Agents & Automations

This workflow with AI agent is designed to navigate through the page to retrieve a specific type of information (in this example: social media profile links). The agent is equipped with two tools: - Text tool: to retrieve all the text from the page. - URLs tool: to extract all possible links from the page. 💡 You can edit the prompt and JSON schema connected to the agent in order to return other data than social media profile links. 👉 This workflow uses Supabase as storage (input/output). Feel free to change it to any other database of your choice. 🎬 See this workflow in action in my YouTube video. How it works? The workflow uses the input URL (website) as a starting point to retrieve the data (e.g. example.com). Using the "URLs tool," the agent is able to retrieve all links from the page and navigate to them. For example, if you want to retrieve contact information, the agent will try to find a subpage that might contain this information (e.g. example.com/contact) and extract the information using the text tool. Set up steps: 1. Connect database with input data (website addresses) or pin sample data to trigger node. 2. Configure the crawling agent to retrieve the desired data (e.g. modify prompt and/or parsing schema). 3. Set credentials for OpenAI. 4. Optionally: split agent tools to separate workflows. If you like this workflow, please subscribe to my YouTube channel and/or my newsletter.

🧠 What This Workflow Does This n8n workflow allows you to upload a T-shirt mockup design (even if it's rough or outdated) and automatically turns it into a refined, print-ready artwork using the power of AI. It starts with an image of a T-shirt design, analyzes it using OpenAI's vision model, and then generates a cleaner, upgraded prompt to be used with OpenAI’s image generation API (gpt-image-1). The final output is a new T-shirt graphic optimized for printing on a solid black background, with no visible shirt or mockup framing. ⚙️ How It Works 1. User Sends a T-shirt Mockup Image Link The workflow begins when the user drops an image link (T-shirt mockup) into a chat interface or input trigger. 2. AI Analyzes the Image (OpenAI Vision) Using OpenAI’s GPT-4 vision capabilities, the workflow extracts the key design elements from the image: - Characters, text, layout - Graphic style, composition - Visual tone and focus 3. AI Agent Creates a Refined Prompt The extracted details are passed to an AI agent that: - Preserves the original layout and message - Enhances the visual composition and typography - Removes mockup elements like shirt collar, sleeves, and shadows - Locks the artwork on a pure black background only Outputs a clean, artistic, JSON-safe one-line prompt for generation. 4. Text Escaping for API Compatibility A JavaScript function node escapes the prompt (quotes, slashes, line breaks) to make it safe for use in downstream JSON requests. 5. Image Generation via GPT-Image-1 API The final prompt is sent to OpenAI’s gpt-image-1 to generate a brand-new artwork — ideal for direct printing on a black T-shirt. ⚠️ Cost Notice for gpt-image-1 Usage This workflow uses OpenAI's gpt-image-1 model to generate high-quality T-shirt artwork from refined prompts. Please note that this model is a paid service, and each image generation request may cost approximately $0.25 per design, depending on resolution and usage. We strongly recommend users to review their OpenAI API usage plan and be mindful of costs when running this workflow, especially if generating in bulk or integrating into larger automation flows. You can monitor your usage at the OpenAI platform. ✅ Key Features - Works from any uploaded mockup image - Converts design concepts into print-ready artwork prompts - Avoids outputting shirt models, collars, or product mockups - Optimized for solid black background with no distractions - Modular and easy to connect with file delivery or approval flows 🚀 How to Use - Import the .json workflow into n8n - Configure your OpenAI credentials for both vision and image APIs - Trigger the flow by sending an image URL of a T-shirt mockup - Let the workflow generate and return a brand-new design from that concept

Convert text to speech, send via email, and upload files to FTP using HTTP, ElevenLabs, FTP, and Google Email modules.

Who is this template for This template is for marketers, SEO specialists, or content managers who need to analyze keywords to identify which ones contain references to a specific area or topic, in this case – IT software, services, tools, or apps. Use case Automating the process of scanning a large list of keywords to determine if they reference known IT products or services (like ServiceNow, Salesforce, etc.), and updating a Google Sheet with this classification. This helps in categorizing keywords for targeted SEO campaigns, content creation, or market analysis. How this workflow works - Fetches keyword data from a Google Sheet. - Processes keywords in batches to prevent rate limiting. - Uses an AI agent (OpenAI) to analyze each keyword and determine if it contains a reference to an IT service/software. - Updates the original Google Sheet with the results in a "Service?" column. - Continues processing until all keywords are analyzed. Set up steps 1. Connect your Google Sheets account credentials. 2. Set the Google Sheet document ID (currently using "Copy of Sheet1 1"). 3. Configure the OpenAI API credentials for the AI agent. 4. Adjust the batch size (currently 6) if needed based on your API rate limits. 5. Ensure the Google Sheet has the required columns: "Number", "Keyword", and "Service?". The AI agent's prompt is highly customizable to match different identification needs. For example, instead of looking for IT software/services, you could modify the prompt to identify: - Industry-specific terms (healthcare, finance, education) - Geographic references (cities, countries, regions) - Product categories (electronics, clothing, food) - Competitor brand mentions Here's how you could modify the prompt for different use cases: // For identifying educational content keywords "Check the keyword I provided and define if this keyword relates to educational content, courses, or learning materials and return yes or no." // For identifying local service keywords "Check the keyword I provided and determine if it contains location-specific terms (city names, neighborhoods, regions) that suggest local service intent and return yes or no." // For identifying competitor mentions "Check the keyword I provided and determine if it mentions any of our competitors (CompetitorA, CompetitorB, CompetitorC) and return yes or no."

Tags: Productivity, Education, Learning, Language Context I’m a Supply Chain Data Scientist from Paris who lived six years in China — and yes, learning Mandarin while working full-time was tough. Learning Mandarin as an adult can be very difficult, especially if you have a full-time job. With AI, you can now have a Chinese tutor available 24/7 on your phone — no excuses left! It is with this spirit that I designed this workflow to support fellow Mandarin learners with a Chinese Teacher powered by GPT-4o. Boost your language skills with AI using N8N! 📬 For business inquiries, you can add me on LinkedIn. Who is this template for? This workflow template is designed for language learners and educators who need support to learn a vocabulary list in Mandarin (or any other language) using Open AI GPT-4o, an AI agent and a Telegram Bot to interact with users. For the vocabulary list, you can use another template shared in my profile 🉑 Generate Anki Flash Cards for Language Learning with Google Translate and GPT-4o to generate the Google Sheet needed in this workflow. How does it work? The workflow loads a vocabulary list stored in your Google Sheet. The bot will: 📥 Load your vocabulary list from Google Sheets 🧠 Generate multiple-choice questions with GPT-4o ✅ Evaluate your answer and give instant feedback 🔁 Loop to the next word until you're fluent These fields will be automatically added to a Google Sheet, ready to be loaded in Anki to create flash cards. What do I need to start? This workflow does not require any advanced programming skills. Prerequisite - A Google Drive Account with a folder including a Google Sheet filled with the vocabulary list you want to learn. - API Credentials: Open AI API for the chat model, Google Drive API and Google Sheets API activated with OAuth2 credentials. - A Telegram Bot with its token recorded in the Telegram Node Credentials. - A Google Sheet with two columns (initialText: words in your own language, translatedText: words in the target language). Next Steps Follow the sticky notes to set up the parameters inside each node and get ready to pump your learning skills. Notes This workflow can be used for any language. In the AI Agent prompt, you just need to replace Chinese with your language. This workflow has been created with N8N 1.82.1. Submitted: March 23th, 2025

📄 Description This automation workflow enables users to upload files via an N8N form, automatically analyzes the content using Google Gemini agents, and delivers the analyzed results via email along with a chatbot link. The system leverages Llama Cloud API, Google Gemini LLM, Pinecone vector database, and Gmail to provide a seamless, multilingual content analysis experience. ✅ Prerequisites Before setting up this workflow, ensure the following are in place: - An active N8N instance. - Access to Llama Cloud API. - Google Gemini LLM API keys (for Translator & Analyzer agents). - A Pinecone account with an active index. - A Gmail account with API access configured. - Basic knowledge of N8N workflow setup. ⚙️ Setup InstructionsDeploy the N8N Form Create a public-facing form using N8N. Configure it to accept: - File uploads. - User email input. File Preprocessing Store the uploaded files temporarily. Organize and preprocess them as needed. Content Extraction using Llama Cloud API Feed the files into the Llama Cloud API. Extract and parse the content for further processing. Translation (if required) Use a Translator Agent (Google Gemini). Check if the content is in English. If not, translate it. Content Analysis Forward the (translated) content to the Analyzer Agent (Google Gemini). Perform deep analysis to extract insights. Vector Storage in Pinecone Store both: - The parsed and translated content. - The analyzed content. Use Pinecone to store the content as embeddings for chatbot use. User Notification via Gmail Send the analyzed content and chatbot link to the user’s provided email using Gmail API. 🧩 Customization Guidance To add more languages: Update the translation logic to include additional language support. To modify analysis depth: Adjust the prompts sent to the Gemini Analyzer Agent. To change the chatbot behavior: Retrain or reconfigure the chatbot to utilize the new Pinecone index contextually. 🔁 Workflow Summary - User uploads files and email via N8N form. - Files are parsed using Llama Cloud API. - Content is translated (if needed) using Gemini Translator Agent. - Translated content is analyzed by the Gemini Analyzer Agent. - Parsed and analyzed data is stored in Pinecone. - User receives email with analyzed results and a chatbot link.

Who is this for? This workflow is for small business owners, personal assistants, or project managers who rely on multiple platforms for communication and scheduling. Ideal for users managing customer support, personal scheduling, or group event coordination via LINE, Google Calendar, and Gmail. What problem is this workflow solving? Reduces the manual effort needed to manage conversations, schedule events, and handle email communications. Provides an intelligent system for replying to user messages and fetching relevant calendar or email information in real time. Bridges the gap between messaging platforms and productivity tools, improving efficiency. What this workflow does - LINE Chatbot Automation: Automatically processes and responds to messages received via LINE. - Google Calendar Management: Retrieves upcoming events or schedules new events dynamically based on user queries. - Email Retrieval: Fetches recent emails using Gmail and filters them based on user instructions. - AI-Powered Replies: Uses OpenAI GPT to interpret user queries and provide tailored responses. SetupPrerequisites: - LINE Developer account and API access. - Google Calendar and Gmail accounts with OAuth credentials. - An n8n instance with access to environment variables. Steps: 1. Set up environment variables (LINE_API_TOKEN and DYNAMIC_EMAIL). 2. Configure API credentials for Google Calendar and Gmail in n8n. 3. Test the workflow by sending a sample message via LINE. Enhancements: - Use sticky notes to provide inline instructions for each node. - Include a video walkthrough or a step-by-step document for first-time users. How to customize this workflow to your needs - Localization: Modify responses in the AI Agent node to match the language and tone of your audience. - Integration: Add more integrations like Slack or Microsoft Teams for additional notifications. - Advanced Filters: Add specific conditions to Gmail or Google Calendar nodes to fetch only relevant data, such as events with specific keywords or emails from certain senders. Advanced Use Cases - Customer Support: Automatically schedule meetings with clients based on their messages in LINE. - Event Management: Handle RSVP confirmations, event reminders, and email follow-ups for planned events. - Personalized Assistant: Use the workflow to act as a personal virtual assistant that syncs your schedule, replies to messages, and summarizes emails. Tips for Optimization - Edit Fields Node: Add a centralized node to configure dynamic inputs (e.g., tokens, emails, or thresholds) for easy updates. - Fallback Responses: Use a switch node to handle unrecognized input gracefully and provide clear feedback to users. - Logs and Monitoring: Add nodes to log interactions and track message flows for debugging or analytics. Let me know if you'd like me to expand on any specific section or add more customization ideas!

The News Site from Colt, a telecom company, does not offer an RSS feed; therefore, web scraping is the choice to extract and process the news. The goal is to get only the newest posts, a summary of each post, and their respective (technical) keywords. Note that the news site offers the links to each news post, but not the individual news. We collect first the links and dates of each post before extracting the newest ones. The result is sent to a SQL database, in this case, a NocoDB database. This process happens each week through a cron job. Requirements: - Basic understanding of CSS selectors and how to get them via browser (usually: right click → inspect) - ChatGPT API account - normal account is not sufficient - A NocoDB database - of course you may choose any type of output target Assumptions: - CSS selectors work on the news site - The post has a date with its own CSS selector - meaning the date is not part of the news content Warnings: - Not every site likes to be scraped, especially not with high frequency. - Each website is structured in different ways; the workflow may then need several adaptations.

This n8n template lets you summarize team member activity on Slack for the past week and generates a report. For remote teams, chat is a crucial communication tool to ensure work gets done. With so many conversations happening at once and in multiple threads, ideas, information, and decisions usually live in the moment and get lost just as quickly—often forgotten by the weekend! Using this template, this doesn't have to be the case. Have AI crawl through last week's activity, summarize all threads, and generate a casual and snappy report to bring the team back into focus for the current week. A project manager's dream! How it works A scheduled trigger is set to run every Monday at 6 AM to gather all team channel messages within the last week. Each message thread is grouped by user and data mined for replies. Combined, an AI analyzes the raw messages to pull out interesting observations and highlights. The summarized threads of the user are then combined together and passed to another AI agent to generate a higher-level overview of their week. These are referred to as the individual reports. Next, all individual reports are summarized together into a team weekly report. This allows understanding of group and similar activities. Finally, the team weekly report is posted back to the channel. The timing is important as it should be the first message of the week and ready for the team to glance over coffee. How to use Ideally, this works best per project and where most of the communications happen on a single channel. Avoid combining channels and instead duplicate this workflow for more channels. You may need to filter for specific team members if you want specific team updates. Customize the report to suit your organization, team, or the channel. You may prefer to be more formal if clients or external stakeholders are also present. Customizing this workflow If the Slack channel is busy enough already, consider posting the final report to email. Pull in project metrics to include in your report. As extra context, it may be interesting to tie the messages to production performance. Use an AI agent to query for knowledgebase or tickets relevant to the messages. This may be useful for attaching links or references to add context. Channel not so busy or way too busy for one week? Play with the scheduled trigger and set an interval that works for your team.

This workflow template provides a robust solution for efficiently sending multiple prompts to Anthropic's Claude models in a single batch request and retrieving the results. It leverages the Anthropic Batch API endpoint (/v1/messages/batches) for optimized processing and outputs each result as a separate item. Core Functionality & Example Usage Included This template includes: - The Core Batch Processing Workflow: Designed to be called by another n8n workflow. - An Example Usage Workflow: A separate branch demonstrating how to prepare data and trigger the core workflow, including examples using simple strings and n8n's Langchain Chat Memory nodes. Who is this for? This template is designed for: - Developers, data scientists, and researchers who need to process large volumes of text prompts using Claude models via n8n. - Content creators looking to generate multiple pieces of content (e.g., summaries, Q&As, creative text) based on different inputs simultaneously. - n8n users who want to automate interactions with the Anthropic API beyond single requests, improve efficiency, and integrate batch processing into larger automation sequences. - Anyone needing to perform bulk text generation or analysis tasks with Claude programmatically. What problem does this workflow solve? Sending prompts to language models one by one can be slow and inefficient, especially when dealing with hundreds or thousands of requests. This workflow addresses that by: - Batching: Grouping multiple prompts into a single API call to Anthropic's dedicated batch endpoint (/v1/messages/batches). - Efficiency: Significantly reducing the time required compared to sequential processing. - Scalability: Handling large numbers of prompts (up to API limits) systematically. - Automation: Providing a ready-to-use, callable n8n structure for batch interactions with Claude. - Structured Output: Parsing the results and outputting each individual prompt's result as a separate n8n item. Use Cases: - Bulk content generation (e.g., product descriptions, summaries). - Large-scale question answering based on different contexts. - Sentiment analysis or data extraction across multiple text snippets. - Running the same prompt against many different inputs for research or testing. What the Core Workflow does (Triggered by the 'When Executed by Another Workflow' node) 1. Receive Input: The workflow starts when called by another workflow (e.g., using the 'Execute Workflow' node). It expects input data containing: - anthropic-version (string, e.g., "2023-06-01") - requests (JSON array, where each object represents a single prompt request conforming to the Anthropic Batch API schema). 2. Submit Batch Job: Sends the formatted requests data via POST to the Anthropic API /v1/messages/batches endpoint to create a new batch job. Requires Anthropic credentials. 3. Wait & Poll: Enters a loop: - Checks if the processing_status of the batch job is ended. - If not ended, it waits for a set interval (10 seconds by default in the 'Batch Status Poll Interval' node). - It then checks the batch job status again via GET to /v1/messages/batches/{batch_id}. Requires Anthropic credentials. - This loop continues until the status is ended. 4. Retrieve Results: Once the batch job is complete, it fetches the results file by making a GET request to the results_url provided in the batch status response. Requires Anthropic credentials. 5. Parse Results: The results are typically returned in JSON Lines (.jsonl) format. The 'Parse response' Code node splits the response text by newlines and parses each line into a separate JSON object, storing them in an array field (e.g., parsed). 6. Split Output: The 'Split Out Parsed Results' node takes the array of parsed results and outputs each result object as an individual item from the workflow. Prerequisites - An active n8n instance (Cloud or self-hosted). - An Anthropic API account with access granted to Claude models and the Batch API. - Your Anthropic API Key. - Basic understanding of n8n concepts (nodes, workflows, credentials, expressions, 'Execute Workflow' node). - Familiarity with JSON data structures for providing input prompts and understanding the output. - Understanding of the Anthropic Batch API request/response structure. - (For Example Usage Branch) Familiarity with n8n's Langchain nodes (@n8n/n8n-nodes-langchain) if you plan to adapt that part. Setup - Import Template: Add this template to your n8n instance. - Configure Credentials: - Navigate to the 'Credentials' section in your n8n instance. - Click 'Add Credential'. - Search for 'Anthropic' and select the Anthropic API credential type. - Enter your Anthropic API Key and save the credential (e.g., name it "Anthropic account"). - Assign Credentials: Open the workflow and locate the three HTTP Request nodes in the core workflow: - Submit batch - Check batch status - Get results - In each of these nodes, select the Anthropic credential you just configured from the 'Credential for Anthropic API' dropdown. - Review Input Format: Understand the required input structure for the When Executed by Another Workflow trigger node. The primary inputs are anthropic-version (string) and requests (array). Refer to the Sticky Notes in the template and the Anthropic Batch API documentation for the exact schema required within the requests array. - Activate Workflow: Save and activate the core workflow so it can be called by other workflows. ➡️ Quick Start & Input/Output Examples: Look for the Sticky Notes within the workflow canvas! They provide crucial information, including examples of the required input JSON structure and the expected output format. How to customize this workflow - Input Source: The core workflow is designed to be called. You will build another workflow that prepares the anthropic-version and requests array and then uses the 'Execute Workflow' node to trigger this template. The included example branch shows how to prepare this data. - Model Selection & Parameters: Model (claude-3-opus-20240229, etc.), max_tokens, temperature, and other parameters are defined within each object inside the requests array you pass to the workflow trigger. You configure these in the workflow calling this template. - Polling Interval: Modify the 'Wait' node ('Batch Status Poll Interval') duration if you need faster or slower status checks (default is 10 seconds). Be mindful of potential rate limits. - Parsing Logic: If Anthropic changes the result format or you have specific needs, modify the Javascript code within the 'Parse response' Code node. - Error Handling: Enhance the workflow with more specific error handling for API failures (e.g., using 'Error Trigger' or checking HTTP status codes) or batch processing issues (batch.status === 'failed'). - Output Processing: In the workflow that calls this template, add nodes after the 'Execute Workflow' node to process the individual result items returned (e.g., save to a database, spreadsheet, send notifications). Example Usage Branch (Manual Trigger) This template also contains a separate branch starting with the Run example Manual Trigger node. Purpose: This branch demonstrates how to construct the necessary anthropic-version and requests array payload. Methods Shown: It includes steps for: - Creating a request object from a simple query string. - Creating a request object using data from n8n's Langchain Chat Memory nodes (@n8n/n8n-nodes-langchain). Execution: It merges these examples, constructs the final payload, and then uses the Execute Workflow node to call the main batch processing logic described above. It finishes by filtering the results for demonstration. Note: This branch is for demonstration and testing. You would typically build your own data preparation logic in a separate workflow. The use of Langchain nodes is optional for the core batch functionality. Notes - API Limits: According to the Anthropic API documentation, batches can contain up to 100,000 requests and be up to 256 MB in total size. Ensure your n8n instance has sufficient resources for large batches. - API Costs: Using the Anthropic API, including the Batch API, incurs costs based on token usage. Monitor your usage via the Anthropic dashboard. - Completion Time: Batch processing time depends on the number and complexity of prompts and current API load. The polling mechanism accounts for this variability. - Versioning: Always include the anthropic-version header in your requests, as shown in the workflow and examples. Refer to Anthropic API versioning documentation.

Tags: Accessibility, SEO, Blogging, Marketing, Automation, AI, Web Auditing Context Hey! I’m Samir, a Supply Chain Engineer and Data Scientist from Paris, and the founder of LogiGreen Consulting. In my personal blog, I share insights on how to use AI, automation, and data analytics to improve logistics, operations, and digital sustainability practices. Have you heard about accessibility? In this workflow, I use n8n to improve the quality of alternative texts for images on my personal website. 📬 For business inquiries, you can connect with me on LinkedIn.Who is this template for? This workflow is for: - Bloggers and website owners who want to improve accessibility - SEO professionals looking to boost page performance - Web developers and product teams automating web auditsWhat does it do? This n8n workflow: - 🔍 Downloads the HTML of a blog or web page - 🖼️ Extracts all <img> tags and their alt attributes - 📉 Detects missing or too-short alt texts - 🤖 Sends those images to GPT-4o (with vision) to generate new alt descriptions - 📄 Saves the results into a Google Sheet, updating the alt text when neededHow it works - Set a page URL using the Set node - Download HTML content - Extract image src and alt using a Code node - Store results in a Google Sheet - Filter images with altLength < 50 - Send image URL to GPT-4o - Update the Google Sheet with the newly generated newAlt text The AI alt texts are concise, descriptive, and accessibility-compliant.What do I need to get started? You’ll need: - A Google Sheet to store the audit results - An OpenAI account with GPT-4o accessFollow the Guide! Follow the sticky notes in the workflow or check my tutorial to configure each node and start using AI to improve the accessibility of your website. 🎥 Watch My TutorialNotes - GPT-generated alt texts are limited to ~125–150 characters for best results - Use this to comply with WCAG and improve Google indexing - Easily adapt it to audit multiple domains or e-commerce catalogues This workflow was built using n8n version 1.85.4Submitted: April 21, 2025

This workflow retrieves Google Analytics data from the last 7 days and the same period in the previous year. The data is then prepared by AI as a table, analyzed, and provided with a small summary. The summary is then sent by email to a desired address and, shortened and summarized again, sent to a Telegram account. This workflow has the following sequence: - Time trigger (e.g. every Monday at 7 a.m.) - Retrieval of Google Analytics data from the last 7 days - Assignment and summary of the data - Retrieval of Google Analytics data from the last 7 days of the previous year - Allocation and summary of the data - Preparation in tabular form and brief analysis by AI - Sending the report as an email - Preparation in short form by AI for Telegram (optional) - Sending as a Telegram message. Requirements The following accesses are required for the workflow: - Google Analytics (via Google Analytics API) - AI API access (e.g. via OpenAI, Anthropic, Google or Ollama) - SMTP access data (for sending the mail) - Telegram access data (optional for sending as a Telegram message) Feel free to contact me via LinkedIn if you have any questions!

This template is for Self-Hosted N8N Instances only. This n8n demonstrates how to build a simple SQLite MCP server to perform local database operations as well as use it for Business Intelligence. This MCP example is based off an official MCP reference implementation which can be found here: https://github.com/modelcontextprotocol/servers/tree/main/src/sqlite. How it works A MCP server trigger is used and connected to 5 tools: 2 Code Node and 3 Custom Workflow. The 2 Code Node tools use the SQLite3 library and are simple read-only queries; as such, the Code Node tool can be simply used. The 3 custom workflow tools are used for select, insert, and update queries as these are operations which require a bit more discretion. While it may be easier to allow the agent to use raw SQL queries, we may find it a little safer to just allow for the parameters instead. The custom workflow tool allows us to define this restricted schema for tool input which we'll use to construct the SQL statement ourselves. All 3 custom workflow tools trigger the same "Execute workflow" trigger in this very template which has a switch to route the operation to the correct handler. Finally, we use our Code nodes to handle select, insert, and update operations. The responses are then sent back to the MCP client. How to use This SQLite MCP server allows any compatible MCP client to manage a SQLite database by supporting select, create, and update operations. You will need to have a SQLite database available before you can use this server. Connect your MCP client by following the n8n guidelines found here: https://docs.n8n.io/integrations/builtin/core-nodes/n8n-nodes-langchain.mcptrigger/#integrating-with-claude-desktop. Try the following queries in your MCP client: - "Please create a table to store business insights and add the following..." - "What business insights do we have on current retail trends?" - "Who has contributed the most business insights in the past week?" Customising this workflow If the scope of schemas or tables is too open, try to restrict it so the MCP serves a specific purpose for business operations. For example, confine the querying and editing to HR only tables before providing access to people in that department. Remember to set the MCP server to require credentials before going to production and sharing this MCP server with others!

This workflow allows you to collect tweets, store them in MongoDB, analyze their sentiment, insert them into a Postgres database, and post positive tweets in a Slack channel. Cron node: Schedule the workflow to run every day. Twitter node: Collect tweets. MongoDB node: Insert the collected tweets in MongoDB. Google Cloud Natural Language node: Analyze the sentiment of the collected tweets. Set node: Extract the sentiment score and magnitude. Postgres node: Insert the tweets and their sentiment score and magnitude in a Postgres database. IF node: Filter tweets with positive and negative sentiment scores. Slack node: Post tweets with a positive sentiment score in a Slack channel. NoOp node: Ignore tweets with a negative sentiment score.

This workflow automates document summarization directly from Google Drive, processes the content using Mistral AI, and delivers a clean, styled summary via Gmail. It's ideal for professionals who need quick insights from lengthy documents without manually reading through them. Key Features: - Google Drive Integration: Fetches a file (PDF/DOCX) from your Drive. - AI Summarization: Uses Mistral AI to extract key points efficiently. - Styled Email Output: Delivers a formatted, easy-to-read summary to your inbox with a timestamp. - Error Handling: Built to skip corrupted files or missing credentials. Nodes Breakdown: 1. Manual Trigger — Starts the workflow manually for easy testing. 2. Google Drive Node — Downloads a specified file from Google Drive (supports PDF/DOCX). 3. Mistral Cloud Chat Model Node — Connects to Mistral AI for summarization. 4. Summarization Chain Node — Breaks the file into chunks, processes content, and generates a concise summary. 5. Gmail Node — Sends the styled summary directly to the user’s inbox, with custom formatting and current time in the Lagos timezone. Extra Features: - Dynamic Time Formatting: Supports Lagos timezone (easily adjustable). - HTML Styling: Beautiful email formatting with headers, icons, and line breaks for clarity. - Custom Email Sender Name: Branded output (e.g., "Swot.AI"). - Future Expansion: Can extend to WhatsApp or Slack with minor tweaks. Use Cases: - Legal teams summarizing contracts. - Content creators extracting highlights from research papers. - Business analysts getting insights from reports on-the-go. Customization Tips: - Change the timezone (Africa/Lagos) to match your preferred location. - Add error-handling nodes for missing files or API failures. - Swap Mistral AI with OpenAI for different summarization behavior. - Change the "Send To" address (email to receive the summarized texts) with your personal preferred address. - Change the "Sender Name" from Swot.AI to your preferred Sender Name. Why To Use This Workflow? This automation saves hours of manual reading. It’s perfect for personal productivity, legal analysis, content creation, or business reporting. With clean formatting and a professional email summary — your team will get instant insights in seconds!

Purpose of workflow: The purpose of this workflow is to automate scraping of a website, transforming it into a structured format, and loading it directly into a Google Sheets spreadsheet. How it works:Web Scraping: Uses the Jina AI service to scrape website data and convert it into LLM-friendly text. Information Extraction: Employs an AI node to extract specific book details (title, price, availability, image URL, product URL) from the scraped data. Data Splitting: Splits the extracted information into individual book entries. Google Sheets Integration: Automatically populates a Google Sheets spreadsheet with the structured book data. Step by step setup: 1. Set up Jina AI service: Sign up for a Jina AI account and obtain an API key. 2. Configure the HTTP Request node: Enter the Jina AI URL with the target website. Add the API key to the request headers for authentication. 3. Set up the Information Extractor node: Use Claude AI to generate a JSON schema for data extraction. Upload a screenshot of the target website to Claude AI. Ask Claude AI to suggest a JSON schema for extracting required information. Copy the generated schema into the Information Extractor node. 4. Configure the Split node: Set it up to separate the extracted data into individual book entries. 5. Set up the Google Sheets node: Create a Google Sheets spreadsheet with columns for title, price, availability, image URL, and product URL. Configure the node to map the extracted data to the appropriate columns.

This workflow automates the Mark as Fulfilled action in Shopify for each order, ensuring a seamless fulfillment process without manual intervention. This workflow retrieves all unfulfilled orders and processes their fulfillment automatically. Since Shopify requires a Fulfillment Order ID (not Order ID) to trigger fulfillment, the workflow follows these steps: 1️⃣ Get all unfulfilled orders using the Shopify node. 2️⃣ Retrieve the Fulfillment Order ID using the "List Fulfillment Orders" action. 3️⃣ Create a fulfillment request using "Mark fulfillment order as fulfilled." 4️⃣ Handle edge cases, such as partially fulfilled orders or API errors. This ensures that every valid order is marked as fulfilled efficiently. 🔗 Ongoing discussions on this topic: Relevant Shopify API Discussion The workflow can be run as requested or on schedule. You can adjust these parameters within the Shopify and filter nodes: - Shopify Admin URL – A Global node to customize the Shopify store URL. To find your Shopify store ID, log in to your Shopify admin, then look at the URL in your browser's address bar; the subdomain portion (e.g., example_store_id.myshopify.com) is your store ID (in this case: example_store_id). - Order Filtering – Ensures only valid orders are fulfilled, particularly useful if you sell digital downloads or gift cards exclusively, or if you use third-party fulfillment services for all products. Credentials To run this workflow, you'll need: - Shopify API Key – Required for authentication. Who Is This For? - Shopify store owners looking to automate their fulfillment process. - Merchants selling digital or personalized products who need instant fulfillment.

How it works This workflow adds a priority to each Todoist item in your inbox, based on a list of projects that you add in the workflow. Setup - Add your Todoist credentials - Add your OpenAI credentials - Set your project names and add priority

Automate Pinterest Analysis & AI-Powered Content Suggestions With Pinterest API This workflow automates the collection, analysis, and summarization of Pinterest Pin data to help marketers optimize content strategy. It gathers Pinterest Pin performance data, analyzes trends using an AI agent, and delivers actionable insights to the Marketing Manager via email. This setup is ideal for content creators and marketing teams who need weekly insights on Pinterest trends to refine their content calendar and audience engagement strategy. Prerequisites Before setting up this workflow, ensure you have the following: - Pinterest API Access & Developer Account Sign up at Pinterest Developers and obtain API credentials. Ensure you have access to both Organic and Paid Pin data. - Airtable Account & API Key Create an account at Airtable and set up a database. Obtain an API key from Account Settings. - AI Agent for Trend Analysis An AI-powered agent (such as OpenAI's GPT or a custom ML model) is required to analyze Pinterest trends. Ensure integration with your workflow automation tool (e.g., Zapier, Make, or a custom Python script). - Email Automation Setup Configure an SMTP email service (e.g., Gmail, Outlook, SendGrid) to send the summarized results to the Marketing Manager. Step-by-Step Guide to Automating Pinterest Pin Analysis 1. Scheduled Trigger for Data Collection At 8:00 AM (or your preferred time), an automated trigger starts the workflow. Adjust the timing based on your marketing schedule to optimize trend tracking. 2. Fetch Data from Pinterest API Retrieve recent Pinterest Pin performance data, including impressions, clicks, saves, and engagement rate. Ensure both Organic and Paid Ads data are labeled correctly for clarity. 3. Store Data in Airtable Pins are logged and categorized in an Airtable database for further analysis. Sample Airtable Template for Pinterest Pins - Column Name: Description - pin_id: Unique identifier for each Pin - created_at: Timestamp of when the Pin was created - title: Title of the Pin - description: Short description of the Pin - link: URL linking to the Pin - type: Type of Pin (e.g., organic, ad) 4. AI Agent Analyzes Pinterest Trends The AI model reviews the latest Pinterest data and identifies: - Trending Topics & Keywords - Engagement Patterns - Audience Interests & Behavior Changes - Optimal Posting Times & Formats 5. Generate Content Suggestions with AI The AI Agent recommends new Pin ideas and content calendar updates to maximize engagement. Suggestions include creative formats, hashtags, and timing adjustments for better performance. 6. Summary & Insights Generated by AI A concise report is created, summarizing Pinterest trends and actionable insights for content strategy. 7. Email Report Sent to the Marketing Manager The summary is emailed to the Marketing Manager to assist with content planning and execution. The report includes: - Performance Overview of Recent Pins - Trending Content Ideas - Best Performing Pin Formats - AI-Generated Recommendations This workflow enables marketing teams to automate Pinterest analysis and optimize their content strategy through AI-driven insights. 🚀

This workflow template creates an AI agent chatbot with long-term memory and note storage using Google Docs and Telegram integration. Google Docs Integration 📄 - n8n Google Docs Node Setup - Google Credentials Telegram Integration 💬 - Telegram Setup Core Features 🌟 - AI Agent Integration 🤖 Implements a sophisticated AI agent with memory management capabilities. Uses GPT-4o-mini and DeepSeek models for intelligent conversation handling. Maintains context awareness through session management. - Memory System 🧠 Long-term memory storage using Google Docs. Separate note storage system for specific information. Window buffer memory for maintaining conversation context. Intelligent memory retrieval and storage mechanisms. - Communication Interface 💬 Telegram integration for message handling. Real-time message processing and response generation. Technical Components 🔧 - Memory Architecture 📚 Dual storage system separating memories from notes. Automated memory retrieval before each interaction. Structured memory saving with timestamps. - AI Models 🤖 Primary GPT-4o-mini mini model for general interactions. DeepSeek-V3 Chat for specialized processing. Custom agent system with tool integration. - Storage Integration 💾 Google Docs integration for persistent storage. Separate document management for memories and notes. Automated document updates and retrievals.

Your workflow is an intelligent chatbot, using OpenAI assistant, integrated with a backend that supports WhatsApp Business, designed to handle various use cases such as sales and customer support. Below is a breakdown of its functionality and key components: Workflow Structure and FunctionalityChat Input (Chat Trigger) The flow starts by receiving messages from customers via WhatsApp Business. It collects basic information, such as session_id, to organize interactions. Condition Check (If Node) Checks if additional customer data (e.g., name, age, dependents) is sent along with the message. If additional data is present, a customized prompt is generated, which includes this information. The prompt specifies that this data is for the assistant's awareness and doesn’t require a response. Data Preparation (Edit Fields Nodes) Formats customer data and the interaction details to be processed by the AI assistant. Compiles the customer data and their query into a single text block. AI Responses (OpenAI Nodes) The assistant’s prompt is carefully designed to guide the AI in providing accurate and relevant responses based on the customer’s query and data provided. Prompts describe the available functionalities, including which APIs to call and their specific purposes, helping to prevent “hallucinated” or irrelevant responses. Memory and Context (Postgres Chat Memory) Stores context and messages in continuous sessions using a database, ensuring the chatbot maintains conversation history. API Calls The workflow allows the use of APIs with any endpoints you choose, depending on your specific use case. This flexibility enables integration with various services tailored to your needs. The OpenAI assistant understands JSON structures, and you can define in the prompt how the responses should be formatted. This allows you to structure responses neatly for the client, ensuring clarity and professionalism. Make sure to describe the purpose of each endpoint in the assistant’s prompt to help guide the AI and prevent misinterpretation. Customer Response Delivery After processing and querying APIs, the generated response is sent to the backend and ultimately delivered to the customer through WhatsApp Business. Best Practices ImplementedPreventing Hallucinations Every API has a clear description in its prompt, ensuring the AI understands its intended use case. Versatile Functionality The chatbot is modular and flexible, capable of handling both sales and general customer inquiries. Context Persistence By utilizing persistent memory, the flow maintains continuous interaction context, which is crucial for longer conversations or follow-up queries. Additional Recommendations Include practical examples in the assistant’s prompt, such as frequently asked questions or decision-making flows based on API calls. Ensure all responses align with the customer’s objectives (e.g., making a purchase or resolving technical queries). Log interactions in detail for future analysis and workflow optimization. This workflow provides a solid foundation for a robust and multifunctional virtual assistant 🚀