Workflow Templates

PersonalNotesAssistant – Organize and Understand Your Thoughts with Local AI PersonalNotesAssistant is an offline-capable, AI-powered agent that helps you store, summarize, retrieve, and reflect on your personal notes and voice memos — all processed locally and sent via Telegram. Built to run efficiently on a Raspberry Pi 5, this agent supports a variety of note-taking styles and acts as your private memory extension. 🧠 What It Can Do Accept voice or text notes via Telegram Transcribe audio messages into clean, structured text (using Whisper) Automatically summarize or categorize notes with a local LLM Answer questions based on your past notes Retrieve relevant entries by topic, date, or keyword Help you journal or reflect by asking follow-up questions Work completely offline — no cloud or external APIs 🔧 How It Works Capture Notes via Telegram You send a voice message or text to your Telegram bot. The assistant supports both quick thoughts and long-form content. Transcription with Whisper (Local) If the input is a voice message, it is transcribed into text using Whisper running locally on your Raspberry Pi. AI Summarization & Tagging The transcribed or typed note is sent to LLaMA 3.2 via Ollama, which summarizes it, suggests tags, and stores it with metadata (e.g., timestamp, mood, theme). Storage & Retrieval Notes are stored in a local database (e.g., SQLite or JSON). You can later query the assistant with prompts like: “What did I say about stress last week?” “Summarize my ideas from this month.” “Show notes tagged with 'travel'.” Follow-Up & Reflection The agent can optionally engage with reflective prompts to help you deepen your thoughts or gain insight from what you’ve recorded. 💡 Use Cases Track personal growth, habits, or therapy progress Create voice memos while walking or commuting Maintain a structured journal without typing Use as a second brain to help you remember and revisit important thoughts 🔐 Privacy by Default Everything runs locally: No notes are uploaded to cloud platforms No audio is sent to third-party transcription services No LLM processing happens outside your device Ideal for privacy-minded users, psychologists, researchers, or digital minimalists who want AI assistance without surveillance. ⚙️ Technical Stack Raspberry Pi 5: Low-power edge device Whisper (local): For voice-to-text conversion Ollama + LLaMA 3.2: For summarization, classification, and retrieval Telegram Bot API: For input/output Custom Database (e.g., JSON/SQLite): For storing and querying notes 🧪 Real-Life Use This agent is actively used daily by the developer to log ideas, emotions, and plans. It has proven effective for lightweight journaling and context-aware memory assistance, even when offline.

Use case This workflow is designed for e-commerce brands and content teams who: Need to scale SEO content production without sacrificing quality Want to eliminate manual keyword filtering (saves 10+ hours/week) Aim to dominate niche search terms (e.g., "vegan leather crossbody bags") What this workflow does Automates the end-to-end process from keyword discovery to publish-ready articles: Keyword Harvesting: Pulls 1,000+ keywords/day from SEMrush/Ahrefs Smart Filtering:Blocks competitor brands (e.g., "Zara alternatives") Detects irrelevant demographics ("kids", "petite") AI Content Generation:Flags non-compliant colors (non-black/white terms) Multi-Channel Output: Formats content for blogs, product descriptions, and email campaigns setup Add Google,SEMrush and OpenAI credentials Set the rules excel of google drive Test workflow by testing workflow Review generated opportunity report in Google Sheets How to adjust this template Change scenario: Replace the rules and define different target

An automated n8n workflow that analyzes stocks using RSI and MACD, summarizes insights with OpenAI, and sends a Slack-ready market update every hour. This workflow: Runs hourly from 6:30 AM to 2:30 PM PT, Mon–Fri Checks if the U.S. stock market is open using Alpaca’s /clock API Pulls daily stock bars for a list of tickers via Alpaca’s /v2/stocks/bars Calculates RSI and MACD using a Python code node Categorizes each stock as Buy / Hold / Sell Uses OpenAI Assistant to summarize the results in Slack markdown Sends the message to a specific Slack user or channel

This workflow automatically identifies trending topics and hashtags across social media platforms to keep you informed of current trends and viral content. It saves you time by eliminating the need to manually research trending topics and provides data-driven insights for content strategy and social media planning. Overview This workflow automatically scrapes trending hashtag platforms and social media sites to extract currently trending topics, hashtags, and viral content themes. It uses Bright Data to access trend data sources without restrictions and AI to intelligently analyze trending content and provide actionable insights for content creators and marketers. Tools Used n8n**: The automation platform that orchestrates the workflow Bright Data**: For scraping trend platforms and social media without being blocked OpenAI**: AI agent for intelligent trend analysis and content insights Google Sheets**: For storing trending topics data and analysis results How to Install Import the Workflow: Download the .json file and import it into your n8n instance Configure Bright Data: Add your Bright Data credentials to the MCP Client node Set Up OpenAI: Configure your OpenAI API credentials Configure Google Sheets: Connect your Google Sheets account and set up your trending topics tracking spreadsheet Customize: Define target trend platforms and topics of interest Use Cases Content Marketing**: Discover trending topics for timely and relevant content creation Social Media Strategy**: Plan posts around viral hashtags and trending themes Brand Monitoring**: Track if your brand or industry topics are trending Influencer Marketing**: Identify trending content opportunities for collaborations Connect with Me Website**: https://www.nofluff.online YouTube**: https://www.youtube.com/@YaronBeen/videos LinkedIn**: https://www.linkedin.com/in/yaronbeen/ Get Bright Data**: https://get.brightdata.com/1tndi4600b25 (Using this link supports my free workflows with a small commission) #n8n #automation #trendingtopics #hashtags #brightdata #webscraping #contentmarketing #n8nworkflow #workflow #nocode #socialmediatrends #trendanalysis #viralcontent #contentresearch #socialmediamonitoring #trendtracking #contentdiscovery #hashtagresearch #socialmediamarketing #contentautomation #trendmonitoring #socialmediainsights #contentplanning #trendalerts #viralmarketing #socialtrends #contentoptimization #trendingcontent #socialmediadata #contentintelligence

Ever wanted to just tell your 3d printer what to do remotely? This game changer let's you converse with OpenAI agents to manage OctoPrint connected 3d printers. Great for remote management and monitoring with easy to read responses. Query what jobs are available, Load a print job (upload workflow in development, will be released soon for community use), start the print job and request detailed reports on your printers performance as it runs. Chat > AI > OctoPrint API > Your 3d Printer ++Example 1:++ Human Input: "What print job is running?" AI Response: Current Print Job Details, Job Name: Stand v1.gcode File Size: 2,533,233 bytes Estimated Print Time: Approximately 6 hours 15 minutes (22536 seconds) Progress: Completion: 1.97%, Current Position in File: 49,940 bytes, Time Spent Printing: 2,611 seconds (~43.5 minutes), Time Remaining: Approximately 5 hours 34 minutes (20,123 seconds), Status, Current State: Printing." ++Example 2++ Human Input: "Is my 3d Printer ok?" AI Response: "Status: Printing, Operational: Yes, ++Temperature:++ Bed Temperature: Actual: 50°C, Target: 50°C, Nozzle (Tool 0) Temperature: Actual: 200°C, Target: 200°C, ++Connection Status:++ Connection State: Currently connected to the printer, Port: /dev/ttyUSB0, Baudrate: 115200, Summary, Your 3D printer is currently operational and printing without errors. The bed and nozzle temperatures are both at their target values."

YouTube Transcript Summarization in Any Language for Social Media This n8n workflow automates the process of: Retrieving YouTube Video Transcripts: It fetches the transcript for any YouTube video URL provided using the YouTube Transcript API from RapidAPI. Generating a Concise Summary in Any Language: The workflow uses Google Gemini (PaLM) to create a concise summary of the transcript in the language specified by the user (e.g., English, Spanish, etc.). Storing the Summary in Google Docs: The generated summary is inserted into a predefined Google Document, making it easy for users to share or edit. Features: Language Flexibility:** Summaries are created in the desired language. Fully Automated:** From fetching the transcript to updating Google Docs, the process is fully automated. Social Media Ready:** The summary is formatted and stored in a Google Doc, ready for use in social media posts. This workflow integrates with YouTube Transcript API via RapidAPI, allowing you to easily fetch video transcripts and summarize them with AI. The entire process is automated and seamless. Powered by RapidAPI: API Used:* YouTube Transcript API via *RapidAPI** to get the transcript data. Benefits: Saves Time:** Automates the transcript summarization process, eliminating the need for manual content extraction and summarization. Customizable Language Support:** Provides summaries in any language, enabling accessibility and engagement for a global audience. Streamlined Content Creation:** Automatically generates concise, engaging summaries that are ready for social media use. Google Docs Integration:** Saves summaries directly into a Google Doc for easy sharing, editing, and content management. Challenges Addressed: Manual Transcript Extraction:** Problem: Manually transcribing and summarizing YouTube videos for social media can be time-consuming and error-prone. Solution: This workflow fully automates the process, saving hours of manual work using the YouTube Transcript API. Lack of Language Support in Summaries:** Problem: Many automated tools only summarize content in a single language, limiting their accessibility. Solution: With language flexibility, the workflow creates summaries in the language of your choice, helping you cater to diverse audiences. Inconsistent Video Quality & Transcript Accuracy:** Problem: Not all YouTube videos have well-structured or accurate transcripts, leading to incomplete or inaccurate summaries. Solution: The workflow can process and format even imperfect transcripts, ensuring that the generated summaries are still accurate and useful. Managing Content Across Platforms:** Problem: Transcripts and summaries often need to be stored in multiple locations for social media posts, which can be cumbersome. Solution: The workflow integrates with Google Docs to automatically store and manage summaries in one place, making it easier to share and reuse content.

Paul Graham Essay Search & Chat with Milvus Vector Database How It Works This workflow creates a RAG (Retrieval-Augmented Generation) system using Milvus vector database to search Paul Graham essays: Scrape & Load: Fetches Paul Graham essays, extracts text, and stores them as vector embeddings in Milvus Chat Interface: Enables semantic search and AI-powered conversations about the essays Set Up Steps Set up Milvus server following the official installation guide, then create a collection Execute the workflow to scrape essays and load them into your Milvus collection Chat with the AI agent using the Milvus tool to query and discuss essay content

🌐 AI Customer Support Assistant - Cloud Version What this workflow does: This AI-powered customer support automation processes incoming support requests via email or chat, analyzes them using AI, retrieves relevant context, and generates draft responses for support agents. Key Features: ✅ Multi-channel Input: Email & chat triggers ✅ AI-powered Analysis: Extracts sentiment, urgency, and key information ✅ Context Integration: Combines product manuals, ERP data, and support history ✅ Draft Response Generation: Creates professional responses in German ✅ Human-in-the-loop: Approval workflow before sending to customers Demo Instructions: Use the Chat interface to test with sample customer queries Or send test emails to trigger the email workflow Watch how AI analyzes and generates contextual responses

This workflow automates currency rate uploads into SAP Business One via Service Layer, using flexible input sources such as JSON (API), SQL Server, Google Sheets, or manual values. It leverages logic branching, AI validation, and logging for complete control and traceability. ++⚙️ HOW IT WORKS:++ 🔹 1. Receive Data via Webhook The workflow listens on the endpoint /formulario-datos via HTTP POST. The request body should include: origen: one of JSON, SQL, GoogleSheets, or Manual Depending on the value, the flow branches accordingly. 🔹 2. Authenticate with SAP Business One A POST request is sent to SAP B1’s Login endpoint. A session cookie (B1SESSION) is retrieved and used in all subsequent API calls. 🔹 3. Switch by Origin The flow branches into four processing paths based on origen: JSON: The payload is normalized using OpenAI to extract an array of rates. Each rate is sent to SAP individually after parsing. SQL: The SQL query provided in the payload is executed on a connected Microsoft SQL Server. The results are checked by AI to validate the date format. If valid, rates are sent to SAP. GoogleSheets: Rates are pulled from a connected spreadsheet. Each entry is sent to SAP in sequence. Manual: Uses currency, rate, and rateDate directly from the webhook payload. Sends the result directly to SAP. 🔹 4. AI-Powered Enhancements (Optional but enabled) Normalize JSON: Uses OpenAI (LangChain node) to convert any messy structure into a uniform array under the key rate. Date Formatting: Another OpenAI call ensures RateDate is in yyyyMMdd format (required by SAP), converting from ISO, timestamp, or other formats. 🔹 5. Send to SAP Business One (Service Layer) All paths send a POST request to: /SBOBobService_SetCurrencyRate With a payload such as: { "Currency": "USD", "Rate": "0.92", "RateDate": "20250612" } 🔹 6. Log Results All success/failure results are appended to a Google Sheets log (LOGS_N8N) The log includes method, URL, sent payload, status code, and message. ++🛠 SETUP STEPS:++ 1️⃣ Create Required Credentials: Go to Credentials > + New Credential and configure: SAP Business One (Service Layer) Type: HTTP Request Auth or Token Base URL: https://<your-host>:50000/b1s/v1/ Provide Username, Password, and CompanyDB via variables or fields Google Sheets OAuth2 connection to a Google account with access Microsoft SQL Server SQL login credentials and host OpenAI API key with access to models like GPT-4o 2️⃣ Environment Variables (Recommended) Set these variables in n8n → Settings → Variables: SAP_URL=https://<host>:50000/b1s/v1/ SAP_USER=your_username SAP_PASSWORD=your_password SAP_COMPANY_DB=your_companyDB 3️⃣ Prepare Google Sheets Sheet 1: RATE (for charging the data) Columns: Currency, Rate, RateDate Sheet 2: LOGS_N8N (to save the logs, success or failed) Columns: workflow, method, url, json, status_code, message 4️⃣ Activate and Test Deploy the webhook and grab the URL. ++✅ BONUS++ Built-in AI assistance for input validation and structure Logs all results for compliance and audit Flexible integration paths: perfect for hybrid or transitional systems

This workflow contains community nodes that are only compatible with the self-hosted version of n8n. This workflow automatically tracks customer satisfaction scores across multiple platforms and surveys to help improve customer experience and identify areas for enhancement. It saves you time by eliminating the need to manually check different feedback sources and provides comprehensive satisfaction analytics. Overview This workflow automatically scrapes customer satisfaction surveys, review platforms, and feedback forms to extract satisfaction scores and sentiment data. It uses Bright Data to access various feedback platforms without being blocked and AI to intelligently analyze satisfaction trends and identify improvement opportunities. Tools Used n8n**: The automation platform that orchestrates the workflow Bright Data**: For scraping satisfaction surveys and review platforms without being blocked OpenAI**: AI agent for intelligent satisfaction analysis and trend identification Google Sheets**: For storing satisfaction scores and generating analytics reports How to Install Import the Workflow: Download the .json file and import it into your n8n instance Configure Bright Data: Add your Bright Data credentials to the MCP Client node Set Up OpenAI: Configure your OpenAI API credentials Configure Google Sheets: Connect your Google Sheets account and set up your satisfaction tracking spreadsheet Customize: Define feedback sources and satisfaction metrics you want to monitor Use Cases Customer Experience**: Monitor satisfaction trends across all customer touchpoints Product Teams**: Identify product features that impact customer satisfaction Support Teams**: Track satisfaction scores for support interactions Management**: Get comprehensive satisfaction reporting for strategic decisions Connect with Me Website**: https://www.nofluff.online YouTube**: https://www.youtube.com/@YaronBeen/videos LinkedIn**: https://www.linkedin.com/in/yaronbeen/ Get Bright Data**: https://get.brightdata.com/1tndi4600b25 (Using this link supports my free workflows with a small commission) #n8n #automation #customersatisfaction #satisfactionscores #brightdata #webscraping #customerexperience #n8nworkflow #workflow #nocode #satisfactiontracking #csat #nps #customeranalytics #feedbackanalysis #customerinsights #satisfactionmonitoring #experiencemanagement #customermetrics #satisfactionsurveys #feedbackautomation #customerfeedback #satisfactiondata #customerjourney #experienceanalytics #satisfactionreporting #customersentiment #experienceoptimization #satisfactiontrends #customervoice

Workflow based on the following article. https://www.anthropic.com/news/contextual-retrieval This n8n automation is designed to extract, process, and store content from documents into a Pinecone vector store using context-based chunking. The workflow enhances retrieval accuracy in RAG (Retrieval-Augmented Generation) setups by ensuring each chunk retains meaningful context. Workflow Breakdown: 🔹 Google Drive - Retrieve Document: The automation starts by fetching a source document from Google Drive. This document contains structured content, with predefined boundary markers for easy segmentation. 🔹 Extract Text Content - Once retrieved, the document’s text is extracted for processing. Special section boundary markers are used to divide the text into logical sections. 🔹 Code Node - Create Context-Based Chunks: A custom code node processes the extracted text, identifying section boundaries and splitting the document into meaningful chunks. Each chunk is structured to retain its context within the entire document. 🔹 Loop Node - Process Each Chunk: The workflow loops through each chunk, ensuring they are processed individually while maintaining a connection to the overall document context. 🔹 Agent Node - Generate Context for Each Chunk: We use an Agent node powered by OpenAI’s GPT-4.0-mini via OpenRouter to generate contextual metadata for each chunk, ensuring better retrieval accuracy. 🔹 Prepend Context to Chunks & Create Embeddings - The generated context is prepended to the original chunk, creating context-rich embeddings that improve searchability. 🔹 Google Gemini - Text Embeddings: The processed text is passed through Google Gemini text-embedding-004, which converts the text into semantic vector representations. 🔹 Pinecone Vector Store - Store Embeddings: The final embeddings, along with the enriched chunk content and metadata, are stored in Pinecone, making them easily retrievable for RAG-based AI applications. Use Case: This automation enhances RAG retrieval by ensuring each chunk is contextually aware of the entire document, leading to more accurate AI responses. It’s perfect for applications that require semantic search, AI-powered knowledge management, or intelligent document retrieval. By implementing context-based chunking, this workflow ensures that LLMs retrieve the most relevant data, improving response quality and accuracy in AI-driven applications.

This workflow contains community nodes that are only compatible with the self-hosted version of n8n. This workflow automatically gathers and analyzes feature requests from multiple sources including support tickets, user forums, and feedback platforms to help prioritize product development. It saves you time by eliminating the need to manually monitor various channels and provides intelligent feature request analysis. Overview This workflow automatically scrapes support systems, user forums, social media, and feedback platforms to collect feature requests from customers. It uses Bright Data to access various platforms without being blocked and AI to intelligently categorize, prioritize, and analyze feature requests based on frequency and user impact. Tools Used n8n**: The automation platform that orchestrates the workflow Bright Data**: For scraping support platforms and user forums without being blocked OpenAI**: AI agent for intelligent feature request categorization and analysis Google Sheets**: For storing feature requests and generating prioritization reports How to Install Import the Workflow: Download the .json file and import it into your n8n instance Configure Bright Data: Add your Bright Data credentials to the MCP Client node Set Up OpenAI: Configure your OpenAI API credentials Configure Google Sheets: Connect your Google Sheets account and set up your feature request tracking spreadsheet Customize: Define feedback sources and feature request identification parameters Use Cases Product Management**: Prioritize roadmap items based on customer demand Development Teams**: Understand which features users need most Customer Success**: Track and respond to feature requests proactively Strategy Teams**: Make data-driven decisions about product direction Connect with Me Website**: https://www.nofluff.online YouTube**: https://www.youtube.com/@YaronBeen/videos LinkedIn**: https://www.linkedin.com/in/yaronbeen/ Get Bright Data**: https://get.brightdata.com/1tndi4600b25 (Using this link supports my free workflows with a small commission) #n8n #automation #featurerequests #productmanagement #brightdata #webscraping #productdevelopment #n8nworkflow #workflow #nocode #roadmapping #customervoice #productinsights #featureanalysis #productfeedback #userresearch #productdata #featuretracking #productplanning #customerneeds #featurediscovery #productprioritization #featurebacklog #uservoice #productintelligence #developmentplanning #featuremonitoring #productdecisions #feedbackgathering #productautomation