by Sleak
Who is this template for? This workflow template is designed for business owners and HR professionals to automatically detect and structure unstructured job applications received through email. Additionally, other email categories can be added, each with it's own workflow. How it works Every time a new email is received, an OpenAI model classifies it into a predefined category by analyzing the plain text of the email and the extracted content from the attachment. If the email is classified as a job application, an OpenAI model uses the email’s plain text and extracted attachment content to populate predefined fields such as age and study. A relevant additional step would be to directly push the applicant and their structured job application into a CRM or ATS like Hubspot or Recruitee. Set up steps Configure your IMAP credentials to connect your email account. Use this n8n documentation page for quickstart guides for common email providers. Connect your OpenAI account in the 'Classify email' node. And add or remove any category for classification in this node. Make sure the description is clear and concise. Connect your OpenAI account in the 'Extract variables - email & attachment' node. And add or remove any predefined fields that should be populated for job applications in this node. Make sure the description is clear and concise.
by Yang
📄 What this workflow does This workflow helps you analyze Google reviews of any business to generate powerful marketing insights. By simply submitting a business name and its Google Place ID, it fetches the top 30 reviews and uses GPT-4 (via LangChain Agent) to extract valuable customer insights such as marketing angles, customer motivations, product pain points, and voice of customer (VOC) quotes. The output is stored automatically in a connected Google Sheet. 👤 Who is this for Marketing teams looking for messaging inspiration Founders or product managers exploring customer feedback Brand strategists gathering real-world insights Agencies running VOC or sentiment analysis 🛠️ Requirements Dumpling AI API key** OpenAI GPT-4 or GPT-4o access** Google Sheets connection** A form or manual input with: Business Name Google Place ID ⚙️ How to set up Connect Credentials Dumpling AI (via HTTP Header Auth) OpenAI (GPT-4) Google Sheets (OAuth2) Prepare your Google Sheet Create columns: Business Name, Place ID, Marketing Angles, Customer Motivations, Frictions and Barriers, Product Opportunities, VOC Snippets Update Nodes Replace the Google Sheets Document ID and Tab Name with yours Check that the Dumpling API node is linked to your credential Optional: tweak the prompt in the LangChain Agent node to fit your tone or goals 🤖 How it works (Workflow Steps) User submits business name + Google Place ID Dumpling AI fetches top 30 reviews Workflow aggregates review text GPT-4 via LangChain analyzes the reviews Insights are parsed and logged to Google Sheets 💡 Customization Ideas Push output to Notion, Airtable, or Slack Add sentiment scoring to prioritize themes Create summaries for each insight category Schedule insights to be emailed weekly This is a plug-and-play VOC research workflow — great for founders, marketers, and product teams who want actionable data from real customers without doing manual review scraping or summarizing.
by AdrianWang
How it works This workflow automates the conversion of various document formats (such as PDF, Word, and PPT) into Markdown. It connects to the MinerU API service, which leverages OCR, formula, and table recognition to produce high-quality output. Users can initiate the process by simply uploading a document through an n8n chat interface. Set up steps Ensure you have a local n8n instance running. Set up and run the MinerU MCP (MinerU Computing Platform) server locally. Import this workflow into your n8n instance. Configure your AI model credentials (e.g., for OpenAI, add your API Key and Base URL). Click the "Write Files from Disk" node and edit the file path to your desired local save location. Click the "MCP Client" node and input your MinerU MCP server address (e.g., http://localhost:8000/sse). Click the "Open Chat" button to upload a file, send a message, and test the workflow.
by Robert Breen
Web-Form Auto-Responder: Instant Email + SMS Follow-Up 📝 Description Embed a simple web form on your site and let this workflow: Collect a visitor’s name, email, phone, and question Generate a professional email and a friendly SMS using GPT-4o-mini Delay briefly (1 min by default) to simulate human writing time Send the AI-crafted email via Microsoft Outlook Send the AI-crafted text via Twilio Perfect for solo consultants or small teams who want rapid, personalized responses without manual typing. ⚙️ Setup Instructions Import the workflow n8n → Workflows → Import from File (or Paste JSON) → Save Add credentials | Service | Where to get credentials | Node(s) to update | |---------|-------------------------|-------------------| | OpenAI | <https://platform.openai.com> → create API key | OpenAI Chat Model | | Microsoft Outlook | Azure/M365 account with email-send permissions | Send email to the submitter | | Twilio | <https://console.twilio.com> → Account SID, Auth Token | Send text to the submitter | Embed the form on your website Open Form to be embedded on website Click “Embed” → copy the iframe code → paste into your contact page Set your Twilio “From” number In Send text to the submitter, change phone to your verified Twilio number Adjust wait times (optional) Wait some time to write the email response (default 1 min) Wait some time to write the text response (default 1 min) Customize the AI prompt (optional) Edit the AI Agent system message to tweak tone, questions asked, or signature Test the flow Open the form URL (generated by the Form node) Submit a test entry → after ~1 min you should receive both an email and an SMS Activate Toggle Active so the form handles real submissions 24/7 🧩 Customization Ideas Pipe form data into Pipedrive, HubSpot, or Airtable for lead tracking Trigger a Slack/Teams alert to notify your team of hot questions Add a calendar link in the email so visitors can book a call instantly Use a language-detection node to reply in the visitor’s native language Contact Email:** rbreen@ynteractive.com Website:** https://ynteractive.com YouTube:** https://www.youtube.com/@ynteractivetraining LinkedIn:** https://www.linkedin.com/in/robertbreen
by Rudi Afandi
Description Turn your Telegram bot into a powerful OCR (Optical Character Recognition) tool. This workflow allows you to send any image (like a screenshot, a photo of a document, or a picture of a sign) to your bot, and it will instantly extract and send back the text from that image. Powered by Google's advanced Gemini AI, this automation is perfect for quickly digitizing notes, saving important snippets, or avoiding manual typing. How it works This workflow performs a few high-level steps: It triggers when a new image is sent to your Telegram bot. It sends the image to the Google Gemini Vision API to be analyzed. It extracts the text found in the image. It sends the extracted text back to you as a message in Telegram. Set up steps Estimated set up time: Less than 5 minutes. The setup is straightforward. You only need to configure two credentials: Telegram Bot Credentials: To connect your bot. Google Gemini API Credentials: To use the OCR feature. You can get a free API key from Google AI Studio.
by Zain Ali
🧾 Generate Project Summary from meeting transcript Who’s it for 🤝 Project managers looking to automate client meeting summaries Client success teams needing structured deliverables from transcripts Agencies and consultants who want consistent, repeatable documentation How it works / What it does ⚙️ Trigger: Manual or webhook trigger kicks off the workflow. Get meeting transcript: Reads the raw transcript from a specified Google Docs file. Generate summary: Sends transcript + instructions to OpenAI (gpt-4.1-mini) to produce a structured project summary. Convert to HTML: Transforms the LLM-generated Markdown into styled HTML. Prepare request: Wraps HTML and metadata into a multipart request body. Create Google Doc: Uploads the new “Project Summary” document into your Drive folder. How to set up 🛠️ Credentials Google Docs & Drive OAuth2 credentials OpenAI API key (gpt-4.1-mini) Nodes configuration Manual Trigger / webhook node Google Docs “Get meeting transcript” node: set documentURL AI Chat Model node: select gpt-4.1-mini Markdown node: enable tables & emoji Google Drive “CreateGoogleDoc” node: set target folder ID Paste in your IDs Update documentURL to your transcript doc Update google_drive_folder_id in the Set node Execute Click “Execute Workflow” or call via webhook Requirements 📋 n8n Google OAuth2 scopes for Docs & Drive OpenAI account with GPT-4.1-mini access A Google Drive folder to store summaries How to customize ✨ Output format**: Edit the Markdown prompt in the ChainLlm node to adjust headings or tone Timeline section**: Extend LLM prompt template with your own phase table Styling**: Tweak inline CSS in the Code node (Prepare_Request) for fonts or margins Trigger**: Swap Manual Trigger for HTTP/Webhook trigger to integrate with other tools Language model**: Upgrade to a different model by changing model.value in the AI node
by Tausif
Guidebook: How the Website ChatBot Template Works Chapter 1: Introduction & Objectives This guidebook provides a comprehensive walkthrough of the Website ChatBot developed using n8n and OpenAI. The chatbot is designed to qualify real estate leads and encourage site visits for the Alcove New Kolkata Sangam project through personalized, intelligent conversations. Chapter 2: Tools Required 1. n8n Workflow Automation Tool An open-source workflow builder to automate data flows between services. 2. OpenAI Account with GPT-4o-mini Access For generating AI-based chatbot responses. 3. Web Chat Widget Frontend integration that sends messages via webhook to the chatbot. Chapter 3: Workflow Breakdown Step 1: Webhook Receives POST requests from the chat widget. Endpoint: /webhook/chatbot-webhook Step 2: Set User Message Extracts message from the JSON body. Stores it as user_message. Step 3: Memory Setup Uses session ID to track conversation across messages. Step 4: OpenAI Chat Model GPT-4o-mini processes queries using the defined agent prompt. Step 5: AI Agent (Khusboo) Persona of a pre-sales agent. Uses AIDA + BANT + SPIN + PAS frameworks. Shares videos, responds in Hinglish, schedules site visits. Step 6: Respond to Webhook Formats the chatbot's reply into a JSON response. Chapter 4: Strategy & Psychology Behind Responses | Framework | Purpose | | --------- | ---------------------------------------------------- | | AIDA | Capture attention, interest, desire, action | | BANT | Qualify Budget, Authority, Need, Timing | | SPIN | Understand user's Situation, Problems, Implications | | PAS | Tackle objections using Problem, Agitation, Solution | The chatbot aims to qualify leads and gently move them toward booking a site visit without pushing or over-informing. Chapter 5: Setup Instructions A. n8n Workflow Setup Import the JSON workflow. Ensure OpenAI credentials are set up. Enable webhook at /webhook/chatbot-webhook. B. Frontend Widget Integration Send message as POST to the webhook with structure: { "message": "Looking for 2 BHK", "session_id": "user123" } Chapter 6: Testing & Troubleshooting Test via Postman Send sample request to verify AI response. Common Issues | Issue | Fix | | ---------------- | ----------------------------------- | | No response | Check webhook URL or credentials | | Repeated replies | Ensure memory node is active | | Wrong language | Check system message language rules | Chapter 7: Sample Conversations User: Hi, I’m looking for a home near the Ganga. Bot: Namaste! Main Khusboo hoon, Alcove New Kolkata Sangam se. Aapka naam kya hai? User: Rajat. Bot: Great Rajat! Kya aap apne family ke saath shift hone ka plan kar rahe ho? ... (continues using frameworks) Chapter 8: FAQs & Maintenance Tips Q: Can I update the AI agent persona? A: Yes, by modifying the system message inside the AI Agent node. Q: How do I share new videos or links? A: Add them in the sharingVideos or UserRequests section in the system message. Q: How to scale this for multiple projects? A: Duplicate the workflow and update the aboutProject and links accordingly. End of Guidebook.
by Lucas Peyrin
How it works This workflow changes the file name, and therefore the extension and MIME type, of any binary file passed to it. This is perfect for converting file formats on the fly, like turning a Telegram voice message (.oga) into an MP3 for an AI transcription service. Set New File Name: The SET OUTPUT FILE NAME node is where you define the desired output file name and extension (e.g., audio.mp3). It also dynamically captures the property name of the incoming binary (e.g., data). Extract Binary Data: The workflow temporarily converts the binary file into a Base64 text string to make it accessible in the next step. Rebuild Binary with New Name: A Code node takes the Base64 data and reconstructs it as a binary file, but this time, it assigns the new file name you specified. n8n automatically sets the MIME type based on the new file extension. Set up steps Setup time: < 1 minute This workflow is designed to be used as a sub-workflow. In your main workflow, add an Execute Sub-Workflow node where you need to change a file's type. In the Workflow parameter, select this "Change Binary MimeType/Extension" workflow. Open this workflow and go to the SET OUTPUT FILE NAME node. Modify the output_file_name value to your desired file name (e.g., voice_message.mp3 or document.pdf). Save this workflow. Now, any binary file you send to it from your main workflow will be returned with the new fileName and mimeType.
by WeblineIndia
This workflow contains community nodes that are only compatible with the self-hosted version of n8n. This workflow automates summarizing YouTube videos by accepting a YouTube URL via a form, fetching the video transcript using Apify, and then generating a concise summary with OpenAI GPT. Setup Instructions Prerequisites: Apify account with access to the YouTube Transcript actor. OpenAI API key (for GPT-4o-mini model). n8n instance with the Apify and OpenAI credentials configured. Configuration Steps Apify Setup: Configure Apify API credentials in the Apify node. Ensure the YouTube Transcript actor ID (1s7eXiaukVuOr4Ueg) is correct. OpenAI Setup: Add your OpenAI API key in the OpenAI Chat Model node. Confirm model selection is set to gpt-4o-mini. Customization Modify form field to accept additional inputs if needed. Adjust Apify actor input JSON in the Payload node for extra metadata extraction. Customize the summarization options to tweak summary length or style. Change OpenAI prompt or model parameters in the OpenAI Chat Model node for different output quality or tone. Steps 1. On Form Submission Node:** Form Trigger Purpose:** Collect the YouTube video URL from the user via a web form. 2. Prepare Payload Node:** Set Purpose:** Format the YouTube URL and options into the JSON payload for Apify input. 3. Fetch Transcript Node:** Apify Purpose:** Run the YouTube Transcript actor to retrieve video captions and metadata. 4. Extract Captions Purpose:** Isolate the captions field from the Apify response for processing. 5. Summarize Transcript Purpose:** Generate a concise summary of the video captions.
by AlexAutomates
Auto-Categorize Outlook Emails with AI in n8n How It Works Trigger: The workflow starts with the Microsoft Outlook Trigger node, polling your inbox every minute for new emails. Extract & Clean Email Content: The email’s key fields (from, subject, isRead, body) are extracted. The body is converted from HTML to Markdown, then sanitized to plain text for reliable AI processing. Node Setup Details: Microsoft Outlook Trigger Resource: Message Operation: Trigger on new email Fields to Output: from, subject, isRead(optional), body Folders to Include: (Set to your Inbox or specific folder IDs) Markdown Node Input: {{$json"body"}} (HTML email body) Output Key: Email Body Markdown Purpose: Converts HTML to Markdown for easier downstream processing. Sanitize Node (Code Node) Input: Email Body Markdown from previous node Purpose: Cleans up Markdown, strips images, links, HTML tags, table formatting, and truncates to 4000 characters. Sample JS Code: // Get the markdown content from the previous node const markdownContent = $input.item.json["Email Body Markdown"]; Setup AI tools Move message and Get Folders Outlook tools are required, get contacts is optional. Set each field in the tools to "defined automatically by the model" and describe each field so the model understands how to use it. OpenRouter or other LLM models tool: You can use any client for this, but make sure to use a model that does well with tool calls (Claude, GPT-4.1, Gemini 2.5 Pro, etc.). Best Practices & Notes AI Prompt Engineering:** The AI is instructed to be conservative—never move emails from real people or saved contacts, and always explain its reasoning if it doesn’t move a message. This automation only works for NEW incoming messages. Inbox Zero:** This system is designed to help you achieve and maintain Inbox Zero by keeping only actionable items in your main inbox. Customization:** You can adjust the folder logic, add more categories, or tweak the AI prompt for your specific needs. Privacy:** All processing happens within your n8n instance; no email data is stored outside your environment except for the AI call (which only receives sanitized, minimal content).
by Mohan Gopal
Overview This release introduces a Voice-Enabled Tour Recommendation System that leverages n8n, ElevenLabs Voice Agent, OpenAI GPT-4o, and Pinecone Vector DB to deliver personalized travel itineraries based on spoken input. Users speak their preferences to the ElevenLabs voice agent, which then triggers an n8n workflow that returns a tailored tour plan. Features Voice interaction with AI-powered travel agent via ElevenLabs Uses ChatGPT-4o for contextual understanding and generation Dynamic query handling with vector-based search using Pinecone Fast response generation using n8n webhook Modular agent memory and role design for scalable enhancement Pre-requisites n8n account with workflow creation access ElevenLabs account with agent and webhook setup OpenAI API key (GPT-4o access) Pinecone account for vector database A list of vectorized tour packages using this n8n embedder (https://creators.n8n.io/workflows/5085) Setup Instructions Step 1: Configure the Voice Agent Webhook in ElevenLabs Use POST method Webhook URL: https://... Breakdown voice input into: Destination Type of tour Number of days Number of passengers Step 2: Set Up the AI Agent Prompt in ElevenLabs Use a conversational style with summaries, clarifying questions, and affirmations. Example Prompt: “You use a natural speech style and periodically summarize... Your goal is to help callers create a personalized tour plan.” Step 3: Select LLM LLM: GPT-4o Mini Memory window: Up to 5 contexts Step 4: Integrate Tools Use Custom Tool: n8n ID: tool_xxxxxx Tool Description: “Generates travel plan once the details are collected” Step 5: Build n8n Workflow Trigger: Webhook (POST) Process user input: Tour Recommendation AI Agent Use OpenAI Chat Model (GPT-4o) for reasoning Query Pinecone Vector Store using Tour Builder Q&A node Respond with structured Itinerary Plan via webhook response How to use: Execute the n8n workflow (the webhook waits for the voice trigger from elevenlabs) Start the Elevenlabs Voice Agent Request for a tour plan to any destination giving the details of your tour preferences. Wait for the Voice Agent to respond back with tour package suggestions after fetching the tour details from the n8n workflow. Close the conversation. | Area | Improvement | | ------------------ | ----------------------------------------------------- | | 🔉 Voice UX | Natural-sounding travel agent using ElevenLabs | | 💡 Personalization | ChatGPT-4o adapts based on travel style & preferences | | 📚 Knowledge Base | Pinecone-powered vector retrieval of real tour data | | 🔁 Reusability | Modular workflow with reusable embedding tools | | ⚙️ System Design | Separation of memory, logic, and data layers | Who is this for? Travel Agencies & DMCs Offer ultra-personalized packages based on customer queries. Let AI do the matching. Tour Package Aggregators Auto-curate and send matching packages from your catalog — no manual searching needed. Content & Marketing Teams Craft customized tour recommendations for email campaigns and newsletters. Tech-enabled Travel Startups Embed this intelligence in your workflows, CRMs, or chatbots to delight customers.
by Guillaume Duvernay
Unlock a new level of sophistication for your AI agents with this template. While the native n8n Think Tool is great for giving an agent an internal monologue, it's limited to one instance. This workflow provides a clever solution using a sub-workflow to create multiple, custom thinking tools, each with its own specific purpose. This template provides the foundation for building agents that can plan, act, and then reflect on their actions before proceeding. Instead of just reacting, your agent can now follow a structured, multi-step reasoning process that you design, leading to more reliable and powerful automations. Who is this for? AI and automation developers:** Anyone looking to build complex, multi-tool agents that require robust logic and planning capabilities. LangChain enthusiasts:** Users familiar with advanced agent concepts like ReAct (Reason-Act) will find this a practical way to implement similar frameworks in n8n. Problem solvers:** If your current agent struggles with complex tasks, giving it distinct steps for planning and reflection can dramatically improve its performance. What problem does this solve? Bypasses the single "Think Tool" limit:** The core of this template is a technique that allows you to add as many distinct thinking steps to your agent as you need. Enables complex reasoning:** You can design a structured thought process for your agent, such as "Plan the entire process," "Execute Step 1," and "Reflect on the result," making it behave more intelligently. Improves agent reliability and debugging:** By forcing the agent to write down its thoughts at different stages, you can easily see its line of reasoning, making it less prone to errors and much easier to debug when things go wrong. Provides a blueprint for sophisticated AI:** This is not just a simple tool; it's a foundational framework for building state-of-the-art AI agents that can handle more nuanced and multi-step tasks. How it works The re-usable "Thinking Space": The magic of this template is a simple sub-workflow that does nothing but receive text. This workflow acts as a reusable "scratchpad." Creating custom thinking tools: In the main workflow, we use the Tool (Workflow) node to call this "scratchpad" sub-workflow multiple times. We give each of these tools a unique name (e.g., Initial thoughts, Additional thoughts). The power of descriptions: The key is the description you give each of these tool nodes. This description tells the agent when and how it should use that specific thinking step. For example, the Initial thoughts tool is described as the place to create a plan at the start of a task. Orchestration via system prompt: The main AI Agent's system prompt acts as the conductor, instructing the agent on the overall process and telling it about its new thinking abilities (e.g., "Always start by using the Initial thoughts tool to make a plan..."). A practical example: This template includes two thinking tools to demonstrate a "Plan and Reflect" cycle, but you can add many more to fit your needs. Setup Add your own "action" tools: This template provides the thinking framework. To make it useful, you need to give the agent something to do. Add your own tools to the AI Agent, such as a web search tool, a database lookup, or an API call. Customize the thinking tools: Edit the description of the existing Initial thoughts and Additional thoughts tools. Make them relevant to the new action tools you've added. For example, "Plan which of the web search or database tools to use." Update the agent's brain: Modify the system prompt in the main AI Agent node. Tell it about the new action tools you've added and how it should use your customized thinking tools to complete its tasks. Connect your AI model: Select the OpenAI Chat Model node and add your credentials. Taking it further Create more granular thinking steps:** Add more thinking tools for different stages of a process, like a "Hypothesize a solution" tool, a "Verify assumptions" tool, or a "Final answer check" tool. Customize the thought process:* You can change *how the agent thinks by editing the prompt inside the fromAI('Thoughts', ...) field within each tool. You could ask for thoughts in a specific format, like bullet points or a JSON object. Change the workflow trigger:** Switch the chat trigger for a Telegram trigger, email, Slack, whatever you need for your use case! Integrate with memory:** For even more power, combine this framework with a long-term memory solution, allowing the agent to reflect on its thoughts from past conversations.