Agents & Automations

Video Guide I prepared a comprehensive guide detailing how to create a Smart Agent that automates meeting task management by analyzing transcripts, generating tasks in Airtable, and scheduling follow-ups when necessary. Who is this for? This workflow is ideal for project managers, team leaders, and business owners looking to enhance productivity during meetings. It is particularly helpful for those who need to convert discussions into actionable items swiftly and effectively. What problem does this workflow solve? Managing action items from meetings can often lead to missed tasks and poor follow-up. This automation alleviates that issue by automatically generating tasks from meeting transcripts, keeping everyone informed about their responsibilities and streamlining communication. What this workflow does The workflow leverages n8n to create a Smart Agent that listens for completed meeting transcripts, processes them using AI, and generates tasks in Airtable. Key functionalities include: - Capturing completed meeting events through webhooks. - Extracting relevant meeting details such as transcripts and participants using API calls. - Generating structured tasks from meeting discussions and sending notifications to clients. SetupWebhook Integration: Listens for meeting completion events to trigger subsequent actions. API Requests for Data: Pulls necessary details like transcripts and participant information from Fireflies. Task and Notification Generation: Automatically creates tasks in Airtable and notifies clients of their responsibilities. AI Processing Setup: Define system messages for AI tasks and configure connections to the AI chat model (e.g., OpenAI's GPT) to process transcripts. Task Creation Logic: Create structured tasks based on AI output, ensuring necessary details are captured and records are created in Airtable. Client Notifications: Use an email node to notify clients about their tasks, ensuring communications are client-specific. Scheduling Follow-Up Calls: Set up Google Calendar events if follow-up meetings are required, populating details from the original meeting context.

Who is this for? - Content strategists analyzing web page semantic content - SEO professionals conducting entity-based analysis - Data analysts extracting structured data from web pages - Marketers researching competitor content strategies - Researchers organizing and categorizing web content - Anyone needing to automatically extract entities from web pages What problem is this workflow solving? Manually identifying and categorizing entities (people, organizations, locations, etc.) on web pages is time-consuming and error-prone. This workflow solves this challenge by: - Automating the extraction of named entities from any web page - Leveraging Google's powerful Natural Language API for accurate entity recognition - Processing web pages through a simple webhook interface - Providing structured entity data that can be used for analysis or further processing - Eliminating hours of manual content analysis and categorization What this workflow does This workflow creates an automated pipeline between a webhook and Google's Natural Language API to: - Receive a URL through a webhook endpoint - Fetch the HTML content from the specified URL - Clean and prepare the HTML for processing - Submit the HTML to Google's Natural Language API for entity analysis - Return the structured entity data through the webhook response - Extract entities including people, organizations, locations, and more with their salience scores SetupPrerequisites: - An n8n instance (cloud or self-hosted) - Google Cloud Platform account with Natural Language API enabled - Google API key with access to the Natural Language API Google Cloud Setup: 1. Create a project in Google Cloud Platform 2. Enable the Natural Language API for your project 3. Create an API key with access to the Natural Language API 4. Copy your API key for use in the workflow n8n Setup: 1. Import the workflow JSON into your n8n instance 2. Replace "YOUR-GOOGLE-API-KEY" in the "Google Entities" node with your actual API key 3. Activate the workflow to enable the webhook endpoint 4. Copy the webhook URL from the "Webhook" node for later use Testing: 1. Use a tool like Postman or cURL to send a POST request to your webhook URL 2. Include a JSON body with the URL you want to analyze: {"url": "<https://example.com>"} 3. Verify that you receive a response containing the entity analysis data How to customize this workflow to your needsAnalyzing Specific Entity - Modify the "Google Entities" node parameters to include entityType filters - Add a "Function" node after "Google Entities" to filter specific entity types - Create conditions to extract only entities of interest (people, organizations, etc.) Processing Multiple URLs in Batch: - Replace the webhook with a different trigger (HTTP Request, Google Sheets, etc.) - Add a "Split In Batches" node to process multiple URLs - Use a "Merge" node to combine results before sending the response Enhancing Entity Data: - Add additional API calls to enrich extracted entities with more information - Implement sentiment analysis alongside entity extraction - Create a data transformation node to format entities by type or relevance Additional Notes - This workflow respects Google's API rate limits by processing one URL at a time. - The Natural Language API may not identify all entities on a page, particularly for highly technical content. - HTML content is trimmed to 100,000 characters if longer to avoid API limitations. - Consider legal and privacy implications when analyzing and storing entity data from web pages. - You may want to adjust the HTML cleaning process for specific website structures.

What's the workflow used for? Leverage this Kling API (unofficial) provided by PiAPI workflow to streamline virtual try-on video creation. This tool is designed for e-commerce platforms, fashion brands, content creators, and content influencers. By uploading model and clothing images and linking your PiAPI account, users can swiftly generate a realistic video of the model sporting the outfit with a 360° turn, offering an immersive viewing experience. Step-by-step Instruction For basic settings of virtual try-on, check the API documentation for best practices. 1. Fill in your X-API-Key of your PiAPI account in the Preset Parameters node. 2. Upload the model photo and provide target clothing image URLs. 3. Click Test Workflow to generate the virtual try-on image. 4. Get the video output in the final node. Param Settings - If you want to change into a dress, input the model_input URL and the dress_input URL in the parameters. - If you want to change into separates, input model_input URL, upper_input URL, and lower_input URL in Preset Parameters. Use Case Input images: Output Video: The output demonstrates that the model is wearing the clothing from the specified image and showcases a rotating runway-style view. This workflow enables you to efficiently test garment-on-model presentation effects while reducing business model validation costs to a certain extent.

Execute this automation on a specific schedule to filter Google Sheets rows, generate AI responses with ChatGPT, and update rows, streamlining data management and enhancing decision-making.

Easily generate images with Black Forest's Flux Text-to-Image AI models using Hugging Face’s Inference API. This template serves a webform where you can enter prompts and select predefined visual styles that are customizable with no-code. The workflow integrates seamlessly with Hugging Face's free tier, and it’s easy to modify for any Text-to-Image model that supports API access. Key Features: - Text-to-Image Creation: Generates unique visuals based on your prompt and style. - Hugging Face Integration: Utilizes Hugging Face’s Inference API for reliable image generation. - Customizable Visual Styles: Select from preset styles or easily add your own. - Adaptable: Swap in any Hugging Face Text-to-Image model that supports API calls. Ideal for: - Creators: Rapidly create visuals for projects. - Marketers: Prototype campaign visuals. - Developers: Test different AI image models effortlessly. How It Works: You submit an image prompt via the webform and select a visual style, which appends style instructions to your prompt. The Hugging Face Inference API then generates and returns the image, which gets hosted on Cloudflare S3. The workflow can be easily adjusted to use other models and styles for complete flexibility.

Telegram Personal Assistant with Long-Term Memory & Note-Taking This n8n workflow transforms your Telegram bot into a powerful personal assistant that handles voice, photo, and text messages. The assistant uses AI to interpret messages, save important details as long-term memories or notes in a Baserow database, and recall information for future interactions. 🌟 How It WorksMessage Reception & Routing - Telegram Integration: The workflow is triggered by incoming messages on your Telegram bot. - Dynamic Routing: A switch node inspects the message to determine whether it's voice, text, or photo (with captions) and routes it for the appropriate processing. Content Processing - Voice Messages: Audio files are retrieved and sent to an AI transcription node to convert spoken words into text. - Text Messages: Text is directly captured and prepared for analysis. - Photos: If an image is received, the bot fetches the file (and caption, if provided) and uses an AI-powered image analysis node to extract relevant details. AI-Powered Agent & Memory Management The core AI agent (powered by GPT-4o-mini) processes the incoming message along with any previous conversation history stored in PostgreSQL memory buffers. - Long-Term Memory: When a message contains personal or noteworthy information, the assistant uses a dedicated tool to save this data as a long-term memory in Baserow. - Note-Taking: For specific instructions or reminders, the assistant saves concise notes in a separate Baserow table. The AI agent follows defined rules to decide which details are saved as memories and which are saved as notes. Response Generation After processing the message and updating memory/notes as needed, the AI agent crafts a contextual and personalized response. The response is sent back to the user via Telegram, ensuring smooth and natural conversation flow. 🚀 Key Features - Multimodal Input: Seamlessly handles voice, photo (with captions), and text messages. - Long-Term Memory & Note-Taking: Uses a Baserow database to store personal details and notes, enhancing conversational context over time. - AI-Driven Contextual Responses: Leverages an AI agent to generate personalized, context-aware replies based on current input and past interactions. - User Security & Validation: Incorporates validation steps to verify the user's Telegram ID before processing, ensuring secure and personalized interactions. - Easy Baserow Setup: Comes with a clear setup guide and sample configurations to quickly integrate Baserow for managing memories and notes. 🔧 Setup Guide - Telegram Bot Setup: Create your bot via BotFather and obtain the Bot Token. Configure the Telegram webhook in n8n with your bot's token and URL. - Baserow Database Configuration: - Memory Table: Create a workspace titled "Memories and Notes." Set up a table (e.g., "Memory Table") with at least two fields: Memory (long text) and Date Added (US date format with time). - Notes Table: Duplicate the Memory Table and rename it to "Notes Table." Change the first field's name from "Memory" to "Notes." - n8n Workflow Import & Configuration: Import the workflow JSON into your n8n instance. Update credentials for Telegram, Baserow, OpenAI, and PostgreSQL (for memory buffering) as needed. Adjust node settings if you need to customize AI agent prompts or memory management rules. - Testing & Deployment: Test your bot by sending various message types (text, voice, photo) to confirm that the workflow processes them correctly, updates Baserow, and returns the appropriate response. Monitor logs to ensure that memory and note entries are correctly stored and retrieved. ✨ Example Interactions - Voice Message Processing: User sends a voice note requesting a reminder. Bot Response: "Thanks for your message! I've noted your reminder and saved it for future reference." - Photo with Caption: User sends a photo with the caption "Save this recipe for dinner ideas." Bot Response: "Got it! I've saved this recipe along with the caption for you." - Text Message for Memory Saving: User: "I love hiking on weekends." Bot Response: "Noted! I’ll remember your interest in hiking." - Retrieving Information: User asks: "What notes do I have?" Bot Response: "Here are your latest notes: [list of saved notes]." 🛠️ Resources & Next Steps - Telegram Bot Configuration: Telegram BotFather Guide - n8n Documentation: n8n Docs - Community Forums: Join discussions and share your customizations! This workflow not only streamlines message processing but also empowers users with a personal AI assistant that remembers details over time. Customize the rules and responses further to fit your unique requirements and enjoy a more engaging, intelligent conversation experience on Telegram!

Personal Portfolio CV Rag Chatbot - with Conversation Store and Email SummaryTarget Audience This template is perfect for: - Individuals looking to create a working professional and interactive personal portfolio chatbot. - Developers interested in integrating RAG Chatbot functionality with conversation storage.1. Description Create a stunning Personal Portfolio CV with integrated RAG Chatbot capabilities, including conversation storage and daily email summaries.2. Features:Training: Setup Ingestion stage Upload your CV to Google Drive and let the Drive trigger updates to read your resume CV and convert it into your vector database (RAG purpose). Modify any parts as needed.Chat & Track: Use any frontend/backend interface to call the chat API and chat history API.Reporting Daily Chat Conversations: Receive daily automatic summaries of chat conversations. Data stored via NocoDB.3. Setup Guide:Step-by-Step Instructions: Ensure all credentials are ready. Follow the notes provided.Ingestion: Upload your CV to Google Drive. The Drive triggers RAG update in your vector database. You can change the folder name, files, and index name of the vector database accordingly.Chat: Use any frontend/backend interface to call the chat API (refer to the notes for details). [optional] Use any frontend/backend interface to call the update chat history API (refer to the notes for details).3. Tracking Chat: Get daily automatic summaries of chat conversations. Format email conversations report as you like. You are ready to go!

Automate Instagram DMs with OpenAI GPT and ManyChat. How It Works: Once connected, GPT will automatically initiate conversations with messages from new recipients in Instagram. Who Is This For? This workflow is ideal for: - Marketers - Business owners - Content creators These individuals want to automatically respond to Instagram direct messages using OpenAI GPT. By integrating ManyChat, you can manage conversations, nurture leads, and provide instant replies at scale. What This Workflow Does: - Captures incoming Instagram DMs through ManyChat’s integration. - Processes messages with GPT to generate a relevant response. - Delivers instant replies back to Instagram users, creating efficient, AI-driven communication. Setup: 1. Import the Template: Copy the n8n workflow into your workspace. 2. OpenAI Credentials: Add your OpenAI API key in n8n so GPT can generate responses. 3. ManyChat Account: Create (or log in to) your ManyChat account. 4. Connect Instagram: Link your Instagram profile as a channel in ManyChat. 5. ManyChat Custom Field: Create a custom field for storing user input or conversation context. 6. Configure Default Reply: In ManyChat, set up the default Instagram reply flow to point to your n8n webhook. 7. Add External Request: Create an external request step in ManyChat to send messages to n8n. 8. Test the Flow: Send yourself a DM on Instagram to confirm the workflow triggers and GPT responds correctly.

Raise your Google keyword rankings using Browse AI's optimization strategies and improve your website's performance with ChatGPT's actionable suggestions. Ensure your robot fetches only 10 rankings for the scenario to work correctly. This template is the first of two in the series, providing a comprehensive approach to enhancing your SEO efforts.

This workflow gives you the ability to reply to a long email with a voice note, rather than having to type everything out. ChatGPT will format your audio response and create an email draft for you. How it works: When a new email arrives in your inbox, the workflow checks if it needs a response. If it does, it sends a message to you on Telegram via a VoiceEmailer bot. When you reply to that message with an audio message, the second part of this workflow is triggered. It checks if the message is in the right format, transcribes the audio, and creates a draft response that shows up in the same email thread. Set up steps: 1. Add your credentials for Gmail and OpenAI. 2. Create a Telegram bot following the instructions. 3. Connect your Telegram credentials so the workflow will use your bot. 4. Turn on the workflow, and message the bot from your Telegram. Find the Chat ID from the Executions tab of your workflow, and enter it in as a variable.

This workflow template, "Daily Gratitude Reminder Bot for LINE," is designed to help users cultivate a habit of gratitude by sending personalized, AI-generated reminders every evening at 9:00 PM. Using Azure OpenAI, the bot generates varied and engaging messages to prompt users to reflect on the positive aspects of their day. The reminders are then sent directly to users via the LINE messaging platform, ensuring a seamless and impactful experience. Whether you're a developer, counselor, or business owner, this template offers a customizable and scalable solution for promoting mental wellness and fostering a culture of gratitude. ### Who Is This Template For? - Developers who want to integrate AI-powered workflows into messaging platforms like LINE. - Counselors & Therapists looking to encourage mindfulness and emotional well-being among their clients. - Businesses & Organizations focused on employee wellness or customer engagement through positive reinforcement. - Educators & Nonprofits seeking tools to promote mental health awareness and self-care practices. ### What Problem Does This Workflow Solve? Gratitude journaling has been proven to improve mental health, reduce stress, and increase overall happiness. However, many people struggle to maintain the habit due to busy schedules or forgetfulness. This workflow solves that problem by automating daily reminders to reflect on positive experiences, making it easier for users to build and sustain a gratitude practice. ### What This Workflow Does - Scheduled Trigger: The workflow is triggered every evening at 9:00 PM using a schedule node. - AI-Powered Message Generation: An Azure OpenAI Chat Model generates a unique and engaging reminder message with a temperature setting of 0.9 to ensure variety and creativity. - Message Formatting: The generated message is reformatted to comply with the LINE Push API requirements, ensuring smooth delivery. - Push Notification via LINE: The formatted message is sent to the user via the LINE Push API, delivering the reminder directly to their chat. ### How to Customize This Workflow to Your Needs - Change the Time: Adjust the schedule trigger to send reminders at a different time. - Modify the Prompt: Edit the AI model's input prompt to generate messages tailored to your audience (e.g., focus on work achievements or personal growth). - Expand Recipients: Update the LINE Push API node to send reminders to multiple users or groups. - Integrate Additional Features: Add nodes to log user responses or track engagement metrics. ### Why Use This Template? - Promotes Mental Wellness: Encourages users to reflect on positive experiences, improving emotional well-being. - Highly Customizable: Easily adapt the workflow to suit different audiences and use cases. - Scalable: Send reminders to one user or thousands, making it suitable for both personal and organizational use. - AI-Powered Creativity: Avoid repetitive messages by leveraging AI to generate fresh and engaging content.

Create a RAG System with Paul Essays, Milvus, and OpenAI for Cited Answers. This workflow automates the process of creating a document-based AI retrieval system using Milvus, an open-source vector database. It consists of two main steps: 1. Data Collection and Processing - Set up a Milvus server using the official guide. - Create a collection named "my_collection." - Execute the workflow to scrape Paul Graham essays: - Fetch essay lists. - Extract names. - Split content into manageable items. - Limit results (if needed). - Fetch texts. - Extract content. - Load everything into Milvus Vector Store. This step uses OpenAI embeddings for vectorization. 2. Retrieval and Response Generation When a chat message is received, the system: - Sets chunks to send to the model. - Retrieves relevant information from the Milvus Vector Store. - Prepares chunks. - Answers the query based on those chunks. - Composes citations. - Generates a comprehensive response. This process uses OpenAI embeddings and models to ensure accurate and relevant answers with proper citations.

🎥 Summarize YouTube Videos using SearchApi & LLMWho is this for? This workflow is ideal for content creators, students, digital marketers, educators, and researchers who want to quickly summarize YouTube videos. What problem does this workflow solve? Manually extracting important information from lengthy YouTube videos can be tedious and prone to errors. This workflow streamlines the process by automatically fetching video transcripts using SearchApi.io and producing concise, informative summaries through a summarization chain powered by any LLM provider. This allows users to quickly access crucial information without the need for manual transcription or detailed viewing. What this workflow does - Fetches the complete transcript of a YouTube video using SearchApi. - Combines the retrieved transcript into a single, continuous text. - Utilizes a Summarization Chain with an LLM (e.g., OpenRouter models) to create a concise summary of the video content. Setup - Install the SearchApi community node: Open Settings → Community Nodes inside your self‑hosted n8n instance. Fill npm Package Name with @searchapi/n8n-nodes-searchapi. Accept the risk prompt, and hit Install. It should now appear as a node when you search for it. - API Configuration: Set up your SearchApi.io credentials in n8n. Add your preferred LLM provider credentials (e.g., OpenRouter API). - Input Requirements: Provide the YouTube video ID (e.g., wBuULAoJxok). - Connect LLM Integration: Configure the summarization chain with your chosen model and parameters for text splitting. How to customize this workflow to meet your needs - Adjust the summarization model or modify text-splitter parameters to accommodate different lengths and complexities of video transcripts. - Integrate additional nodes to export summaries directly into your preferred tools, such as Google Drive, Slack, or email. - Customize prompt templates in the summarization chain to obtain various summary styles (bullet points, paragraphs, etc.). - Modify the trigger to suit your workflow. Example Usage - Input: YouTube video ID (wBuULAoJxok). - Output: A concise, actionable summary that highlights key ideas, recommendations, and insights from the video.

Optimize your Pipedrive CRM lead engagement using ChatGPT to craft personalized introduction messages, while organizing and reviewing them on Google Sheets.

Disclaimer This template is only available on n8n self-hosted as it's making use of the community node for MCP Client. Who this is for? The Scrape Web Data with Bright Data and MCP Automated AI Agent workflow is built for professionals who need to automate large-scale, intelligent data extraction by utilizing the Bright Data MCP Server and Google Gemini. This solution is ideal for: - Data Analysts - Who require structured, enriched datasets for analysis and reporting. - Marketing Researchers - Seeking fresh market intelligence from dynamic web sources. - Product Managers - Who want competitive product and feature insights from various websites. - AI Developers - Aiming to feed web data into downstream machine learning models. - Growth Hackers - Looking for high-quality data to fuel campaigns, research, or strategic targeting. What problem is this workflow solving? Manually scraping websites, cleaning raw HTML data, and generating useful insights from it can be slow, error-prone, and non-scalable. This workflow solves these problems by: - Automating complex web data extraction through Bright Data’s MCP Server. - Reducing the human effort needed for cleaning, parsing, and analyzing unstructured web content. - Allowing seamless integration into further automation processes. What this workflow does? This n8n workflow performs the following steps: - Trigger: Start manually. - Input URL(s): Specify the URL to perform the web scraping. - Web Scraping (Bright Data): Use Bright Data’s MCP Server tools to accomplish the web data scraping with markdown and HTML format. - Store / Output: Save results into disk and also perform a Webhook notification. Setup Please make sure to set up n8n locally with MCP Servers by navigating to n8n-nodes-mcp. Please make sure to install the Bright Data MCP Server @brightdata/mcp on your local machine. Sign up at Bright Data. Create a Web Unlocker proxy zone called mcp_unlocker on the Bright Data control panel. Navigate to Proxies & Scraping and create a new Web Unlocker zone by selecting Web Unlocker API under Scraping Solutions. In n8n, configure the Google Gemini (PaLM) API account with the Google Gemini API key (or access through Vertex AI or proxy). In n8n, configure the credentials to connect with MCP Client (STDIO) account with the Bright Data MCP Server. Make sure to copy the Bright Data API_TOKEN within the Environments textbox above. Update the LinkedIn URL person and company workflow. Update the Webhook HTTP Request node with the Webhook endpoint of your choice. Update the file name and path to persist on disk. How to customize this workflow to your needs - Different Inputs: Instead of static URLs, accept URLs dynamically via webhook or form submissions. - Outputs: Update the Webhook endpoints to send the response to Slack channels, Airtable, Notion, CRM systems, etc.

How it works: Using a crew of AI agents (Senior Researcher, Visionary, and Senior Editor), this crew will automatically determine the right questions to ask to produce a detailed fundamental stock analysis. This application has two components: a front-end and a Stock Q&A engine. The front end is the team of agents automatically figuring out the questions to ask, and the back-end part is the ability to answer those questions with the SEC 10K data. For the front-end of the application, you can choose one of two options: - Using CrewAI with the Replit environment (code approach) - Fully visual approach with n8n template (AI-powered automated stock analysis) Setup steps: 1. Use the first workflow in the template to upsert a company annual report PDF (such as from SEC 10K filing). 2. Get the URL for the Webhook in the second workflow template. 3. Set the webhook URL into the N8N_WEBHOOK_URL variable. 4. Set the OpenAI_API_KEY variable.

This workflow template, "Personal Assistant to Note Messages and Extract Namecard Information," is designed to streamline the processing of incoming messages on the LINE messaging platform. It integrates with powerful tools like Microsoft Teams, Microsoft To Do, OneDrive, and OpenRouter.ai to handle tasks such as saving notes, extracting namecard information, and organizing images. Whether you’re managing personal productivity or automating workflows for teams, this template offers a versatile and customizable solution. By leveraging this workflow, you can automate repetitive tasks, improve collaboration, and enhance efficiency in handling LINE messages. Who Is This Template For? This template is ideal for: - Professionals: Who want to save important messages, extract data from namecards, or organize images automatically. - Teams: Looking to integrate LINE messages into tools like Microsoft Teams and Microsoft To Do for better collaboration. - Developers: Seeking to build intelligent workflows that process text, images, and other inputs from LINE. - Business Owners: Who need to manage customer interactions, follow-ups, and task tracking efficiently. What Problem Does This Workflow Solve? Managing incoming messages on LINE can be time-consuming, especially when dealing with diverse input types like text, images, and namecards. This workflow solves that problem by: - Automatically identifying and routing different message types (text, images, namecards) to appropriate actions. - Extracting structured data from namecards and saving it for follow-up tasks. - Uploading images to OneDrive and saving text messages to Microsoft Teams or Microsoft To Do for easy access. - Sending real-time feedback to users via LINE to confirm that their messages have been processed. What This Workflow Does - Receive Messages via LINE Webhook: The workflow is triggered whenever a user sends a message (text, image, or other types) to the LINE bot. - Display Loading Animation: A loading animation is displayed to reassure the user that their request is being processed. - Route Input Types: The workflow uses a Switch node to determine the type of input: - Text Starting with "T": Adds the message as a task in Microsoft To Do. - Plain Text: Saves the message in Microsoft Teams under a designated channel (e.g., "Notes"). - Images: Identifies whether the image is a namecard, handwritten note, or other content, then processes accordingly. Unsupported formats trigger a polite response indicating the limitation. - Process Namecards: If the image is identified as a namecard, the workflow extracts structured data (e.g., name, email, phone number) using OpenRouter.ai and saves it to Microsoft To Do for follow-up tasks. - Save Images to OneDrive: Images are uploaded to OneDrive, renamed based on their unique message ID, and linked in Microsoft Teams for reference. - Send Feedback via LINE: The workflow replies to the user with confirmation messages, such as "[Task Created]" or "[Message Saved]."Setup GuidePre-Requisites - Access to the LINE Developers Console to configure your webhook and bot. - Accounts for Microsoft Teams, Microsoft To Do, and OneDrive with API access. - An OpenRouter.ai account with credentials to access models like GPT-4o. - Basic knowledge of APIs, webhooks, and JSON formatting. Step-by-Step Setup 1. Configure the LINE Webhook: - Go to the LINE Developers Console and set up a webhook to receive incoming messages. - Copy the Webhook URL from the Line Webhook node and paste it into the LINE Console. - Remove any "test" configurations when moving to production. 2. Set Up Microsoft Integrations: - Connect your Microsoft Teams, Microsoft To Do, and OneDrive accounts to the respective nodes in the workflow. 3. Set Up OpenRouter.ai: - Create an account on OpenRouter.ai and obtain your API credentials. - Connect your credentials to the OpenRouter nodes in the workflow. 4. Test the Workflow: - Simulate sending text, images, and namecards to the LINE bot to verify that all actions are processed correctly. How to Customize This Workflow to Your Needs - Add More Actions: Extend the workflow to handle additional input types or integrate with other tools. - Enhance Image Processing: Use advanced OCR tools to improve text extraction from complex images. - Customize Feedback Messages: Modify the reply format to include emojis, links, or other formatting options. - Expand Use Cases: Adapt the workflow for specific industries, such as sales or customer support, by tailoring the actions to relevant tasks. Why Use This Template? - Versatile Automation: Handles multiple input types (text, images, namecards) with ease. - Seamless Integration: Connects LINE messages to popular productivity tools like Microsoft Teams and To Do. - Structured Data Extraction: Extracts and organizes data from namecards, saving time and effort. - Real-Time Feedback: Keeps users informed about the status of their requests with instant notifications.

Automatically generate responses for new Google Sheets rows using ChatGPT. Enhance data processing by adding AI-generated content directly to your spreadsheet.

Effortlessly streamline your WordPress media management with Picsart. First, select and retrieve your media files directly from WordPress. Then, utilize Picsart's powerful compression tools to reduce file sizes while maintaining high-quality visuals. Finally, seamlessly upload the optimized media back to your WordPress site, ensuring faster load times and an enhanced user experience.

This n8n workflow acts as your personal AI speechwriting coach, directly accessible through Telegram. It listens to your spoken or typed drafts, provides insightful feedback on clarity, engagement, structure, and content, and iteratively refines your message based on your updates. Once you're ready, it synthesizes a brand-new speech or talk incorporating all the improvements and your accumulated ideas. This tool streamlines the speechwriting process, offering on-demand AI assistance to help you craft impactful and well-structured presentations. How it WorksInput via Telegram: You interact with the workflow by sending your speech drafts or talking points directly to a designated Telegram bot. AI Feedback: The workflow processes your input using AI models (OpenAI and/or Google Gemini) to analyze various aspects of your speech and provides constructive feedback via Telegram. Iterative Refinement: You can then send updated versions of your speech to the bot, receiving further feedback to guide your revisions. Speech Synthesis: When you send the command to "generate speech," the workflow compiles all your previous input and the AI's feedback to synthesize a new, improved speech or talk, which is then sent back to you via Telegram. New Speech Cycle: By sending the command "new speech," the workflow clears its memory, allowing you to start the process anew for a different topic. Set Up Steps (Takes Approximately 5 Minutes)Step 1: Create a Telegram Bot and Obtain its ID Open the Telegram application and search for "BotFather." Start a chat with BotFather by clicking "Start" or sending the /start command. Create a new bot by sending the command /newbot. Follow BotFather's instructions to choose a name and username for your bot. Once your bot is created, BotFather will provide you with an API token. Keep this token secure as it's required to connect your n8n workflow to your bot. Step 2: Obtain an OpenAI API Key Go to the OpenAI website and sign up for an account if you don't already have one. Navigate to the API keys section (usually under your profile settings or a "Developers" tab). Click on "Create new secret key." Copy the generated API key and store it securely. You will need to provide this key to your n8n workflow to access OpenAI's language models. Step 3: Obtain a Google Gemini LLM API Key Go to the Google Cloud AI Platform or Google AI Studio website (the specific platform may vary depending on the current Google AI offerings; search for "Google AI API"). Sign up or log in with your Google account. Follow the instructions to enable the Gemini API and create an API key. This might involve creating a project if you haven't already. Copy the generated API key and store it securely. You can then configure your n8n workflow to utilize Google Gemini's language models as well. Customization Options This n8n workflow offers significant flexibility; below are a few options: - Modify AI prompts to tailor feedback and generation for presentations, storytelling, interviews, sales pitches, academic talks, and creative writing. - Switch the interface from Telegram to Slack, WhatsApp, or even a web interface by replacing the relevant n8n nodes. - Integrate analysis for sentiment, keyword density, pacing (with voice input), and filler word detection by adjusting the workflow. - Connect to external data sources to provide context to the AI for more targeted feedback and generation. This adaptability allows you to reuse this workflow for a wide range of specific use cases and communication environments.

Who is this template for? This template is ideal for small businesses, agencies, and solo professionals who want to automate appointment scheduling and caller follow-up through a voice-based AI receptionist. If you’re using tools like Google Calendar, Airtable, and Vapi (Twilio), this setup is for you. What problem does this workflow solve? Manual call handling, appointment booking, and email coordination can be time-consuming and prone to errors. This workflow solves that by automating the receptionist role: answering calls, checking calendar availability, managing appointments, and storing call summaries—all without human intervention. What this workflow does This Agent Receptionist manages inbound voice calls and scheduling tasks using Vapi and Google Calendar. It checks availability, books or updates calendar events, sends email confirmations, and logs call details into Airtable. The workflow includes built-in logic for slot management, email triggers, and storing call transcripts. Setup Instructions 1. Duplicate Airtable Base: Use this Airtable base template. 2. Import Workflow: Load provided JSON into your n8n instance. 3. Credentials: Connect your Google Calendar and Airtable credentials in n8n. 4. Activate Workflow: Enable workflow to get live webhook URLs. 5. Vapi Configuration: Paste provided system prompt into Vapi Assistant. 6. Link the appropriate webhook URLs from n8n (GetSlots, BookSlots, UpdateSlots, CancelSlots, and end-of-call report). Disclaimer Optimized for cloud-hosted n8n instances. Self-hosted users should verify webhook and credential setups.