (Code Node). Path 1: Save records to a Google Sheet (one row per expense). Path 2: Format the employee + claim data into a dynamic HTML email Use Send Email node to notify the finance department (e.g., finance@yourcompany.com) ✅ Requirements Jotform account with expense form setup Sign up for free here n8n running with access to: Google Drive API (for file uploads) Google Sheets API (for logging expenses) Email node (SMTP or Gmail for sending) GPT-4o or equivalent LLM with document parsing ability PDF invoices with clear formatting Shared Google Sheet for claim tracking Optional: Shared inbox for finance team 🧩 How to customize the workflow Add approval steps**: route the email to a manager before finance Attach original PDFs**: include uploaded files in the email as attachments Localize for other languages**: adapt form labels, email content, or parser prompts Sync to ERP or accounting system**: replace Google Sheet with QuickBooks, Xero, etc. Set limits/validation**: enforce max claim per trip or required fields before submission Auto-tag expenses**: add categories (e.g., travel, accommodation) for better reporting

Analyzes influencer profiles and scores authenticity before brand partnership approval. Detects fake followers, bot accounts, and suspicious engagement patterns using AI-powered behavioral analysis. 🎯 How It Works Simple 7-Node Workflow: Input → Submit influencer username and platform (Instagram/Twitter/TikTok) Fetch → Retrieve complete profile data and engagement metrics Analyze → Examine follower patterns, ratios, growth velocity, engagement AI Check → Deep behavioral analysis with Claude AI Report → Generate comprehensive fraud assessment Notify → Send detailed email report to partnership team Log → Save to database for tracking 📊 Detection Capabilities Follower Authenticity**: Analyzes follower-to-following ratio (red flag if < 0.5) Engagement Quality**: Calculates engagement rate (industry avg: 1-5%) Growth Patterns**: Detects suspicious rapid follower spikes Content Consistency**: Evaluates posting frequency and regularity Profile Completeness**: Checks verification, bio, activity AI Behavioral Analysis**: Deep pattern recognition for sophisticated fraud ⚙️ Setup Instructions 1. Configure API Access Social Platform APIs: Instagram**: Get Graph API access token from Meta for Developers Twitter**: OAuth 2.0 credentials from Twitter Developer Portal TikTok**: Business API credentials (optional) AI Analysis: Anthropic Claude API**: Get key from console.anthropic.com Used for advanced behavioral fraud detection 2. Setup Notifications Configure SMTP in "Send Report" node Update recipient email (partnerships@company.com) Customize HTML template if needed 3. Database (Optional) Create PostgreSQL table (schema below) Add database credentials to final node Skip if you don't need historical tracking Database Schema CREATE TABLE partnerships.influencer_fraud_reports ( id SERIAL PRIMARY KEY, report_id VARCHAR(255) UNIQUE, username VARCHAR(255), platform VARCHAR(50), profile_url TEXT, followers BIGINT, following BIGINT, posts INTEGER, verified BOOLEAN, authenticity_score INTEGER, risk_level VARCHAR(50), final_decision TEXT, partnership_recommendation VARCHAR(100), ai_verdict VARCHAR(50), ai_confidence VARCHAR(20), red_flags JSONB, fake_follower_estimate VARCHAR(20), detailed_analysis JSONB, created_at TIMESTAMP ); 🚀 How to Use Webhook Endpoint: POST /webhook/influencer-fraud-check Request Body: { "username": "influencer_handle", "platform": "instagram" // or "twitter", "tiktok" } Example: curl -X POST https://your-n8n.com/webhook/influencer-fraud-check \ -H "Content-Type: application/json" \ -d '{"username":"example_user","platform":"instagram"}' 📈 Scoring System Overall Authenticity Score (0-100): 80-100**: LOW RISK → Approved for partnership 60-79**: MEDIUM RISK → Requires manual review 40-59**: HIGH RISK → Caution advised 0-39**: CRITICAL RISK → Rejected Weighted Components: Follower Quality (25%) Engagement Quality (35%) Content Consistency (15%) Growth Pattern (15%) Profile Completeness (10%) Final Score = 70% Automated + 30% AI Analysis 🚩 Red Flags Detected Following-to-follower ratio > 2:1 Engagement rate < 0.5% Rapid growth (>50K followers/month) Large following with <10 posts No verification with >100K followers Bot-like comment patterns Suspicious audience demographics 💰 Cost Estimate Instagram/Twitter API**: Free tier usually sufficient Claude AI**: ~$0.10-0.20 per analysis Estimated**: $5-10/month for 50 checks 💡 Best Practices Always verify HIGH and MEDIUM risk profiles manually Cross-reference with other influencer databases Request media kit and past campaign results Trial campaigns before large commitments Monitor performance metrics post-partnership Update detection thresholds based on your findings 🎯 What You Get Detailed Report Includes: Overall authenticity score (0-100) Risk level classification Partnership recommendation (APPROVE/REVIEW/REJECT) Engagement quality analysis Fake follower percentage estimate AI behavioral insights Specific red flags and concerns Next steps and recommendations

AI-powered alt text generation from Google Sheets to WordPress media Who's it for WordPress site owners, content managers, and accessibility advocates who need to efficiently add alt text descriptions to multiple images for better SEO and web accessibility compliance. What it does This workflow automates the process of generating and updating alt text for WordPress media files using AI analysis. It reads image URLs from a Google Sheet, analyzes each image with Claude AI to generate accessibility-compliant descriptions, updates the sheet with the generated alt text, and automatically applies the descriptions to the corresponding WordPress media files. The workflow includes error handling to skip unsupported media formats and continue processing. How it works Input: Provide a Google Sheets URL containing image URLs and WordPress media IDs Authentication: Retrieves WordPress credentials from a separate sheet and generates Base64 authentication Processing: Loops through each image URL in the sheet AI Analysis: Claude AI analyzes each image and generates concise, accessible alt text (max 125 characters) Error Handling: Automatically skips unsupported media formats and continues with the next item Update Sheet: Writes the generated alt text back to the Google Sheet WordPress Update: Updates the WordPress media library with the new alt text via REST API Requirements Google Sheets with image URLs and WordPress media IDs WordPress site with Application Passwords enabled Claude AI (Anthropic) API credentials WordPress admin credentials stored in Google Sheets Export Media URLs WordPress plugin for generating the media list How to set up Step 1: Export your WordPress media URLs Install the "Export Media URLs" plugin on your WordPress site Go to the plugin settings and check both ID and URL columns for export (these are mandatory for the workflow) Export your media list to get the required data Step 2: Configure WordPress Application Passwords Go to WordPress Admin → Users → Your Profile Scroll down to "Application Passwords" section Enter application name (e.g., "n8n API") Click "Add New Application Password" Copy the generated password immediately (it won't be shown again) Step 3: Set up Google Sheets Duplicate this Google Sheets template to get the correct structure. The template includes two sheets: Sheet 1: "Export media" - Paste your exported media data with columns: ID (WordPress media ID) URL (image URL) Alt text (will be populated by the workflow) Sheet 2: "Infos client" - Add your WordPress credentials: Admin Name: Your WordPress username KEY: The application password you generated Domaine: Your site URL without https:// (format: "example.com") Step 4: Configure API credentials Add your Anthropic API credentials to the Claude node Connect your Google Sheets account to the Google Sheets nodes How to customize Language: The Claude prompt is in French - modify it in the "Analyze image" node for other languages Alt text length: Adjust the 125-character limit in the Claude prompt Batch processing: Change the batch size in the Split in Batches node Error handling: The workflow automatically handles unsupported formats, but you can modify the error handling logic Authentication: Customize for different WordPress authentication methods This workflow is perfect for managing accessibility compliance across large WordPress media libraries while maintaining consistent, AI-generated descriptions. It's built to be resilient and will continue processing even when encountering unsupported media formats.