by James Carter
This n8n workflow automatically fetches trending news articles based on your chosen country, category, and keyword — then enriches the data with AI-powered business insights before posting a concise summary to Slack. Ideal for sales teams, executives, marketers, or anyone who wants fast, actionable news briefings directly in their Slack workspace. ⸻ Who it’s for Executives, analysts, sales teams, or marketing professionals who want curated, AI-enhanced news summaries tailored to business opportunities, risks, and trends — delivered automatically to Slack. ⸻ How it works / What it does A Schedule Trigger runs on a daily, weekly, or custom frequency. It queries the NewsAPI to retrieve top headlines by country, category, or keyword. Headlines are formatted and enriched with your configured query context. The AI model (GPT-4) analyzes articles and summarizes key insights, categorizing them as Opportunities, Risks, or Trends. Finally, the summarized insights are posted directly into a Slack channel of your choice. ⸻ How to set up Set your schedule frequency in the Schedule Trigger node. Configure your preferred country, category, and keyword in the Inject Config node. Add your NewsAPI Key inside the Fetch News Articles node. Connect your Slack credentials in the Post to Slack node. Optional: Adjust the AI prompt for more tailored analysis. ⸻ Requirements A NewsAPI account to fetch headlines. An OpenAI API key for GPT-4 summarization. A Slack workspace and connected credentials via n8n. ⸻ How to customize the workflow Change the country, category, or keyword in the Inject Config to focus on specific markets or sectors. Adjust the AI prompt in the GPT node to prioritize certain insights like ESG factors, M&A activity, or market sentiment. Extend the workflow to log results to Google Sheets, email summaries, or send SMS alerts. Replace the Schedule Trigger with a Webhook if you want to trigger summaries on demand. This template is designed to be modular, making it easy to adapt for competitive intelligence, investment tracking, or industry news curation.
by Jimleuk
This n8n template is one of a 3-part series exploring use-cases for clustering vector embeddings: Survey Insights Customer Insights Community Insights This template demonstrates the Community Insights scenario where HN commments can be quickly grouped by similarity and an AI agent can generate insights on those groupings. With this workflow, Researchers or HN users can quickly breakdown community consensus on a particular topic and identify frequently mentioned positives and negatives. Sample Output: https://docs.google.com/spreadsheets/d/e/2PACX-1vQXaQU9XxsxnUIIeqmmf1PuYRuYtwviVXTv6Mz9Vo6_a4ty-XaJHSeZsptjWXS3wGGDG8Z4u16rvE7l/pubhtml How it works HN comments are imported via the Hacknews API node. Comments are then inserted into a Qdrant collection carefully tagged with the Hackernews API metadata. Comments are then fetched and are put through a clustering algorithm using the Python Code node. The Qdrant points are returned in clustered groups. Each group is looped to fetch the payloads of the points and feed them to the AI agent to summarise and generate insights for. The resulting insights and raw responses are then saved to the Google Spreadsheet for further analysis by the researcher or the HN user. Requirements Works best with lots of comments! Qdrant Vectorstore for storing embeddings. OpenAI account for embeddings and LLM. Customising the Template Adjust clustering parameters which make sense for your data. Adjust sentimentality setting if comments are overwhelmingly negative at times.
by HoangSP
SEO Blog Generator with GPT-4o, Perplexity, and Telegram Integration This workflow helps you automatically generate SEO-optimized blog posts using Perplexity.ai, OpenAI GPT-4o, and optionally Telegram for interaction. 🚀 Features 🧠 Topic research via Perplexity sub-workflow ✍️ AI-written blog post generated with GPT-4o 📊 Structured output with metadata: title, slug, meta description 📩 Integration with Telegram to trigger workflows or receive outputs (optional) ⚙️ Requirements ✅ OpenAI API Key (GPT-4o or GPT-3.5) ✅ Perplexity API Key (with access to /chat/completions) ✅ (Optional) Telegram Bot Token and webhook setup 🛠 Setup Instructions Credentials: Add your OpenAI credentials (openAiApi) Add your Perplexity credentials under httpHeaderAuth Optional: Setup Telegram credentials under telegramApi Inputs: Use the Form Trigger or Telegram input node to send a Research Query Subworkflow: Make sure to import and activate the subworkflow Perplexity_Searcher to fetch recent search results Customization: Edit prompt texts inside the Blog Content Generator and Metadata Generator to change writing style or target industry Add or remove output nodes like Google Sheets, Notion, etc. 📦 Output Format The final blog post includes: ✅ Blog content (1500-2000 words) ✅ Metadata: title, slug, and meta description ✅ Extracted summary in JSON ✅ Delivered to Telegram (if connected) Need help? Reach out on the n8n community forum
by IvanCore
Disclaimer: This workflow contains community nodes that are only compatible with the self-hosted version of n8n. Important distinction: This template manages Telegram Copilot's UserBots (client accounts), not Telegram Bots. UserBot vs. Bot: Key Differences 🔹 Telegram Copilot's UserBots Authenticate as real user accounts (phone number required) Can join groups/channels without "Bot" label Subject to Telegram's client API limits Require manual login (MFA supported) 🔹 Telegram Bots Use @BotFather-created tokens Limited to bot API functionality Can't initiate chats with unbidden users No phone number required This template solves the unique challenges of UserBot management through: Core Functionality 🛡️ Session Reliability Automatic crash recovery (5-step restart sequence) Persistent session monitoring (checks every 6h) Database cleanup via /clear command 📱 Multi-Device Support Manages sessions independently from mobile clients Tracks active devices via /stat command Isolates session data per credential 🔔 Smart Notifications Real-time alerts to admin chat Detailed error context with authState snapshots Success confirmations with session metadata Setup Guide Prerequisites Self-hosted n8n instance (community node required) Valid Telegram account for UserBot Telegram bot token for notifications TelePilot credentials with api_id/api_hash Configuration Steps Credential Setup Add TelePilot credentials in n8n Configure Telegram bot token in notification nodes Set admin chat ID for alerts Monitoring Customization Adjust check frequency in Schedule Trigger Modify alert thresholds in Filter nodes Configure retry logic in recovery sequence Session Management Test /start command flow Verify /stat output format Confirm notification delivery Workflow Customization Advanced Options Add secondary notification channels (Email, Slack) Implement escalating alert system Integrate with monitoring dashboards Customize recovery attempt limits Compliance Notes UserBots must comply with Telegram's Terms of Service Not intended for bulk messaging or spam Recommended for legitimate automation use cases Note: UserBots must comply with Telegram ToS. Not for spam/mass messaging. Why This Matters: UserBots enable automation scenarios impossible with regular bots (e.g., group management as normal user, reacting as human account). This workflow keeps them reliably online 24/7.
by Femi Ad
"Ade Technical Analyst" is a dual-workflow AI system combining conversational intelligence with visual chart analysis through Telegram. The system features 11 primary nodes for conversation management and 8 secondary nodes for chart generation and analysis. Core Components: Telegram Integration: Message handling with dynamic typing indicators AI Personality: "Ade" - a financial analyst with 50+ years NYSE/LSE experience using Claude 3.5 Sonnet Chart Generation: TradingView integration via Chart-IMG API with MACD and volume indicators Visual Analysis: GPT-4O vision for technical pattern recognition Memory System: Session-based conversation context retention Target Users Individual traders seeking professional-grade analysis without subscription costs Financial advisors wanting 24/7 AI-powered client support Investment educators needing interactive learning tools Fintech companies requiring white-label analysis solutions Setup Requirements Critical Security Fix Needed: Remove hardcoded API key from Chart-IMG node immediately Store all credentials securely in n8n credential manager Required APIs: OpenRouter (Claude 3.5 Sonnet) OpenAI (GPT-4O vision) Chart-IMG API Telegram Bot Token Technical Prerequisites: n8n version 1.7+ with Langchain nodes Webhook configuration for Telegram Dual-workflow setup with proper ID referencing Workflow Requirements Security Compliance: Never hardcode API keys in workflow JSON files Use n8n credential manager for all sensitive data Implement proper session isolation for user data Include mandatory financial disclaimers Performance Specifications: Model temperature: 0.8 for balanced responses Token limit: 500 for optimized performance Dark theme charts with professional indicators Session-based memory management Need help customizing? Contact me for consulting and support or add me on LinkedIn
by Jay Emp0
🔥 Upgrade to V3 Longer blogs, Higher SEO ranking with images, charts and tables We’ve released Version 3 of our AI-Powered Blog Automation workflow. We heard your complains and made a complete redesign built for serious content creators. 📝 Read the New Articles Generated by v3 🛒 View the workflow on n8n.io ✅ Longer Blog contents 3-Agent AI Architecture as the Planner, Writer, Editor: simulate a full content team for structure, writing, and QC. A more continuous flow 📈 2x bump in SEO ranking SEO Scoring System so every article is graded on keyword density, readability, structure, backlinks, and uniqueness. IF quality doesnt meet threshold, we revise the content again. 🖼️ Smarter Visuals In-blog images via Leonardo, charts via QuickChart, tables and web scraped outbound links 🕸️ Multi-Platform Publishing Auto-posts to WordPress, Twitter (X), and Dev.to 🕵️♂️ Research Agent Adds quotes, stats, facts, outbound links, entities, and references to improve article credibility Content Farming V2 AI Powered Blog Automation for WordPress This workflow automatically generates and publishes 10 blog posts per day to a WordPress site. It collects tech-related news articles, filters and analyzes them for relevance, expands them with research, generates SEO-optimized long-form articles using AI, creates a matching image using Leonardo AI, and publishes them via the WordPress REST API. Every step is tracked and stored in MongoDB for reference and performance tracking. You can see the demo results for the AI based articles here: Emp0 Articles How it works A scheduler runs daily to fetch the latest news from RSS feeds including BBC, TechCrunch, Wired, MIT Tech Review, HackerNoon, and others. The RSS data is normalized and filtered to include only articles published within the past 24 hours. Each article is passed through an OpenAI-powered classifier to check for relevance to predefined user topics like AI, robotics, or tech policy. Relevant articles are then aggregated, researched, and summarized with supporting sources and citations. An AI agent generates five long-tail SEO blog title ideas, ranks them by uniqueness and performance score, and selects the top one. A blog outline is created including H1 and H2 headers, keyword targeting, content structure, and featured snippet optimization. A full-length article (1000 to 1500 words) is generated based on the outline, with analogies, citations, examples, and keyword density maintained. SEO metadata is produced including meta title, description, image alt text, slug, and a readability audit. An AI-generated image is created based on the blog theme using Leonardo AI, enhanced for emotional storytelling and visual consistency. The blog article, metadata, and image are uploaded to WordPress as a draft, the image is attached, Yoast SEO metadata is set, and the article is published. All outputs including article versions, metadata, generation steps, and final blog URLs are stored in MongoDB to allow for future analytics and feedback. Requirements To run this project, you need accounts and API access for the following: | Tool | Purpose | Notes | |--------------|------------------------------------------------------------------|-----------------------------------------------------------------------| | OpenAI | Used for blog classification, generation, summarization, SEO | Around $0.20 per day, using GPT-4o-mini. Estimated monthly: $6 | | MongoDB | Stores data flexibly including drafts, titles, metadata, logs | Free tier on MongoDB Atlas offers 512 MB, enough for 64,000 articles | | Leonardo AI | Generates featured images for blog articles | $9 for 3500 credits, $5 monthly top-up needed for 300 images | | WordPress | Final publishing platform via REST API | Hosted on Hostinger for $15/year including domain | Setup Instructions Import the provided JSON file into your n8n instance. Configure these credentials in n8n: OpenAI API key MongoDB Atlas connection string HTTP Header Auth for Leonardo AI WordPress REST API credentials Modify the classifier and prompt nodes to reflect your preferred content themes. Adjust scheduler nodes if you want to change post frequency or publishing times. Run the n8n instance continuously using Docker, PM2, or hosted automation platform. Cost Estimate | Component | Daily Usage | Monthly Cost Estimate | |---------------|------------------------------|------------------------| | OpenAI | 10 posts per day | ~$6 | | Leonardo AI | 10 images per day (15 credits each) | ~$14 (9 base + 5 top-up) | | MongoDB | Free up to 512 MB | $0 | | WordPress | Hosting and domain | ~$1.25 | | Total | | ~$21/month | Observations and Learnings This system can scale daily article publishing with zero manual effort. However, current limitations include inconsistent blog length and occasional coherence issues. To address this, I plan to build a feedback loop within the workflow: An SEO Commentator Agent will assess keyword strength, structure, and discoverability. An Editor-in-Chief Agent will review tone, clarity, and narrative structure. Both agents will loop back suggestions to the content generator, improving each draft until it meets human-level standards. The final goal is to consistently produce high-quality, readable, SEO-optimized content that is indistinguishable from human writing.
by Naveen Choudhary
Who is this for? Marketing, content, and enablement teams that need a quick, human-readable summary of every new video published by the YouTube channels they care about—without leaving Slack. What problem does this workflow solve? Manually checking multiple channels, skimming long videos, and pasting the highlights into Slack wastes time. This template automates the whole loop: detect a fresh upload from your selected channels → pull subtitles → distill the key take-aways with GPT-4o-mini → drop a neatly-formatted digest in Slack. What this workflow does Schedule Trigger fires every 10 min, then grabs a list of YouTube RSS feeds from a Google Sheet. HTTP + XML fetch & parse each feed; only brand-new videos continue. YouTube API fetches title/description, RapidAPI grabs English subtitles. Code nodes build an AI payload; OpenAI returns a JSON summary + article. A formatter turns that JSON into Slack Block Kit, and Slack posts it. Processed links are appended back to the “Video Links” sheet to prevent dupes. Setup Make a copy of this Google Sheet and connect a Google Sheets OAuth2 credential with edit rights. Slack App: create → add chat:write, channels:read, app_mention; enable Event Subscriptions; install and store the Bot OAuth token in an n8n Slack credential. RapidAPI key for https://yt-api.p.rapidapi.com/subtitles (300 free calls/mo) → save as HTTP Header Auth. OpenAI key → save in an OpenAI credential. Add your RSS feed URLs to the “RSS Feed URLs” tab; press Execute Workflow. How to customise Adjust the schedule interval or freshness window in “If newly published”. Swap the OpenAI model or prompt for shorter/longer digests. Point the Slack node at a different channel or DM. Extend the AI payload to include thumbnails or engagement stats. Use-case ideas Product marketing**: Instantly brief sales & CS teams when a competitor uploads a feature demo. Internal learning hub**: Auto-summarise conference talks and share bullet-point notes with engineers. Social media managers**: Get ready-to-post captions and key moments for re-purposing across platforms.
by Evoort Solutions
🖼️ Text-to-Image Generator using n8n + Flux AI This n8n workflow automates image generation from text prompts using the Text-to-Image Flux AI API. It reads prompts from Google Sheets, generates images via API, uploads them to Google Drive, and logs the outcome. 🌟 Key Features Integrates with Text-to-Image Flux AI on RapidAPI Converts base64 image data to downloadable files Stores images on Google Drive Updates logs and errors back into Google Sheets Skips prompts already processed 📄 Google Sheet Column Structure Your source Google Sheet should include the following columns: | Column Name | Description | |-------------------|--------------------------------------------------| | Prompt | The text prompt to generate an image from | | drive path | (Optional) File path or URL of saved image | | Generated Date | Date/time the image was generated | | Base64 | Base64 string or error message (for logging) | Only rows with a non-empty Prompt and empty drive path will be processed. 📌 Use Case Perfect for: Bulk AI image generation for content marketing Creative automation with prompt-based image creation Building image assets based on structured datasets Any workflow where prompts are tracked via Google Sheets Uses the Text-to-Image Flux AI API to generate high-quality images on demand. 🔧 Workflow Summary | Step | Node | Description | |------|------|-------------| | 1 | Manual Trigger | Manually start the workflow | | 2 | Google Sheets2 | Reads prompts from Google Sheets | | 3 | Loop Over Items | Processes rows one by one | | 4 | If2 | Skips rows that already have images | | 5 | HTTP Request1 | Calls Text-to-Image Flux AI via RapidAPI | | 6 | Code1 | Converts base64 image to binary file | | 7 | Google Drive1 | Uploads the image file to a Drive folder | | 8 | Google Sheets1 | Logs base64 result and timestamp back | | 9 | If1 | Handles errors from the API | | 10 | Google Sheets4 | Logs errors to the sheet | | 11 | Wait | Adds delay between batches to prevent rate-limiting | 🚀 RapidAPI: Text-to-Image Flux AI This flow is powered by Text-to-Image Flux AI. Be sure to: Sign up at RapidAPI and subscribe to the API. Copy your API Key. Replace "your key" in the HTTP Request1 node’s x-rapidapi-key header. You can test the API directly here before connecting it to n8n. ✅ Tips for Setup Ensure you’ve set up a Google Service Account with access to both Sheets and Drive. Fill only the Prompt column — leave drive path and Base64 empty for new prompts. Monitor your RapidAPI dashboard for usage and quota. Create your free n8n account and set up the workflow in just a few minutes using the link below: 👉 Start Automating with n8n Save time, stay consistent, and grow your LinkedIn presence effortlessly!
by Julian Kaiser
This automated workflow scrapes and processes the monthly "Who is Hiring" thread from Hacker News, transforming raw job listings into structured data for analysis or integration with other systems. Perfect for job seekers, recruiters, or anyone looking to monitor tech job market trends. How it works Automatically fetches the latest "Who is Hiring" thread from Hacker News Extracts and cleans relevant job posting data using the HN API Splits and processes individual job listings into structured format Parses key information like location, role, requirements, and company details Outputs clean, structured data ready for analysis or export Set up steps Configure API access to [Hacker News](https://github.com/HackerNews/API ) (no authentication required) Follow the steps to get your cURL command from https://hn.algolia.com/ Set up desired output format (JSON structured data or custom format) Optional: Configure additional parsing rules for specific job listing information Optional: Set up integration with preferred storage or analysis tools The workflow transforms unstructured job listings into clean, structured data following this pattern: Input: Raw HN thread comments Process: Extract, clean, and parse text Output: Structured job listing data This template saves hours of manual work collecting and organizing job listings, making it easier to track and analyze tech job opportunities from Hacker News's popular monthly hiring threads.
by inderjeet Bhambra
Who is this for? This workflow is designed for travel bloggers, content creators, social media managers, and anyone who wants to transform their travel photos into engaging written narratives. It's perfect for travelers looking to create compelling stories from their photo collections without spending hours crafting content manually, families wanting to document memorable trips, and digital nomads who need to produce travel content efficiently. What problem is this workflow solving? Converting travel photos into engaging stories is time-consuming and requires both creative writing skills and the ability to analyze visual content meaningfully. This workflow solves the challenge of: Transforming visual memories into compelling written narratives Organizing photos chronologically to create logical story flow Generating professional-quality travel content without writing expertise Analyzing photo content to extract meaningful themes and emotions Creating day-by-day structured narratives from unorganized photo collections Reducing the time spent on manual content creation for travel documentation What this workflow does This AI-powered photo storyteller takes your travel photos and automatically generates immersive, first-person travel narratives. The workflow: Accepts multiple photos through a webhook endpoint Uses OpenAI Vision API (GPT-4o) to analyze each photo's content, emotions, and themes Automatically organizes photos chronologically by date and timestamp Groups photos by travel days and extracts daily themes Leverages GPT-4.1 (minimum required) to craft engaging, first-person travel stories with creative day titles Generates structured narratives with sensory details, cultural observations, and emotional insights Outputs JSON formatted content ready for formatting Creates day-by-day story structure with memorable moments and reflective conclusions Setup Required Credentials: OpenAI API key configured in n8n for both Vision Analysis and Story Generation nodes Ensure you have sufficient OpenAI credits for image analysis and text generation Webhook Configuration: The workflow creates a webhook endpoint at /tripteller-upload Configure your photo upload interface to POST photos array to this endpoint Photos should be sent as base64 encoded data with filename and metadata Photo Requirements: Supported formats: Standard image formats (JPEG, PNG, etc.) Photos should include timestamp metadata for chronological organization Caution Do not upload all photos at once. Start with a small number of photos, like 5 at a time. How to customize this workflow to your needs Story Style Customization: Modify the system prompt in the "Generate Travel Story" node to adjust writing tone (nostalgic, adventurous, poetic, etc.) Customize the story structure by editing the output format requirements Add specific cultural or geographical context prompts for location-specific storytelling Photo Analysis Enhancement: Adjust the Vision Analysis node prompt to focus on specific elements (architecture, food, people, landscapes) Modify the grouping logic in the "Group Photos by Day" node for different time-based organization Add location extraction from EXIF data for geographical context Output Format Adjustment: Customize the final response structure in the "Format Final Response" node Add integration with publishing platforms (blog APIs, social media, etc.) Include additional metadata like location tags, travel duration, or trip statistics Performance Optimization: Adjust the execution timeout based on your typical photo volume Modify the parallel processing approach for large photo collections Add progress tracking for longer processing workflows
by AlexAy
Who is this workflow template for? This workflow template is perfect for freelancers, small business owners, accounting teams, or anyone responsible for managing and recording invoices regularly. If you deal with multiple invoices and spend considerable time manually entering invoice data into a database, this automation will significantly simplify your daily operations and reduce potential errors. What this workflow does The workflow automates the entire invoice logging process. It continuously monitors a designated Google Drive folder every minute for new PDF invoice uploads. Once a new invoice is detected, it is automatically converted from PDF to an image format using the ILovePDF API. After conversion, Google's Gemini AI analyzes the image, intelligently extracting essential details such as vendor name, item description, invoice amount, invoice date, payment date, and bank reference numbers. Finally, this structured data is automatically recorded in an Airtable database (or optionally in a Google Sheet), ensuring organized, accessible records. Detailed Workflow Explanation Step 1: Invoice Detection** Monitors Google Drive for newly uploaded PDF invoices. Step 2: PDF to Image Conversion** Converts PDFs into images using ILovePDF. Step 3: Data Extraction via Gemini AI** Uses Gemini AI to analyze the invoice image. Extracts data such as Vendor, Description, Amount, Invoice Date, Paid Date, and Bank Reference. Provides clear descriptions even when original invoice descriptions are vague or missing by analyzing vendor context. Step 4: Structured Data Storage** Automatically sends extracted data to Airtable or Google Sheets. Step 5: File Management** Moves processed PDF files into a separate "Done" folder to clearly differentiate between processed and unprocessed invoices. Step-by-Step Setup Instructions Set Up Google Drive: Log in to Google Drive and create two folders: One named Invoices (for incoming PDF files) One named Processed (for processed files) Obtain API Credentials: ILovePDF API: Sign up at ILovePDF Developers. Retrieve your API key from your account dashboard. Google Gemini AI API: Register at Google AI and generate an API key. Airtable Database Preparation: Create an Airtable base with the following columns: Vendor (Text) Description (Text) Amount (Number or Text) Invoice Date (Date) Paid Date (Date) Bank Reference (Text) Import and Configure Workflow in n8n: Import the provided workflow JSON file into your n8n instance. Connect your Google Drive, ILovePDF, Google Gemini AI, and Airtable accounts by entering your credentials in their respective nodes. Adjust Workflow Settings: In the Google Drive nodes, ensure your newly created Invoices and Processed folders are correctly selected. Update the ILovePDF public key in the appropriate HTTP Request node. Customize the Gemini AI prompt to refine or expand data extraction according to your specific needs. Testing Your Setup: Upload a sample PDF invoice into the Invoices folder. Execute the workflow by clicking Test Workflow in n8n and verify if data extraction and Airtable logging operate correctly. Airtable Column Specifications Ensure your Airtable includes the following structure: Vendor**: Single Line Text Description**: Single Line Text Amount**: Currency or Single Line Text Invoice Date**: Date (formatted as YYYY-MM-DD) Paid Date**: Date (formatted as YYYY-MM-DD) Bank Reference**: Single Line Text How to Customize the Workflow System Prompt:** Adjust the AI instructions by modifying the prompt text to focus on additional or fewer invoice details. Structured Output Parser:** Modify the JSON schema in the parser node to match the structure and data points your project specifically requires: By following these instructions, you’ll have a fully automated, reliable system for handling and logging invoice data, significantly enhancing your productivity.
by Robert Breen
Extract Local Business Contacts with Google Sheets, SerpAPI & GPT‑4o Status: Ready for Use ✅ Disclaimer: This workflow relies on community nodes that are not part of n8n’s core package. Install the following from n8n → Community Nodes before running: n8n-nodes-langchain** n8n-nodes-openai** (Structured Output Parser) n8n-nodes-apify** 📝 Description This n8n workflow automates discovery of local‑business contact details by search term and location, then enriches the results with publicly listed email addresses using GPT‑4o AI. 🔑 Key Features 🔗 Google Sheets Integration Reads search terms and locations from a Google Sheet. Processes only rows that are not marked Complete, preventing duplicates. 🗺️ Google Maps Search via SerpAPI Queries Google Maps through SerpAPI for every search‑term‑and‑location pair. Retrieves the following fields: business name, website, street address, and phone number. 🧠 Website Scraping & Email Extraction Scrapes the business homepage content with Apify’s Fast Website Content Crawler. Sends the scraped HTML to a GPT‑4o AI Agent. Extracts any publicly listed email address. Returns a clean, structured JSON object for downstream use. 💾 Data Storage & Tracking Writes every result to a Results tab in the same Google Sheet. Marks the corresponding row in the Searches tab as Complete once finished. 🧱 Extensible Design The workflow uses modular sub‑workflows and AI agents. You can easily extend it to add: Phone‑number verification with Twilio Social‑media enrichment with Clearbit Exports to HubSpot, Salesforce, Airtable, PostgreSQL, or CSV files 📄 Google Sheet Setup Create a Searches tab with these exact columns (one header row): Search | Area | Area Name | Complete Create a results tab with these columns title | website | address | phone | Search | Search Name | Area | email (Manual Entry) ⚙️ Prerequisites Google Cloud Project with Google Sheets API and Google Drive API enabled SerpAPI account (free trial or paid) – obtain an API key Apify account (free trial or paid) with the Fast Website Content Crawler actor installed OpenAI account with an API key that can access GPT‑4o models 🚀 Setup Instructions Copy the Google Sheet Make a personal copy of the template sheet. Ensure the tab names are Searches and Results. https://docs.google.com/spreadsheets/d/1QgcVMlXRlM_5ZFFUHr6bVK-93Tzia9XseTX03ZYnowI/edit?usp=sharing Configure Google Sheets nodes in n8n Open the workflow. Update the nodes Extract Search Terms and Save Emails to Sheet to point at your copied sheet. Authenticate using Google OAuth2 credentials that have access to the sheet. Add SerpAPI credentials Sign in at <https://serpapi.com>. Copy your API key. In the Search Google Maps node, create a new credential and paste the key. Set up Apify Sign up at <https://apify.com>. Add the Fast Website Content Crawler actor to your account. In the Scrape Web Page HTTP node, append ?token=YOUR_API_KEY to the actor URL. Add your OpenAI API key Go to <https://platform.openai.com>. Generate an API key. Add it to the AI Agent and OpenAI Chat Model node credentials. ✅ Running the Workflow Click Execute Workflow in n8n. For each unprocessed row in the Searches tab, the automation will: Retrieve business information from Google Maps via SerpAPI. Scrape the business website using Apify. Use GPT‑4o to extract a public email address. Write all collected data to the Results tab. Mark the original row as Complete. 🧩 Example Use Cases Build highly targeted lead lists for sales and marketing outreach. Compile local business directories for regional websites or apps. Automate contact‑information collection for lead‑generation campaigns and reduce manual data entry. 🤝 Connect with Me Description I’m Robert Breen, founder of Ynteractive — a consulting firm that helps businesses automate operations using n8n, AI agents, and custom workflows. I’ve helped clients build everything from intelligent chatbots to complex sales automations, and I’m always excited to collaborate or support new projects. If you found this workflow helpful or want to talk through an idea, I’d love to hear from you. Links 🌐 Website: https://www.ynteractive.com 📺 YouTube: @ynteractivetraining 💼 LinkedIn: https://www.linkedin.com/in/robert-breen 📬 Email: rbreen@ynteractive.com