Agents & Automations

This workflow analyzes the sentiments of the feedback provided by users and sends them to a Mattermost channel. Typeform Trigger node: Whenever a user submits a response to the Typeform, the Typeform Trigger node will trigger the workflow. The node returns the response that the user has submitted in the form. Google Cloud Natural Language node: This node analyses the sentiment of the response the user has provided and gives a score. IF node: The IF node uses the score provided by the Google Cloud Natural Language node and checks if the score is negative (smaller than 0). If the score is negative we get the result as True, otherwise False. Mattermost node: If the score is negative, the IF node returns true and the true branch of the IF node is executed. We connect the Mattermost node with the true branch of the IF node. Whenever the score of the sentiment analysis is negative, the node gets executed and a message is posted on a channel in Mattermost. NoOp: This node here is optional, as the absence of this node won't make a difference to the functioning of the workflow. This workflow can be used by Product Managers to analyze the feedback of the product. The workflow can also be used by HR to analyze employee feedback. You can even use this node for sentiment analysis of Tweets. To perform a sentiment analysis of Tweets, replace the Typeform Trigger node with the Twitter node. Note: You will need a Trigger node or Start node to start the workflow. Instead of posting a message on Mattermost, you can save the results in a database or a Google Sheet, or Airtable. Replace the Mattermost node with (or add after the Mattermost node) the node of your choice to add the result to your database. You can learn to build this workflow on the documentation page of the Google Cloud Natural Language node.

Context Hey! I'm Samir, a Supply Chain Data Scientist from Paris who spent six years in China studying and working while struggling to learn Mandarin. I know the challenges of mastering a complex language like Chinese and my greatest support was flashcards. Therefore, I designed this workflow to support fellow Mandarin learners by automating flashcard creation using n8n, so they can focus more on learning and less on manual data entry. Who is this template for? This workflow template is designed for language learners and educators who want to automate the creation of flashcards for Mandarin (or any other language) using Google Translate API, an AI agent for phonetic transcription and generating an illustrative sentence, and a free image retrieval API. Why? If you use the open-source application Anki, this workflow will help you automatically generate personalized study materials. How? Let us imagine you want to learn how to say the word Contract in Mandarin. The workflow will automatically: - Translate the word in Simplified Mandarin (Mandarin: 合同). - Provide the phonetic transcription (Pinyin: Hétóng). - Generate an example sentence (Example: 我们签订了一份合同). - Download an illustrative picture (For example, a picture of a contract signature). All these fields are automatically recorded in a Google Sheet, making it easy to import into Anki and generate flashcards instantly. What do I need to start? This workflow can be used with the free tier plans of the services used. It does not require any advanced programming skills. Prerequisite - A Google Drive Account with a folder including a Google Sheet - API Credentials: Google Drive API, Google Sheets API, and Google Translate API activated with OAuth2 credentials - A free API key of pexels.com - A Google Sheet with the columns Next Follow the sticky notes to set up the parameters inside each node and get ready to pump your learning skills. I have detailed the steps in a short tutorial. Notes This workflow can be used for any language. In the AI Agent prompt, you just need to replace the word "pinyin" with "phonetic transcription." You can adapt the trigger to operate the workflow in the way you want. These operations can be performed by batch or triggered by Telegram, email, or webhook. If you want to learn more about how I used Anki flashcards to learn Mandarin, check out my blog article about Anki flashcards. Submitted: March 17th, 2025

Overview This workflow allows you to trigger custom logic in n8n directly from Retell's Voice Agent using Custom Functions. It captures a POST webhook from Retell every time a Voice Agent reaches a Custom Function node. You can plug in any logic—call an external API, book a meeting, update a CRM, or even return a dynamic response back to the agent. Who is it for For builders using Retell who want to extend Voice Agent functionality with real-time custom workflows or AI-generated responses. Prerequisites - Have a Retell AI Account - A Retell agent with a Custom Function node in its conversation flow - Set your n8n webhook URL in the Custom Function configuration - (Optional) Familiarity with Retell's Custom Function docs Start a conversation with the agent (text or voice)Retell Agent Example To get you started, we've prepared a Retell Agent ready to be imported, that includes the call to this template. Import the agent to your Retell workspace. You will need to modify the function URL in order to call your own instance. This template is a simple hotel agent that calls the custom function to confirm a booking, passing basic formatted data. How it works Retell sends a webhook to n8n whenever a Custom Function is triggered during a call (or test chat). The webhook includes: - Full call context (transcript, call ID, etc.) - Parameters defined in the Retell function node You can process this data and return a response string back to the Voice Agent in real-time. How to use it 1. Copy the webhook URL (e.g. https://your-instance.app.n8n.cloud/webhook/hotel-retell-template) 2. Modify the Retell Custom Function webhook URL 3. Edit the function 4. Modify the URL 5. Modify the logic in the Set node or replace it with your own custom flow 6. Deploy and test: Retell will hit your n8n workflow during the conversation Extension Ideas - Call a third-party API to fetch data (e.g. hotel availability, CRM records) - Use an LLM node to generate dynamic responses - Trigger a parallel automation (Slack message, calendar invite, etc.) 👉 Reach out to us if you're interested in analyzing your Retell Agent conversations.

CallForge - AI Gong Sales Call Processor Streamline your sales call analysis with CallForge, an automated workflow that extracts, enriches, and refines Gong.io call data for AI-driven insights. Who is This For? This workflow is designed for: ✅ Sales teams looking to automate sales call insights. ✅ Revenue operations (RevOps) professionals optimizing call data processing. ✅ Businesses using Gong.io to analyze and enhance sales call transcripts. What Problem Does This Workflow Solve? Manually analyzing sales calls is time-consuming and prone to inconsistencies. While Gong provides raw call data, interpreting these conversations and improving AI-generated summaries can be challenging. With CallForge, you can: ✔️ Automate transcript extraction from Gong.io. ✔️ Enhance AI insights by adding product and competitor data. ✔️ Reduce errors from AI-generated summaries by correcting mispronunciations. ✔️ Eliminate duplicate calls to prevent redundant processing. What This Workflow Does 1. Extracts Gong Call Data Retrieves call recordings, metadata, meeting links, and duration from Gong. 2. Removes Duplicate Entries Queries Notion to ensure that already processed calls are not duplicated. 3. Enriches Call Data Fetches integration details from Google Sheets. Retrieves competitor insights from Notion. Merges data to provide AI with a more comprehensive context. 4. Prepares AI-Friendly Transcripts Cleans up transcripts for structured AI processing. Reduces prompt complexity for more accurate OpenAI outputs. 5. Sends Processed Data to an AI Call Processor Delivers the cleaned and enriched transcript to an AI-powered workflow for generating structured call summaries. How to Set Up This Workflow 1. Connect Your APIs 🔹 Gong API Access – Set up your Gong API credentials in n8n. 🔹 Google Sheets Credentials – Provide API access for retrieving integration data. 🔹 Notion API Setup – Connect Notion to fetch competitor insights and store processed data. 🔹 AI Processing Workflow – Ensure an OpenAI-powered workflow is in place for structured summaries. 2. Customize to Fit Your Needs 💡 Modify Data Sources – Update connections if using a different CRM, database, or analytics tool. 💡 Adjust AI Processing Logic – Optimize transcript formatting based on your preferred AI model. 💡 Expand Data Enrichment – Integrate CRM data, industry benchmarks, or other insights. Why Use CallForge? By automating Gong call processing, CallForge empowers sales teams to: 📈 Gain valuable AI-driven insights from calls. ⚡ Speed up decision-making with cleaner, structured data. 🛠 Improve sales strategies based on enriched, accurate transcripts. 🚀 Start automating your Gong call analysis today!

Generate engaging podcast topics by transforming Feedly articles with ChatGPT. Stay ahead with fresh ideas and captivating content for your next podcast episode.

This n8n workflow demonstrates how to manage your Qdrant vector store when there is a need to keep it in sync with local files. It covers creating, updating, and deleting vector store records, ensuring our chatbot assistant is never outdated or misleading. Disclaimer This workflow depends on local files accessed through the local filesystem and so will only work on a self-hosted version of n8n at this time. It is possible to amend this workflow to work on n8n cloud by replacing the local file trigger and read file nodes. How it works A local directory where bank statements are downloaded to is monitored via a local file trigger. The trigger watches for the file create, file changed, and file deleted events. When a file is created, its contents are uploaded to the vector store. When a file is updated, its previous records are replaced. When the file is deleted, the corresponding records are also removed from the vector store. A simple Question and Answer Chatbot is set up to answer any questions about the bank statements in the system. Requirements A self-hosted version of n8n. Some of the nodes used in this workflow only work with the local filesystem. Qdrant instance to store the records. Customizing the workflow This workflow can also work with remote data. Try integrating accounting or CRM software to build a managed system for payroll, invoices, and more. Want to go fully local? A version of this workflow is available which uses Ollama instead.

This workflow is designed to analyze YouTube videos by extracting their transcripts, summarizing the content using AI models, and sending the analysis via email. This workflow is ideal for content creators, marketers, or anyone who needs to quickly analyze and summarize YouTube videos for research, content planning, or educational purposes. How It Works:Trigger: The workflow starts with a manual trigger, allowing you to test it by clicking "Test workflow." You can also set a YouTube video URL manually or dynamically. YouTube Video ID Extraction: The workflow extracts the YouTube video ID from the provided URL using a custom JavaScript function. This ID is necessary for fetching the transcript. Transcript Generation: The video ID is sent via an HTTP request to generate the transcript. You need to replace APIKEY with a free API key from the service. Transcript Validation: The workflow checks if a transcript exists for the video. If a transcript is available, it proceeds; otherwise, it stops. Full Text Extraction: If a transcript exists, the workflow combines all transcript segments into a single text variable for further analysis. AI-Powered Analysis: The full transcript is passed to an AI model (DeepSeek, OpenAI, or OpenRouter) for analysis. The AI generates a structured summary, including a title and key points, formatted in markdown. Email Notification: The analysis results (title and summary) are sent via email using SMTP credentials. The email contains the structured summary of the video. Set Up Steps:YouTube Transcript API: Obtain a free API key from youtube-transcript.io and replace APIKEY in the "Generate transcript" node with your key. AI Model Configuration: Configure the AI model nodes (DeepSeek, OpenAI, or OpenRouter) with the appropriate API credentials. You can choose one or multiple models depending on your preference. Email Setup: Configure the "Send Email" node with your SMTP credentials (e.g., Gmail, Outlook, or any SMTP service). Ensure the email settings are correct to send the analysis results. Key Features: - Free Tools: Uses youtube-transcript.io for free transcript generation. - AI Models: Supports multiple AI models (DeepSeek, OpenAI, OpenRouter) for flexible analysis. - Email Notifications: Sends the analysis results directly to your inbox. - Customizable: Easily adapt the workflow to analyze different videos or use different AI models.

👥 Who Is This For? Content creators, marketing teams, and channel managers who want a simple, hands‑off solution to upload videos and automatically generate optimized metadata from video transcripts. 🛠 What Problem Does This Solve? Manual video uploads with proper metadata creation is time‑consuming and repetitive. This workflow fully automates: - Monitoring a specific Google Drive folder for new video uploads - Seamless YouTube upload processing - Transcript extraction for context understanding - AI‑powered generation of titles, descriptions, and tags - Metadata application to uploaded videos without manual intervention 🔄 Node‑by‑Node Breakdown | Step | Node Purpose | |------|--------------| | 1 | New Video? (Trigger) – Monitors specified Google Drive folder | | 2 | Download New Video – Retrieves the video file from Google Drive | | 3 | Upload to YouTube – Uploads the video to YouTube with initial settings | | 4 | Get Transcript – Extracts transcript from the uploaded video | | 5 | Adjust Transcript Format – Formats raw transcript for processing | | 6 | Create Description – Generates SEO‑optimized description | | 7 | YT Tags (Message Model) – Creates relevant tags based on content | | 8 | YT Title (Message Model) – Generates compelling title | | 9 | Define File Path Upload Format (Optional) – Structures data paths | | 10 | Update Video’s Metadata – Applies generated title, description, tags | ⚙️ Pre‑conditions / Requirements - n8n with Google Drive and YouTube API credentials configured (stored as n8n credentials/variables; no hard‑coded IDs) - Dedicated Google Drive folder for video uploads - YouTube channel with proper upload permissions - AI service access for transcript processing and metadata generation - Sufficient storage for temporary video handling ⚙️ Setup Instructions 1. Import this workflow into your n8n instance. 2. Configure Google Drive credentials; reference folder ID via n8n variable (do not hard‑code). 3. Set up YouTube API credentials with upload and edit permissions. 4. Specify the target Google Drive folder ID in the New Video? trigger node (via variable). 5. Configure AI service credentials for transcript and metadata generation. 6. Adjust message templates for title, description, and tag creation. 7. Test with a small video file before production use. 🎨 How to Customize - Modify AI prompts to match your channel’s tone and style. - Add conditional logic based on video categories or naming conventions. - Implement notification systems to alert when uploads complete. - Create custom metadata templates for different content types. - Include timestamps or chapter markers based on transcript analysis. - Add social media sharing nodes to announce new uploads. ⚠️ Important Notes - Video quality is preserved through the upload process. - Consider YouTube API quotas when handling multiple uploads. - Transcript quality affects metadata generation results. - Videos are initially uploaded without visibility adjustments. - Processing time depends on video length and transcript complexity. 🔐 Security and Privacy - Store API credentials and folder IDs as n8n Credentials/Variables—remove any hard‑coded tokens or IDs. - Video files are processed temporarily and not stored permanently. - Limit Google Drive folder access to authorized users only. - Manage YouTube upload permissions carefully (use OAuth/service accounts). - Ensure compliance with organizational data‑handling policies.

✨ Overview This workflow allows candidates to schedule interviews through a conversational AI assistant. It integrates with your Google Calendar to check for existing events and generates a list of available 30-minute weekday slots between 9 AM and 5 PM Eastern Time. Once the candidate selects a suitable time and provides their contact information, the AI bot automatically books the meeting on your calendar and confirms the appointment. ⚡ Prerequisites To use this workflow, you need an OpenAI account with access to the GPT-4o model, a Google account with a calendar that can be accessed through the Google Calendar API, and an active instance of n8n—either self-hosted or via n8n cloud. Within n8n, you must have two credential configurations ready: one for Google Calendar using OAuth2 authentication, and another for your OpenAI API key. 🔐 API Credentials Setup For Google Calendar, go to the Google Cloud Console and create a new project. Enable the Google Calendar API, then create OAuth2 credentials by selecting “Web Application” as the application type. Add http://localhost:5678/rest/oauth2-credential/callback as the redirect URI if using local n8n. After that, go to n8n, navigate to the Credentials section, and create a new Google Calendar OAuth2 credential using your account. For OpenAI, visit platform.openai.com to retrieve your API key. Then go to the n8n Credentials page, create a new credential for OpenAI, paste your key, and name it for reference. 🔧 How to Make This Workflow Yours To customize the workflow for your use, start by replacing all instances of the calendar email [email protected] with your own Google Calendar email. This email is referenced in multiple places, including Google Calendar nodes and the ToolWorkflow JSON for the node named "Run Get Availability." Also update any instances where the Google Calendar credential is labeled as Google Calendar account to match your own credential name within n8n. Do the same for the OpenAI credential label, replacing OpenAi account with the name of your own credential. Next, go to the node labeled Candidate Chat and copy the webhook URL. This is the public chat interface where candidates will engage with the bot—share this URL with them through email, your website, or anywhere you want to allow access. Optionally, you can also tweak the system message in the Interview Scheduler node to modify the tone, language, or logic used during conversations. If you want to add branding, update the title, subtitle, and inputPlaceholder in the Candidate Chat node, and consider modifying the final confirmation message in Final Response to User to reflect your brand voice. You can also update the business rules such as time zone, working hours, or default duration by editing the logic in the Generate 30 Minute Timeslots code node. 🧩 Workflow Explanation This workflow begins with the Candidate Chat node, which triggers when a user visits the public chat URL. The Interview Scheduler node acts as an AI agent, guiding the user through providing their email, phone number, and preferred interview time. It checks availability using the Run Get Availability tool, which in turn reads your calendar and compares it with generated free time slots from the Generate 30 Minute Timeslots node. The check day names tool helps the AI interpret natural language date expressions like “next Tuesday.” The schedule is only populated with 30-minute weekday slots from 9 AM to 5 PM Eastern Time, and no events are scheduled if they overlap with existing ones. When a suitable time is confirmed, the AI formats the result into structured JSON, creates an event on your Google Calendar, and sends a confirmation back to the user with all relevant meeting details. 🚀 Deployment Steps To deploy the interview scheduler, import the provided workflow JSON into your n8n instance. Update the Google Calendar email, OpenAI and Google credential labels, system prompts, and branding as needed. Test the connections to ensure the API credentials are working correctly. Once everything is configured, copy and share the public chat URL from the Candidate Chat node. When candidates engage with the chat, the workflow will walk them through the interview booking process, check your availability, and finalize the booking automatically. 💡 Additional Tips By default, the workflow avoids scheduling interviews on weekends and outside of 9–5 EST. Each interview lasts exactly 30 minutes, and overlapping with existing events is prevented. The assistant does not reveal details about other meetings. You can customize every part of this workflow to fit your use case, including subworkflows like Get Availability and check day names, or even white-label it for client use. This workflow is ready to become your AI-powered interview scheduling assistant.

🚀 AI-Powered Business Performance Reporting Automation Unlock executive-level insights with ZERO manual work! This n8n template empowers you to automate your entire monthly business performance reporting using dynamic SQL queries, AI-driven analysis, and beautiful HTML dashboards — all delivered directly to your inbox. 🎯 What This Automation Does 📆 Triggers automatically every month (5th of each month) 🧮 Fetches financial data from SQL (ERPNext or any database) 🔁 Loops over cost centers to analyze each business unit individually 📊 Generates Profit & Loss reports, WIP, Employee stats, and vertical breakdowns 🤖 Uses Google Gemini 2.5 AI to perform advanced financial analysis 💌 Delivers a polished HTML report to your email inbox 🔧 Fully modular – replace data source with Excel, Google Sheets, or APIs 🧑‍🏫 Step-by-Step Video Tutorial 🎥 Watch the full tutorial on YouTube: 📌 Learn how each node works and see the AI-generated report in action. 🌐 Useful Links 🔗 Sign up for n8n Cloud (recommended for non-tech users): 👉 https://n8n.syncbricks.com 📘 Download the step-by-step Guidebook (Free): 👉 https://lms.syncbricks.com/books/n8n 📚 Explore the full course on n8n (includes templates, workflows, and AI integrations): 👉 https://lms.syncbricks.com/courses/n8n 🛠 Requirements ✅ n8n (Self-hosted or Cloud) ✅ SQL Database (MySQL / PostgreSQL / ERPNext) ✅ Microsoft Outlook or Gmail (to send the report) ✅ Gemini API Key (for AI analysis) ✅ Basic understanding of your data schema 💡 Why Use This Template? ⏱ Saves 2-3 days of manual work every month 📈 Improves financial visibility across business units 🤝 Great for CFOs, COOs, Finance Analysts, and BI teams 🔄 Scales across multiple divisions and companies 🧠 Leverages AI for actionable insights and recommendations 🧩 Customize It Your Way Replace the SQL nodes with: - Excel / Google Sheets - Airtable / APIs - Custom Applications Swap the AI model: - OpenAI GPT - Claude - DeepSeek Adjust the report structure or HTML style 🙌 Get Started Now 🎯 Import the JSON template → Connect your data → Receive business insights via email. Don’t let manual reporting slow down your decision-making. 👉 Sign up for n8n Cloud 👉 Learn n8n with Amjid 👉 Download Guide Created by Amjid Ali | SyncBricks™ – Automation for Everyone

This workflow implements a message-batching buffer using Redis for temporary storage and GPT-4 for consolidated response generation. Incoming user messages are collected in a Redis list; once a configurable “inactivity” window elapses or a batch size threshold is reached, all buffered messages are sent to GPT-4 in a single prompt. The system then clears the buffer and returns the consolidated reply. Key Features - Redis-backed buffer to queue incoming messages per user session - Dynamic wait time (shorter for long messages, longer for short messages) - Batch trigger on inactivity timeout or minimum message count - GPT-4 consolidation: merges all buffered messages into one coherent response Setup InstructionsMap Input - Rename node to “Extract Session & Message” - Assign context_id and message from webhook or manual trigger Compute Wait Time - Rename node to “Determine Inactivity Timeout” - JS Code: javascript const wordCount = $json.message.split(' ').filter(w=>w).length; return [{ json: { context_id: $json.context_id, message: $json.message, waitSeconds: wordCount < 5 ? 45 : 30 }}]; Buffer Message in Redis - Push into list buffer_in:{{$json.context_id}} - INCR key buffer_count:{{$json.context_id}} with TTL {{$json.waitSeconds + 60}} Mark Waiting State - GET waiting_reply:{{$json.context_id}} → if null, SET it to true with TTL {{$json.waitSeconds}} - Rename nodes to “Check Waiting Flag” / “Set Waiting Flag” Wait for Inactivity - Wait node: pause for {{$json.waitSeconds}} seconds Check Batch Trigger - GET keys: - last_seen:{{$json.context_id}} - buffer_count:{{$json.context_id}} - IF both: - buffer_count >= 1 - (now – last_seen) >= waitSeconds * 1000 - Rename node to “Trigger Batch on Inactivity or Count” Fetch & Consolidate - GET entire list buffer_in:{{$json.context_id}} - Information Extractor → rename to “Consolidate Messages” - System prompt: “You are an expert at merging multiple messages into one clear paragraph without duplicates.” GPT-4 Chat - OpenAI Chat Model (GPT-4) Cleanup & Respond - Delete Redis keys: - buffer_in:{{$json.context_id}} - waiting_reply:{{$json.context_id}} - buffer_count:{{$json.context_id}} - Return the consolidated reply to the user Customization Guidance - Batch Size Trigger: Add an additional IF to fire when buffer_count reaches your desired batch size. - Timeout Policy: Adjust the word-count thresholds or replace with character-count logic. - Multi-Channel Support: Change the trigger from a manual test node to any webhook (e.g., chat, SMS, email). - Error Handling: Insert a fallback branch to catch Redis timeouts or OpenAI API errors and notify users.

This workflow allows you to add positive feedback messages to a table in Notion. Prerequisites: - Create a Typeform that contains a Long Text field question type to accept feedback from users. - Get your Typeform credentials by following the steps mentioned in the documentation. - Follow the steps mentioned in the documentation to create credentials for Google Cloud Natural Language. - Create a page on Notion similar to this page. - Create credentials for the Notion node by following the steps in the documentation. - Follow the steps mentioned in the documentation to create credentials for Slack. - Follow the steps mentioned in the documentation to create credentials for Trello. Workflow Steps: 1. Typeform Trigger node: Whenever a user submits a response to the Typeform, the Typeform Trigger node will trigger the workflow. The node returns the response that the user has submitted in the form. 2. Google Cloud Natural Language node: This node analyses the sentiment of the response the user has provided and gives a score. 3. IF node: The IF node uses the score provided by the Google Cloud Natural Language node and checks if the score is positive (larger than 0). If the score is positive we get the result as True; otherwise, False. 4. Notion node: This node gets connected to the true branch of the IF node. It adds the positive feedback shared by the user in a table in Notion. 5. Slack node: This node will share the positive feedback along with the score and username to a channel in Slack. 6. Trello node: If the score is negative, the Trello node is executed. This node will create a card on Trello with the feedback from the user.

Automatically send new RSS articles to Telegram as a photo with ChatGPT. Convert HTML to text, generate an image, and share via Telegram.

About The List Building Automation This automation will guide you on how to automate list building using Airtop. You’ll have a streamlined workflow that can reduce your research time by up to 90% while improving the accuracy of your target lists. How to automate list building It can be challenging to spend too much time on tasks like compiling lists of potential investors, customers, job candidates, industry influencers, or key decision-makers. Verifying contact details often requires significant effort, whether building an outreach list, tracking thought leaders, or researching potential customers. Not anymore. With Airtop's List Building Automation, turn hours of tedious research into clean, reliable, and accurate lists, built in just minutes. What You'll Need - A free Airtop API Key - Target audience parameters (persona and which network, e.g., "AI Influencers on LinkedIn") - Make a copy of this template to startUnderstanding the Process This automation leverages Airtop's advanced data processing capabilities powered by AI to scan multiple unstructured sources and compile accurate, targeted lists based on your specific requirements. The magic lies in its ability to understand context and verify information across different platforms. This workflow: - Handles multi-source data collection and consolidation - Manages automatic verification of social profiles and domains - Automates the filtering and ranking of results based on relevanceSetting Up Your Automation Enter your search criteria in the "Parameters" node: - Who: Your target audience (e.g., "Angel investors in Europe," "Top AI influencers") - Where: The platform or domain to focus on (e.g., "LinkedIn," "TikTok") Configure your Airtop API Key. Create one for free at the Airtop Portal. In the last node, select the spreadsheet that you copied earlier, then run the workflow. Customization Options While our template works out of the box, you might want to customize it for your specific needs: - Add custom filtering criteria for more targeted results - Implement automatic data enrichment from additional sources - Set up automatic exports to your preferred CRM or databaseReal-World Applications Here's how businesses can use this automation: A VC firm could use this automation to build a comprehensive EU angel investors database. What previously required their analysts to work 15 hours per week now runs automatically in the background, providing fresh leads daily. A PR agency could automate its influencer discovery process across multiple platforms, reducing its research time from 10 hours to 30 minutes per client while increasing the relevance of its outreach lists. Best Practices To get the most out of this automation: - Start with specific, well-defined parameters to ensure relevant results - Regularly update your parameters to keep your lists fresh and relevant - Combine multiple runs with different parameters for comprehensive coverageWhat's Next? Now that you've automated your list building, you might be interested in: - Setting up automated outreach sequences - Creating dynamic lead scoring systems - Implementing automatic list updating and maintenance Happy automating!

Discover YouTube videos within a specific channel, get concise summaries with ChatGPT, and receive the results via email. This streamlined process ensures you quickly access valuable information in an easy and informative format, enhancing your productivity and decision-making.

Microsoft Outlook AI Email AssistantPrerequisites 1. Microsoft 365 Login Credentials Provide your Office 365 credentials to connect Outlook. 2. Monday.com Generate an API token and have a board with your contact details. 3. Airtable Obtain an API key (or personal access token) and set up a base to store: - Contacts (populated by the Monday.com sync). - Rules & Categories (used by the AI Email Assistant). Use this Airtable base as the template: Airtable AI Email Assistant Template. Define your own rules, categories, and delete rules. 4. OpenAI API Key Sign up for OpenAI if you don’t already have an account. Generate a new API key at OpenAI API Keys. What the System Does 1. Daily Contact Sync (Monday.com → Airtable) Runs once a day to pull the latest contacts from Monday.com and store or update them in Airtable. 2. AI Email Categorisation & Prioritisation - Fetches Outlook emails with filters. - Cleans and processes email content. - Matches emails with known contacts from Airtable. - Uses an AI agent to classify, categorise, and prioritise emails. - Updates Outlook categories and importance based on AI results. - Runs in parallel with Airtable rules & categories retrieval for real-time decision-making. Workflow 1: Daily Contact Sync (Monday.com → Airtable)Purpose Keep Airtable’s Contacts table up to date by pulling new or updated contact data from Monday.com daily. Steps - Schedule Trigger Runs at a set interval (daily) to initiate contact syncing. - Monday.com: Get Contacts Reads the specified board/columns from Monday.com where you store contact details. - Airtable - Contacts Upserts (adds or updates) the fetched Monday.com data into Airtable’s Contacts table. Ensures daily updates reflect changes from Monday.com. Result A consolidated contact list in Airtable, ready for AI email categorisation. Workflow 2: Categorise & Prioritise Outlook EmailsPurpose Fetches Outlook emails, cleans and processes their content, matches senders with known contacts, and uses AI to categorise and prioritise them. Steps 1. Get Outlook Emails with Filters Trigger: Either scheduled (Check Mail Schedule Trigger) or manual (Test Workflow). Outlook Filters: - Not flagged (flag/flagStatus == 'notFlagged'). - Not categorised (not categories/any()). 🔹 Result: A batch of fresh, unprocessed emails ready for processing. 2. Sanitise Email Convert to Markdown: Strips HTML tags and normalises formatting. Email Messages Processing: Allows manual removal of signatures, disclaimers, or extra content. 🔹 Result: A clean, AI-friendly email for categorisation. 3. Match Contact Loop Over Emails: Iterates over each email. Contact Lookup: Checks Airtable’s Contacts table (updated daily). Merge Data: Enriches emails with known client, supplier, or internal team info. 🔹 Result: Enhanced email context for AI processing. 4. AI Agent to Categorise & Prioritise - Retrieve Rules & Categories Reads Rules, Categories, and Delete Rules from Airtable in parallel. - AI: Analyse Email (Tools Agent) Uses email text, sender info, and rules to build a structured AI prompt. - OpenAI Chat Model Processes the AI prompt and outputs: - Category - Subcategory (optional) - Priority level - Short rationale - Structured Output Parser Ensures AI response is valid JSON format. 🔹 Result: Each email is labelled, categorised, and prioritised with AI-driven logic. 5. Set Outlook Category & Importance - Set Category: Updates Outlook with the assigned category. - Check Priority Conditions (If Node): If Action Required or from a VIP, mark as High Priority. - Set Importance: Updates the email's importance flag in Outlook. 🔹 Result: Outlook is updated with categories & importance based on AI recommendations. Parallel Processing: Retrieve Rules & Categories Runs alongside the email categorisation workflow. Ensures Airtable-based rules are available before AI processing. Steps - Airtable: Get Rules & Categories Fetches Rules, Categories, and Delete Rules from Airtable. - Delete Rules (Optional) If a delete rule matches, the email is removed. 🔹 Result: A dynamic, updatable rule system ensuring emails are handled properly. Final Outcome Daily Contact Sync keeps contacts up to date. AI-driven email workflow ensures smart categorisation. Outlook automatically updated with AI-generated categories and importance. This automated system saves time, ensures efficient inbox management, and allows for customisable rules via Airtable.

Automatically send personalized messages to ManyChat subscribers using ChatGPT's assistant. Trigger via Custom Webhook, update subscriber fields, and send flows.

The YogiAI workflow automates sending daily yoga pose reminders and related information via Line Push Messages. This automation leverages data from a Google Sheets database containing yoga pose details such as names, image URLs, and links to ensure users receive personalized and engaging content every day. Purpose - Provide users with daily yoga pose suggestions tailored to their practice. - Deliver visually appealing and informative content through Line's Flex Messages, including images and clickable links. - Log user interactions and preferences back into Google Sheets to refine future recommendations. Key Features - Automated Daily Reminders: Sends a curated list of yoga poses at a scheduled time (21:30 Bangkok time). - Dynamic Content Generation: Uses AI to rewrite and format messages in a user-friendly manner, complete with emojis and clear instructions. - Integration with Google Sheets: Pulls data from a predefined Google Sheet and logs interactions for continuous improvement. - Customizable Messaging: Ensures JSON outputs are properly formatted for Line’s Flex Message API, allowing for interactive and visually rich content. Data SourceGoogle Sheets Structure The workflow relies on a Google Sheet structured as follows: - PoseName: The name of the yoga pose. - uri: The image URL representing the pose. - url: A clickable link directing users to more information about the pose. Sample Data Layout - Supine Anglehttps://example.com/SupineAngle-tn146.pnghttps://example.com/pose/SupineAngle - Warrior IIhttps://example.com/WarriorII-tn146.pnghttps://example.com/pose/WarriorIINote: Ensure that you update the Google Sheet with your own data. Refer to this sample sheet for reference.Scheduled Trigger The workflow is triggered daily at 21:30 (9:30 PM) Bangkok Time (Asia/Bangkok). This ensures timely delivery of reminders to users, keeping them engaged with their yoga practice. Workflow Process - Data Retrieval Node: Get PoseName Fetches yoga pose details from the specified range in the Google Sheet. - Content Generation Node: WritePosesToday Utilizes Azure OpenAI to craft user-friendly text, complete with emojis and clear instructions. Node: RewritePosesToday Formats the AI-generated text specifically for Line messaging, ensuring compatibility and visual appeal. - JSON Formatting Node: WriteJSONflex Generates JSON structures required for Line’s Flex Messages, enabling carousel displays of yoga pose images and links. Node: Fix JSON Ensures all JSON outputs are correctly formatted before being sent via Line. - Message Delivery Node: Line Push with Flex Bubble Sends the final message, including both text and Flex Message carousels, directly to users via Line Push Messages. - Logging Interactions Nodes: YogaLog & YogaLog2 Logs each interaction back into Google Sheets to track which poses were sent and how often they appear, refining future recommendations. Setup Prerequisites - Google Sheets Account: Set up a Google Sheet with the required structure and populate it with your yoga pose data. - Line Developer Account: Create a Line channel to obtain necessary credentials for sending push messages. - Azure OpenAI Account: Configure access to Azure OpenAI services for generating and formatting content. Intended Audience This workflow is ideal for: - Yoga Instructors: Seeking to engage students with daily pose suggestions. - Fitness Enthusiasts: Looking to maintain consistency in their yoga practice. - Content Creators: Interested in automating personalized and visually appealing content distribution.

About The Post to X Automation Seamlessly automate posting to X using Airtop and Make. How to Automate Posting to X with Airtop Consistently engaging your audience on X (formerly Twitter) can be a challenge, particularly when done manually. Developers and automation engineers often struggle with repetitive tasks like scheduling tweets, maintaining consistent posting cycles, and integrating content from various sources or AI-generated feeds. Manually managing content updates increases fatigue, human error, and decreases scalability. This n8n automation, powered by Airtop, simplifies automated content publishing onto X. Whether you're sharing daily updates, integrating dynamically generated AI content, or streamlining your marketing content pipeline, Airtop’s automation helps eliminate manual labor and reduces potential execution errors. Who is this Automation for? - Social Media Managers scheduling recurring or automated posts on X - Content Marketers integrating AI-generated content into their publishing process - Developers implementing automated social media pipelines - Automation Engineers minimizing errors and manual posting efforts Key Benefits - Real-time, authenticated API postings via X - Reliable structured workflows minimize manual errors - Seamless integration with AI content pipelines Use Cases - Automatically publish scheduled daily content updates - Seamlessly post AI-generated insights, news summaries, or industry updates - Distribute alerts and event announcements reliably at set intervals - Maintain active audience engagement by automating regular, high-frequency posts How the Post to X Automation Works This Airtop automation works by using your Airtop Profile signed into X via Airtop. Once authenticated securely with your X credentials, n8n handles the structured data flow, which can come from manual inputs, AI-generated sources, databases, or RSS feeds. Airtop then securely publishes the posts, providing reliable scheduled updates directly on X, removing manual oversight and streamlining your social media workflows. What You’ll Need - An Airtop API key - Your X (Twitter) account - An Airtop Profile signed into X Setting Up the Automation - Connect your Airtop account using your free Airtop API key - Create an Airtop Profile and connect it to your X account - Activate and schedule your scenario to automate regular posting Customize the Automation Customize your posting workflow extensively using Airtop's built-in node in n8n: - Integrate diverse sources like RSS feeds and AI tools to dynamically customize automated posts - Schedule precise posting intervals or diversify times for maximum audience engagement - Set conditional logic to automate content posting based on predefined triggers and events - Utilize Airtop’s structured data flows to manage categories, hashtags, or mentions in your posts Automation Best Practices - Consistently update security credentials for uninterrupted access - Clearly structure your workflow to simplify troubleshooting and logic updates - Monitor posting frequency to ensure optimal audience reach and engagement - Regularly review content sources to maintain quality control of automated postings Happy Automating!

Who is this template for? This workflow powers a simple yet effective customer and sales support chatbot for your webshop. It's perfect for solopreneurs who want to automate customer interactions without relying on expensive or complex support tools. How it works? The chatbot listens to user requests—such as checking product availability—and automatically handles the following: - Fetches product information from a Google Sheet - Answers customer queries - Places an order - Updates the stock after a successful purchase Everything runs through a single Google Sheet used for both stock tracking and order management. Setup Instructions Before you begin, connect your Google Sheets credentials by following this guide: This will be used to connect all the tools to Google Sheets. Get Stock Open "Get Stock" tool node and select the Google sheet credentials you created. Choose the correct Google sheet document and sheet name and you are done. Place Order Go to your "Place Order" tool node and select the Google sheet credentials you have created. Choose the correct Google sheet document and sheet name. Update Stock Open your "Update Stock" tool node and select the Google sheet credentials you have created. Choose the correct Google sheet document and sheet name. In "Mapping Column Mode" section, select map each column manually. In "Column to match on," select the column with a unique identifier (e.g., Product ID) to match stock items. In values to update section, add only the column(s) that need to be updated—usually the stock count. AI Agent node Adjust the prompt according to your use case and customize what you need. Google Sheet TemplateStock sheet | Case ID | Phone Model | Case Name | Case Type | Image URL | Quantity Available | Initial Inventory | Sold | |---------|-------------|-----------|-----------|------------------------|-------------------|------------------|------| | 1023 | Iphone 14 pro | Black Leather | Magsafe | https://example.com/url | 90 | 100 | 10 | Order sheet | Case ID | Phone Model | Case Name | Name | Phone Number | Address | |---------|-------------|-----------|---------------|--------------|-------------------| | 1023 | Black Leather | Iphone 14 pro | Fernando Torres | 9998898888 | Paris, France |

This is a response chatbot in public channels through slash commands. I explain more in detail through the YouTube video, but it's only available in Korean. How it works? When you request the created slash command in Slack, the request comes to the webhook. Then, the Switch Node branches appropriately according to each slash command request. Here, a slash command called /ask is connected to the chatbot, and the chatbot generates answers to the questions asked. The final node responds to the channel. Set up steps 1. Create a Slack app. 2. Add chat:write permission in Slack OAuth & Permissions > Scopes. 3. Create a Command in Slack Slash Commands menu and enter the n8n Webhook node's URL. 4. Complete creating the Slash Commands. 5. Enter the created command in the Switch node.