by Jah coozi
Universal Digital Device Support Assistant Transform any device manual into an intelligent AI assistant that provides 24/7 support for your users. This template works with ANY household appliance, electronic device, or technical equipment. 🎯 Use Cases Manufacturers**: Provide instant support for your products Support Teams**: Reduce ticket volume with AI-powered answers Smart Homes**: Centralized help for all devices Personal Use**: Never lose a manual again ✨ Features Universal Compatibility**: Works with any device type Multi-Language Support**: Serve global customers Intelligent Search**: Semantic understanding of user queries Context Awareness**: Remembers conversation history Easy Setup**: Just upload your manual and go 🛠️ What's Included Webhook Endpoint: Receive user queries via API AI Agent: Processes questions intelligently Vector Database: Stores and searches manuals Memory System: Maintains conversation context Upload Pipeline: Easy manual ingestion 📋 Setup Instructions Add Your Credentials: OpenAI API key (or alternative LLM) Pinecone API key (or alternative vector DB) Upload Device Manuals: Use the manual upload trigger Paste manual text or upload PDF System automatically indexes content Configure Webhook: Set your preferred endpoint path Enable CORS if needed Deploy and share URL Optional Customization: Adjust chunk size for your content Modify system prompts for your brand Add additional tools or integrations 🔧 Supported Devices (Examples) Kitchen Appliances (ovens, dishwashers, coffee machines) Home Entertainment (TVs, sound systems, gaming consoles) Smart Home Devices (thermostats, cameras, lights) Computer Equipment (printers, routers, monitors) Power Tools & Garden Equipment Medical Devices And many more! 🌐 Integration Options Embed in your website Connect to chat platforms Mobile app integration Voice assistant compatibility Email support automation 📈 Benefits Reduce support costs by 70% Available 24/7 in multiple languages Consistent, accurate responses Scales infinitely Improves with usage 🔐 Privacy & Security Your data stays in your control Can be deployed on-premise GDPR compliant architecture No data sharing between devices 💡 Pro Tips Upload manuals in sections for better accuracy Include troubleshooting guides and FAQs Add model numbers and specifications Regular updates keep content fresh Start providing world-class device support today!
by Billy Christi
Who is this for? This workflow is ideal for: Finance teams** that need to process incoming invoices faster with minimal errors Small to mid-sized businesses** that want to automate invoice intake, review, and storage Operations managers** who require approval workflows and centralized record-keeping What problem is this workflow solving? Manually processing invoices is time-consuming, error-prone, and often lacks structure. This workflow solves those challenges by: Automating the intake of invoices** from multiple sources (email, Google Drive, web form) Extracting invoice data using AI**, eliminating manual data entry Implementing an email-based approval system** to add human oversight Automatically storing approved invoice data** in Google Sheets for easy access and reporting Notifying stakeholders** when invoices are approved or rejected What this workflow does This end-to-end invoice processing workflow includes: Three invoice input methods: Google Drive folder monitor, Gmail attachments, and web form uploads PDF to text extraction for each input method using native PDF parsing AI-powered invoice analysis with GPT-4 to extract structured fields such as vendor, total, and due date Dynamic categorization of invoice type (e.g., Travel, Software, Utilities) via AI Email-based approval workflow with embedded forms to collect decisions and notes Automated Google Sheets logging of all invoice data, approval status, and reviewer feedback Rejection notifications sent automatically to your finance team for transparency and follow-up Setup Copy the Google Sheet template here: 👉 PDF Invoice Parser with Approval Workflow – Google Sheet Template Connect your Google Drive account and specify the invoice folder ID Set up Gmail to monitor incoming invoices with PDF attachments Enable your form trigger to accept direct uploads from your internal or external users Enter your OpenAI API key in the AI processing node for data extraction Configure Google Sheets with a target spreadsheet to store invoice data Set recipient email addresses for invoice approvals and rejection notifications Test with a sample invoice to ensure end-to-end flow is working How to customize this workflow to your needs Change input sources**: Replace Gmail with Outlook or use Slack uploads instead Add validation steps**: Include regex or keyword checks before AI analysis Customize the AI schema**: Modify the expected JSON structure based on your internal finance system Integrate with accounting tools**: Add Xero, QuickBooks, or custom API nodes to push data Route based on category**: Add conditional logic to handle invoices differently based on vendor or category Multi-level approvals**: Add additional email steps if higher-level signoff is needed Audit logging**: Use database or Google Sheets to maintain a historical log of approvals and rejections
by David Roberts
This workflow allows you to ask questions about the data in a Google Sheet over a chat interface. It uses n8n's built-in chat, but could be modified to work with Slack, Teams, WhatsApp, etc. Behind the scenes, the workflow uses GPT4, so you'll need to have an OpenAI API key that supports it. How it works The workflow uses an AI agent with custom tools that call a sub-workflow. That sub-workflow reads the Google Sheet and returns information from it. Because models have a context window (and therefore a maximum number of characters they can accept), we can't pass the whole Google Sheet to GPT - at least not for big sheets. So we provide three ways of querying less data, that can be used in combination to answer questions. Those three functions are: List all the columns in the sheet Get all values of a single column Get all values of a single row Note that to use this template, you need to be on n8n version 1.19.4 or later.
by Ranjan Dailata
Who this is for? This workflow is designed for professionals and teams who need real-time, structured insights from Perplexity Search results without manual effort. What problem is this workflow solving? This n8n workflow solves the problem of automating Perplexity Search result extraction, cleanup, summarization, and AI-enhanced formatting for downstream use like sending the results to a webhook or another system. What this workflow does Automates Perplexity Search via Bright Data Uses Bright Data’s proxy-based SERP API to run a Google Search query programmatically. Makes the process repeatable and scriptable with different search terms and regions/zones. Cleans and Extracts Useful Content The Readable Data Extractor uses LLM-based cleaning to remove HTML/CSS/JS from the response and extract pure text data. Converts messy, unstructured web content into structured, machine-readable format. Summarizes Search Results Through the Gemini Flash + Summarization Chain, it generates a concise summary of the search results. Ideal for users who don’t have time to read full pages of search results. Formats Data Using AI Agent The AI Agent acts like a virtual assistant that: - Understands search results Formats them in a readable, JSON-compatible form Prepares them for webhook delivery Delivers Results to Webhook Sends the final summary + structured search result to a webhook (could be your app, a Slack bot, Google Sheets, or CRM). Setup Sign up at Bright Data. Navigate to Proxies & Scraping and create a new Web Unlocker zone by selecting Web Unlocker API under Scraping Solutions. In n8n, configure the Header Auth account under Credentials (Generic Auth Type: Header Authentication). The Value field should be set with the Bearer XXXXXXXXXXXXXX. The XXXXXXXXXXXXXX should be replaced by the Web Unlocker Token. In n8n, configure the Google Gemini(PaLM) Api account with the Google Gemini API key (or access through Vertex AI or proxy). Update the Perplexity Search Request node with the prompt you wish to perform the search. Update the Webhook HTTP Request node with the Webhook endpoint of your choice. How to customize this workflow to your needs 1. Change the Perplexity Search Input Default: It searches a fixed query or dataset. Customize: Accept input from a Google Sheet, Airtable, or a form. Auto-trigger searches based on keywords or schedules. 2. Customize Summarization Style (LLM Output) Default: General summary using Google Gemini or OpenAI. Customize: Add tone: formal, casual, technical, executive-summary, etc. Focus on specific sections: pricing, competitors, FAQs, etc. Translate the summaries into multiple languages. Add bullet points, pros/cons, or insight tags. 3.Choose Where the Results Go Options: Email, Slack, Notion, Airtable, Google Docs, or a dashboard. Auto-create content drafts for WordPress or newsletters. Feed into CRM notes or attach to Salesforce leads.
by Franz
🕸️ Dynamic Website Change Monitor with Smart Email Alerts Never miss important website updates again! This workflow automatically tracks changes on dynamic websites (think React apps, JavaScript-heavy sites) and sends you instant email notifications when something changes. Perfect for keeping tabs on competitors, monitoring product updates, or staying on top of important announcements. ✨ What makes this special? 🚀 Handles Dynamic Websites: Uses Firecrawl API to scrape JavaScript-rendered content that basic scrapers can't touch 📧 Smart Email Alerts: Only sends notifications when content actually changes (no spam!) 📊 Historical Tracking: Keeps a complete log of all changes in Google Sheets 🛡️ Bulletproof: Continues working even if one part fails ⚡ Ready to Deploy: Webhook-triggered, perfect for cron jobs or external schedulers 🎯 Perfect for monitoring: Competitor pricing pages Job board postings Product availability updates News sites for breaking stories API documentation changes Terms of service updates 🛠️ What you'll need to get started: API Accounts & Keys: Firecrawl Account 🔥 Sign up at firecrawl.dev Grab your API key from the dashboard Create a "Bearer Auth" credential in n8n Google Cloud Setup ☁️ Enable Google Sheets API Enable Gmail API Set up OAuth2 credentials Add both as credentials in n8n Google Sheets Document 📋 Create a new spreadsheet Add two tabs: "Log" and "comparison" Follow the structure outlined in the workflow notes 🚀 How it works: Webhook receives trigger → Starts the monitoring process Firecrawl scrapes website → Gets fresh content (even JavaScript-rendered!) Smart comparison → Checks against previously stored content Change detected? → If yes, send email + log everything Update storage → Prepares for next monitoring cycle ⚙️ Setup Steps: Import this workflow into your n8n instance Configure credentials for Firecrawl, Google Sheets, and Gmail Update the target URL in the Firecrawl node Set your email address in the Gmail node Create your Google Sheets with the required structure Test it manually first, then activate! 🎨 Customize it your way: Target any website** by updating the URL Change email templates** to match your style Adjust monitoring frequency** with external cron jobs Switch between markdown/HTML** extraction formats Fine-tune change detection** sensitivity 🔧 Troubleshooting: Firecrawl errors?** Check your API key and rate limits Google Sheets issues?** Verify OAuth permissions and sheet structure Email not sending?** Check Gmail API quotas and spam folders Webhook problems?** Make sure the workflow is activated Ready to never miss another website change? Let's get this automation running! 🎉
by Obsidi8n
How it works: Send notes from Obsidian via Webhook to start the audio conversion OpenAI converts your text to natural-sounding audio and generates episode descriptions Audio files are stored in Cloudinary and automatically attached to your notes in Obsidian A professional podcast feed is generated, compatible with all major podcast platforms (Apple, Spotify, Google) Set up steps: Install and configure the Post Webhook Plugin in Obsidian Set up Custom Auth credentials in n8n for Cloudinary using the following JSON: { "name": "Cloudinary API", "type": "httpHeaderAuth", "authParameter": { "type": "header", "key": "Authorization", "value": "Basic {{Buffer.from('your_api_key:your_api_secret').toString('base64')}}" } } Configure podcast feed metadata (title, author, cover image, etc.) Note: The second flow is a generic Podcast Feed module that can be reused in any '[...]-to-Podcast' workflow. It generates a standard RSS feed from Google Sheets data and podcast metadata, making it compatible with all major podcast platforms.
by Ranjan Dailata
Who is this for? This workflow automates the process of querying Bing's Copilot Search, extracting structured data from the results, summarizing the information, and sending a notification via webhook. It leverages the Microsoft Copilot to retrieve search results and integrates AI-powered tools for data extraction and summarization. What problem is this workflow solving? Data Analysts and Researchers: Who need to gather and summarize information from Bing search results efficiently. Developers and Engineers: Looking to integrate Bing search data into applications or services. Digital Marketers and SEO Specialists: Interested in monitoring search engine results for specific keywords or topics. What this workflow does Manually extracting and summarizing information from search engine results can be time-consuming and error-prone. This workflow automates the process by: Performing Bing searches using Bright Data's Bing Search API. Extracting structured data from the search results. Summarizing the extracted information using AI tools. Sending the summarized data to a specified endpoint via webhook. Setup Sign up at Bright Data. Navigate to Proxies & Scraping and create a new Web Unlocker zone by selecting Web Unlocker API under Scraping Solutions. In n8n, configure the Header Auth account under Credentials (Generic Auth Type: Header Authentication). The Value field should be set with the Bearer XXXXXXXXXXXXXX. The XXXXXXXXXXXXXX should be replaced by the Web Unlocker Token. In n8n, configure the Google Gemini(PaLM) Api account with the Google Gemini API key (or access through Vertex AI or proxy). Update the Perform a Bing Copilot Request node with the prompt you wish to perform the search. Update the Structured Data Webhook Notifier node with the Webhook endpoint of your choice. Update the Summary Webhook Notifier node with the Webhook endpoint of your choice. How to customize this workflow to your needs Modify Search Queries: Adjust the search terms to target different topics or keywords. Change Data Extraction Logic: Customize the extraction process to capture specific data points from the search results. Alter Summarization Techniques: Integrate different AI models or adjust parameters to change how summaries are generated. Update Webhook Endpoints: Direct the summarized data to different endpoints as required. Schedule Workflow Runs: Set up automated triggers to run the workflow at desired intervals.
by Agentick AI
This n8n workflow automates the process of collecting job and decision-maker data, crafting AI-generated referral messages, and drafting them in Gmail—all using a combination of Apify, Google Sheets, LLMs, and email APIs. Use cases Auto-sourcing job postings from LinkedIn via Apify Identifying decision-makers at relevant companies Auto-drafting custom referral request messages using AI Exporting structured data to Google Sheets and drafting Gmail messages for outreach Good to know You can customize the filtering logic to target specific cities or companies. Message creation uses the Gemini 2.0 Flash model and LangChain’s output parser for structured messages. Email data is fetched using Anymailfinder, but can be replaced with other providers like Hunter.io. Gmail API drafts the message, but you need to enable Gmail API access from your Google Cloud console. How it works Trigger A Schedule Trigger runs the automation daily. Job Data Extraction Apify pulls job listings using a predefined actor. The HTTP response is split and structured using the Split Out node. Store Job Data Job listings are saved to a Google Sheet. The node maps key fields like title, company, location, and poster info. Decision-Maker Discovery Another Apify actor pulls decision-maker data from LinkedIn. This is split and filtered (e.g., by city or company name). Store Contacts Contact details (name, title, location, etc.) are appended to another Google Sheet (n8n-sheet). Message Generation A LLM Chain uses Gemini 2.0 Flash to generate short, custom LinkedIn messages. The message respects rules like tone, length (<100 words), and personalization. Parse & Merge AI Output The output is structured using Structured Output Parser and merged with contact data. Save Final Messages The final headline and body are stored back into Google Sheets (n8n-sheet). Email Discovery Get Email IDs node hits Anymailfinder API using the LinkedIn profile link. Draft in Gmail Using Gmail API, the message is drafted in your inbox with subject and body auto-filled. How to use Update Apify actor inputs to specify roles, companies, or locations. Replace the manual Schedule Trigger with a webhook or form input if desired. Update the Google Sheets document and sheet name in the relevant nodes. Add your Gmail and Anymailfinder credentials in n8n settings. Requirements Google Sheets API access Gmail API access Apify account Gemini API key (via Google AI Studio) Anymailfinder (or alternate email discovery API) Customizing this workflow This framework is highly modular. You can: Add more filters for company size, role, or hiring urgency Use alternate LLMs (OpenAI, Claude, etc.) Switch output channels (Slack, WhatsApp, etc.) Plug in different CRM tools for follow-ups
by Leonard
Open Deep Research - AI-Powered Autonomous Research Workflow Description This workflow automates deep research by leveraging AI-driven search queries, web scraping, content analysis, and structured reporting. It enables autonomous research with iterative refinement, allowing users to collect, analyze, and summarize high-quality information efficiently. How it works 🔹 User Input The user submits a research topic via a chat message. 🧠 AI Query Generation A Basic LLM generates up to four refined search queries to retrieve relevant information. 🔎 SERPAPI Google Search The workflow loops through each generated query and retrieves top search results using the SerpAPI API. 📄 Jina AI Web Scraping Extracts and summarizes webpage content from the URLs obtained via SerpAPI. 📊 AI-Powered Content Evaluation An AI Agent evaluates the relevance and credibility of the extracted content. 🔁 Iterative Search Refinement If the AI finds insufficient or low-quality information, it generates new search queries to improve results. 📜 Final Report Generation The AI compiles a structured markdown report, including sources with citations. Set Up Instructions 🚀 Estimated setup time: ~10-15 minutes ✅ Required API Keys:** SerpAPI → For Google Search results Jina AI → For text extraction OpenRouter → For AI-driven query generation and summarization ⚙️ n8n Components Used:** AI Agents with memory buffering for iterative research Loops to process multiple search queries efficiently HTTP Requests for direct API interactions with SerpAPI and Jina AI 📝 Recommended Enhancements:** Add sticky notes in n8n to explain each step for new users Implement Google Drive or Notion Integration to save reports automatically 🎯 Ideal for: ✔️ Researchers & Analysts - Automate background research ✔️ Journalists - Quickly gather reliable sources ✔️ Developers - Learn how to integrate multiple AI APIs into n8n ✔️ Students - Speed up literature reviews 🔗 Completely free and open-source! 🚀
by Keith Rumjahn
Who's this for? If you own a website and need to analyze your Google analytics data If you need to create an SEO report on which pages are getting most traffic or how your google search terms are performing If you want to grow your site based on suggestions from data Use case Instead of hiring an SEO expert, I run this report weekly. It checks compares the data from this week to the week before: Views based on countries The top performing pages Google search console performance Watch youtube tutorial here Get my SEO A.I. agent system here Read my detailed case study here How it works The workflow gathers google analytics for the past 7 days then it gathers the data for the week before for comparison. It does this 3 times to get: views per country, engagement per page and google search console results for organic search results. The google analytics nodes has already chosen the correct dimensions and metrics. At the end, it passes the data to openrouter.ai for A.I. analyse. Finally it saves to baserow. How to use this Input your Google analytics credentials Input your property ID Input your Openrouter.ai credentials Input your baserow credentials You will need to create a baserow database with columns: Name, Country Views, Page Views, Search Report, Blog (name of your blog). Created by Rumjahn
by Jimleuk
This n8n template takes a video and extracts frames from it which are used with a multimodal LLM to generate a script. The script is then passed to the same multimodal LLM to generate a voiceover clip. This template was inspired by Processing and narrating a video with GPT's visual capabilities and the TTS API How it works Video is downloaded using the HTTP node. Python code node is used to extract the frames using OpenCV. Loop node is used o batch the frames for the LLM to generate partial scripts. All partial scripts are combined to form the full script which is then sent to OpenAI to generate audio from it. The finished voiceover clip is uploaded to Google Drive. Sample the finished product here: https://drive.google.com/file/d/1-XCoii0leGB2MffBMPpCZoxboVyeyeIX/view?usp=sharing Requirements OpenAI for LLM Ideally, a mid-range (16GB RAM) machine for acceptable performance! Customising this workflow For larger videos, consider splitting into smaller clips for better performance Use a multimodal LLM which supports fully video such as Google's Gemini.
by David Olusola
A complete, ready-to-deploy Telegram chatbot template for food delivery businesses. This intelligent assistant handles orders, payments, customer service, and order tracking with human-in-the-loop payment verification. ✨ Key Features 🤖 AI-Powered Conversations - Natural language order processing using Google Gemini 📱 Telegram Integration - Seamless customer interaction via Telegram 💳 Payment Verification - Screenshot-based payment confirmation with admin approval 📊 Order Tracking - Automatic Google Sheets logging of all orders 🧠 Memory Management - Contextual conversation memory for better customer experience 🌍 Multi-Currency Support - Easily customizable for any currency (USD, EUR, GBP, etc.) 📍 Location Flexible - Adaptable to any city/country 🔄 Human Oversight - Manual payment approval workflow for security 🛠️ What This Template Includes Core Workflow Customer Interaction - AI assistant takes orders via Telegram Order Confirmation - Summarizes order with total and payment details Information Collection - Gathers customer name, phone, and delivery address Payment Processing - Handles payment screenshots and verification Admin Approval - Human verification of payments before order confirmation Order Tracking - Automatic logging to Google Sheets with delivery estimates Technical Components AI Agent Node - Google Gemini-powered conversation handler Memory System - Maintains conversation context per customer Google Sheets Integration - Automatic order logging and tracking Telegram Nodes - Customer and admin communication Payment Verification - Screenshot detection and approval workflow Conditional Logic - Smart routing based on message types 🚀 Quick Setup Guide Prerequisites n8n instance (cloud or self-hosted) Telegram Bot Token Google Sheets API access Google Gemini API key Step 1: Replace Placeholders Search and replace the following placeholders throughout the template: Business Information [YOUR_BUSINESS_NAME] → Your restaurant/food business name [ASSISTANT_NAME] → Your bot's name (e.g., "Alex", "Bella", "Chef Bot") [YOUR_CITY] → Your city [YOUR_COUNTRY] → Your country [YOUR_ADDRESS] → Your business address [YOUR_PHONE] → Your business phone number [YOUR_EMAIL] → Your business email [YOUR_HOURS] → Your operating hours (e.g., "9AM - 11PM daily") Currency & Localization [YOUR_CURRENCY] → Your currency name (e.g., "USD", "EUR", "GBP") [CURRENCY_SYMBOL] → Your currency symbol (e.g., "$", "€", "£") [YOUR_TIMEZONE] → Your timezone (e.g., "EST", "PST", "GMT") [PREFIX] → Order ID prefix (e.g., "FB" for "Food Business") Menu Items (Customize Completely) [CATEGORY_1] → Food category (e.g., "Burgers", "Pizza", "Sandwiches") [ITEM_1] through [ITEM_8] → Your menu items [PRICE_1] through [DELIVERY_FEE] → Your prices Add or remove categories and items as needed Payment & Support [YOUR_PAYMENT_DETAILS] → Your payment information [YOUR_PAYMENT_PROVIDER] → Your payment method (e.g., "Venmo", "PayPal", "Bank Transfer") [YOUR_SUPPORT_HANDLE] → Your Telegram support username Step 2: Configure Credentials Telegram Bot - Add your bot token to Telegram credentials Google Sheets - Connect your Google account and create/select your orders spreadsheet Google Gemini - Add your Gemini API key Sheet ID - Replace [YOUR_GOOGLE_SHEET_ID] with your actual Google Sheet ID Step 3: Customize Menu Update the menu section in the AI Agent system message with your actual: Food categories Item names and prices Delivery fees Any special offerings or combos Step 4: Test & Deploy Import the template into your n8n instance Test the conversation flow with a test Telegram account Verify Google Sheets logging works correctly Test the payment approval workflow Activate the workflow 💰 Currency Examples USD Version 🍔 MENU & PRICES (USD) Burgers Classic Burger – $12.99 Cheese Burger – $14.99 Deluxe Burger – $18.99 Delivery Fee – $3.99 EUR Version 🍔 MENU & PRICES (EUR) Burgers Classic Burger – €11.50 Cheese Burger – €13.50 Deluxe Burger – €17.50 Delivery Fee – €3.50 📊 Google Sheets Structure The template automatically logs orders with these columns: Order ID Customer Name Chat ID Phone Number Delivery Address Order Info Total Price Payment Status Order Status Timestamp 🔧 Customization Options Easy Customizations Menu Items - Add/remove/modify any food items Pricing - Update to your local pricing structure Currency - Change to any currency worldwide Business Hours - Modify operating hours Delivery Areas - Add location restrictions Payment Methods - Update payment information# Header 1