Workflow Templates

Website AI Agent with Calendar Integration Categories: AI Agents, Website Integration, Calendar Automation This workflow creates a complete website AI agent that can be embedded on any website with just a few lines of code. The agent handles customer inquiries, provides business information, and automatically books meetings by checking calendar availability in real-time. Built for simplicity and business practicality, this system proves that effective AI agents don't need to be overcomplicated. Benefits Universal Website Integration** - Works with WordPress, Webflow, Squarespace, custom sites, or any platform that accepts HTML Intelligent Calendar Management** - Checks availability and books meetings automatically without double-booking Business-Ready Conversations** - Trained with specific business context and maintains professional, helpful interactions Real-Time Functionality** - All changes to the N8N workflow are immediately reflected on your live website No Technical Complexity** - Simple architecture that prioritizes reliability and consistent outputs over flashy features Customizable Branding** - Easy to modify appearance, messages, and behavior to match your brand How It Works Embedded Chat Interface: Generates embeddable HTML code that creates a chat widget on any website Provides both hosted and embedded modes for different use cases Handles all communication between website visitors and the AI system Intelligent Conversation Management: Uses sophisticated system prompts to maintain context about your business Handles common inquiries about services, pricing, and company information Gracefully redirects off-topic conversations back to business matters Smart Calendar Integration: Connects to Google Calendar to check real-time availability Automatically suggests meeting times based on your schedule Collects all necessary information (name, email, preferred time) before booking Meeting Booking Process: Validates meeting requests against existing calendar entries Confirms all details with users before creating calendar events Sends automatic invitations with proper timezone handling Required Setup Configuration System Message Requirements: Your AI agent needs a comprehensive system message that includes: Business Identity:** Company name, services, location, timezone Business Context:** What you offer, pricing information, key differentiators Conversation Rules:** How to handle inquiries, booking procedures, moderation guidelines Personality Instructions:** Tone of voice, response style, conversation length preferences Example System Message Structure: You are a helpful, intelligent website chatbot for [Company Name], a [business type]. The current date is [dynamic date]. You are in the [timezone] timezone. Business Context: We offer [services] with [key benefits] Our pricing is [pricing structure] We work with [target customers] Your task is answering questions about the business & booking meetings. For meetings: use calendar function to check availability, collect name/email/preferred time, confirm details. Rules: Keep responses short and conversational Stay focused on business topics Always confirm timezone when discussing meeting times Google Calendar Setup: Enable Google Calendar API in Google Cloud Console Create OAuth2 credentials for N8N Connect your business calendar in the Google Calendar nodes Set correct timezone in both nodes to match your business location Website Integration: Switch chat trigger to "embedded" mode Copy the provided CDN embed code Paste code into your website's HTML (before closing body tag) Replace webhook URL with your production URL Business Use Cases Service Businesses** - Automate initial consultations and lead qualification Agencies** - Handle project inquiries and schedule discovery calls Consultants** - Streamline the booking process for potential clients E-commerce** - Provide product support and schedule demos Any Business** - Replace contact forms with intelligent conversation Revenue Potential This system can replace expensive chatbot services that cost $100-500/month. The automated booking feature alone typically increases meeting conversion rates by 40-60% compared to traditional contact forms. Difficulty Level: Beginner Estimated Build Time: 15-20 minutes Monthly Operating Cost: ~$10 (OpenAI API usage) Watch My 13-Minute Build Want to see exactly how I built this from scratch? I walk through the complete setup process in real-time, including all the configuration, testing, and website integration. 🎥 See My Complete Build Process: "How to Build a Website AI Agent in 13 Min (Free N8N Template)" This step-by-step tutorial shows you my exact process for creating business-ready AI agents that actually make money, not just impressive demos. Set Up Steps Basic Agent Configuration: Create new N8N workflow with AI Agent node Connect OpenAI Chat Model with your API credentials Add Window Buffer Memory for conversation context System Message Setup: Configure detailed business context and operating instructions Set timezone and personality parameters for consistent responses Define conversation rules and moderation guidelines Google Calendar Integration: Set up Google Calendar credentials through Google Cloud Console Configure "Get All Events" tool for availability checking Set up "Create Event" tool for automated booking Website Embedding: Switch chat trigger to "embedded" mode for website integration Copy the provided CDN embed code Paste code into your website's HTML with your webhook URL Customization Options: Modify initial messages and branding in the embed code Adjust colors and styling using CSS variables Configure timezone settings to match your business location Testing & Optimization: Test complete conversation flows from inquiry to booking Verify calendar integration works correctly with your timezone Optimize system prompts based on actual user interactions Advanced Features Extend this system with additional capabilities: CRM Integration** - Automatically add leads to your sales pipeline Multi-language Support** - Handle conversations in different languages Custom Business Logic** - Add specific qualification questions or routing Analytics Tracking** - Monitor conversation patterns and conversion rates Check Out My Channel For more practical automation systems that generate real business value, check out my YouTube channel where I share the exact strategies I used to scale my automation agency to $72K/month.

Real-time Weather Forecasts with MCP Tools This n8n workflow demonstrates how to integrate real-time weather intelligence into any automation using the Model Context Protocol (MCP). Get current conditions and 5-day forecasts with natural language queries like "What's the weather like in Miami?" or "Will it rain next Tuesday in Seattle?" - all powered by live weather data and AI. Good to know No API keys required - uses hosted MCP weather server with built-in WorldWeatherOnline integration Provides current conditions and detailed 5-day forecasts Natural language queries work for any location worldwide Powered by WorldWeatherOnline - the world's most accurate weather system Fully preconfigured and ready to run out-of-the-box Enterprise-ready with error handling and rate limiting How it works Natural Language Input**: Receives weather queries via webhook, chat, email, or voice AI Agent Processing**: n8n Agent node interprets requests and determines: Location extraction from natural language Weather data type needed (current or 5-day forecast) Response formatting preferences MCP Weather Tool**: Live hosted server provides: Real-time current conditions (temperature, humidity, wind, conditions) 5-day detailed forecasts with daily highs/lows Weather descriptions and condition codes Powered by WorldWeatherOnline's premium data Intelligent Responses**: AI formats weather data into: Conversational natural language responses Structured data for downstream automation Action-triggering data for workflows How to use Import the workflow into n8n from the template Add your preferred AI model API key to the Agent node Customize the system prompt for your specific use case Connect to your preferred input/output channels Run and start querying weather with natural language Use Cases Smart Home Automation**: "Turn on sprinklers if no rain forecast for 3 days" Travel Planning**: "Check weather for my Paris trip next week" Event Management**: "Will outdoor wedding conditions be good Saturday?" Agriculture/Farming**: "Check 5-day forecast for planting schedule" Logistics**: "Delay shipping if severe weather forecast in delivery zone" Personal Assistant**: "Should I wear a jacket today in Chicago?" Sports/Recreation**: "Surf conditions and wind forecast for weekend" Construction**: "Safe working conditions for outdoor project this week" Requirements n8n instance (cloud or self-hosted) AI model provider account (OpenAI, Anthropic, Google, etc.) Internet connection for MCP weather server access Optional: Webhook endpoints for external integrations Customizing this workflow Location Intelligence**: Add geocoding for address-to-coordinates conversion Data Storage**: Save weather history to databases for trend analysis Dashboard Integration**: Connect to Grafana, Tableau, or custom visualizations Voice Integration**: Add speech-to-text for voice weather queries Scheduling**: Set up automated daily/weekly weather briefings Conditional Logic**: Trigger different actions based on weather conditions Sample Input/Output Natural Language Queries: "What's the weather like in Miami?" "Will it rain next Tuesday in Seattle?" "5-day forecast for London" "Temperature in Tokyo tomorrow" "Weather conditions for outdoor event Saturday" Rich Responses: { "location": "Miami, FL", "current": { "temperature": "78°F", "condition": "Partly Cloudy", "humidity": "65%", "wind": "10 mph SE" }, "forecast": { "today": "High 82°F, Low 71°F, 20% rain", "tomorrow": "High 85°F, Low 73°F, Sunny" }, "ai_summary": "Perfect beach weather in Miami today! Partly cloudy with comfortable temperatures and light winds." } Why This Workflow is Unique Zero Setup Weather Data**: No API key management - MCP server handles everything World-Class Accuracy**: Powered by WorldWeatherOnline's premium weather data AI-Powered Intelligence**: Natural language understanding of complex weather queries Enterprise Ready**: Built-in error handling, rate limiting, and reliability Global Coverage**: Worldwide weather data with location intelligence Action-Oriented**: Designed for automation decisions, not just information display Transform your automations with intelligent weather awareness powered by the world's most accurate weather system! 🧪 Setup Steps ✅ The Agent node is already configured: The system prompt is included The tool endpoint is pre-set All you need to do is: Add your AI model API key to the existing Agent credential Hit run and you're done ✅ 🔗 Full project link: Github: weathertrax-mcp-agent-demo

I am submitting this workflow for the Obsidian community to showcase the potential of integrating Obsidian with n8n. While straightforward, it serves as a compelling demonstration of the potential unlocked by integrating Obsidian with n8n. How it works This workflow lets you retrieve specific Airtable data you need in seconds, directly within your Obsidian note, using n8n. By highlighting a question in Obsidian and sending it to a webhook via the Post Webhook Plugin, you can fetch specific data from your Airtable base and instantly insert the response back into your note. The workflow leverages OpenAI’s GPT model to interpret your query, extract relevant data from Airtable, and format the result for seamless integration into your note. Set up steps Install the Post Webhook Plugin: Add this plugin to your Obsidian vault from the plugin store or GitHub. Set up the n8n Webhook: Copy the webhook URL generated in this workflow and insert it into the Post Webhook Plugin's settings in Obsidian. Configure Airtable Access: Link your Airtable account and specify the desired base and table to pull data from. Test the Workflow: Highlight a question in your Obsidian note, use the “Send Selection to Webhook” command, and verify that data is returned as expected.

Who Is This For? This workflow is perfect for content creators, marketers, and business professionals who receive regular newsletters and want to effortlessly convert them into engaging LinkedIn posts. By automating the extraction and repurposing process, you can save time and consistently share thoughtful updates with your network. What Problem Does This Workflow Solve? Manually reading newsletters, extracting the key points, and then formatting that content into professional, engaging LinkedIn posts can be time-consuming and error-prone. This workflow automates those steps by: Filtering Emails:** Uses the Gmail node to process only those emails from a specific sender (e.g., newsletter@example.com). Extracting Content:** Leverages OpenAI to identify and summarize the top news items in your newsletter. Generating Posts:** Crafts concise, insightful LinkedIn posts in a smart, deadpan style with a touch of subtle humor. Publishing:** Posts the generated content directly to LinkedIn. What This Workflow Does Filter Newsletters:** The Gmail node is set up to only handle emails from your chosen sender, ensuring that only relevant newsletters are processed. Extract Key Content:** An OpenAI node analyzes the newsletter text to pull out the most important news items, including headlines and summaries. Split Content:** A Split Out node divides the extracted content so each news item is processed on its own. Generate LinkedIn Posts:** Another OpenAI node takes each news item's details and produces a well-structured LinkedIn post that delivers practical insights and ends with a reflective observation or question. Publish to LinkedIn:** The LinkedIn node publishes the crafted posts directly to your account. Setup Gmail Node: Rename it to “Filter Gmail Newsletter” and configure it to filter emails by your newsletter sender. OpenAI Nodes: Ensure your OpenAI API credentials are set up correctly. Customize the prompt if needed to match your desired tone. LinkedIn Node: Rename it to “Post to LinkedIn” and confirm that your LinkedIn OAuth2 credentials are properly configured. How to Customize OpenAI Prompts:** Adjust the prompts in the OpenAI nodes to fine-tune the post tone and output formatting. Email Filter:** Change the Gmail filter to match the sender of your newsletters. Post Processing:** Optionally, add extra formatting (using Function nodes) to further enhance the readability of the generated LinkedIn posts. This template offers an automated, hands-off solution to transform your newsletter content into engaging LinkedIn updates, keeping your audience informed and inspired with minimal effort.

Google Sheets UI for Workflow Control This n8n template provides a practical and efficient way to manage your n8n workflows using Google Sheets as a user-friendly interface. It demonstrates how to leverage a simple spreadsheet to control inputs, capture outputs, and track the processing status of individual data rows, offering a clear and visual overview of your automation tasks. Purpose of This Template: The primary purpose of this template is to illustrate how Google Sheets can serve as a dynamic UI for your n8n automations. It's designed for n8n users who need: A structured method to feed specific data into their workflows. The ability to selectively trigger workflow execution based on data status. A centralized place to view and store workflow outputs alongside original inputs. A simple, no-code solution for managing workflow data without building custom applications. Setup Instructions: To use this template, follow these steps: Create a Google Sheet: Set up a new Google Sheet (see the template here) with three columns: Color, Status, and Number. Populate the Color column with some sample data (e.g., color names) and set the Status for the rows you want to process to READY. Import the n8n Workflow: Import this n8n template into your n8n instance. Configure Google Sheets Nodes: For the first Google Sheets node (Read operation), ensure it's connected to your newly created Google Sheet and configured to read rows where the Status column is READY. You will need to authenticate your Google Sheets account. For the second Google Sheets node (Update operation), ensure it's also connected to the same Google Sheet. The node should automatically map the row_number, Number, and Status fields from the preceding nodes. Execute the Workflow: Run the workflow. Observe how it reads READY rows, processes them (calculates string length), and updates the Number and Status columns in your Google Sheet to DONE. Control Execution: To process new data, simply add new rows to your Google Sheet and set their Status to READY. Rerunning the workflow will then only process these new entries. For more details and context on this approach, you can refer to the related blog post here.

This workflow demonstrates how to use the workflowStaticData() function to set any type of variable that will persist within workflow executions. https://docs.n8n.io/code/cookbook/builtin/get-workflow-static-data/ This can be useful for example when working with access tokens that expire after a certain time period. Using staticData we can keep a record of that access token and the expiry time and build our workflow logic around it. Important Static Data only persists across production executions, i.e. triggered by Webhooks or Schedule Triggers (not manual executions!) For this the workflow will have to be activated. Setup configure HTTP Request node to fetch access token from your API (optional) activate workflow test the workflow with the webhook production link you can check the population of the static data in the single executions Feedback If you found this useful or want to report some missing information - I'd be happy to hear from you at ria@n8n.io

Extract Title tag and meta description from url for SEO analysis. How it works The workflows takes records from Airtable, get the url in the records and extract from the related webpage the title tag (<title>) and meta description (<meta name="description" content="Some content">). If title tag and/or meta description tag isn't available on the webpage, the result will be empty. Setup Set a Base in Airtable with a table with the following structure: url (field type url), title tag (field type text string), meta desc (field type text field) Minimum suggested table structure is: url (https://example.com), title (Title example), meta desc* (This is the meta description of the example page) Connect Airtable to both Airtable nodes in the template and, with the following formula, get all the records that miss title tag and meta desc. Formula: AND(url != "", {title tag} = "", {meta desc} = "") Insert the url to be analyzed in the table in the field url and let the workflow do the rest. Extra You can also calculate the length for title tag and meta desc using formula field inside Airtable. This is the formula: LEN({title tag}) or LEN({meta desc}) You can automate the process calling a Webhook from Airtable. For this, you need an Airtable paid plan.

This workflow compares two lists of objects (List A and List B) using a user-specified key (e.g. email, id, domain) and returns: Items common to both lists (based on the key) Items only in List A Items only in List B How it works: Accepts a JSON input containing: listA: the first list of items listB: the second list of items key: the field name to use for comparison Performs a field-based comparison using the specified key Returns a structured output: common: items with matching keys (only one version retained) onlyInA: items found only in List A onlyInB: items found only in List B Example Input: { "key": "email", "listA": [ { "email": "alice@example.com", "name": "Alice" }, { "email": "bob@example.com", "name": "Bob" } ], "listB": [ { "email": "bob@example.com", "name": "Bobby" }, { "email": "carol@example.com", "name": "Carol" } ] } Output: common: [ { "email": "bob@example.com", "name": "Bob" } ] onlyInA: [ { "email": "alice@example.com", "name": "Alice" } ] onlyInB: [ { "email": "carol@example.com", "name": "Carol" } ] Use Cases: Deduplicate data between two sources Find overlapping records Identify new or missing entries across systems This workflow is useful for internal data auditing, list reconciliation, transaction reconciliation, or pre-processing sync jobs.

Send structured logs to BetterStack from any workflow using HTTP Request Who is this for? This workflow is perfect for automation builders, developers, and DevOps teams using n8n who want to send structured log messages to BetterStack Logs. Whether you're monitoring mission-critical workflows or simply want centralized visibility into process execution, this reusable log template makes integration easy. What problem is this workflow solving? Logging failures or events across multiple workflows typically requires duplicated logic. This workflow solves that by acting as a shared log sender, letting you forward consistent log entries from any other workflow using the Execute Workflow node. What this workflow does Accepts level (e.g., "info", "warn", "error") and message fields via Execute Workflow Trigger Sends the structured log to your BetterStack ingestion endpoint via HTTP Request Uses HTTP Header Auth for secure delivery Includes a manual trigger for testing and a sample call to demonstrate usage Comes with clear sticky notes to help you get started Setup Copy your BetterStack Logs ingestion URL. Create a Header Auth credential in n8n with your Authorization: Bearer YOUR_API_KEY. Replace the URL in the HTTP Request node with your BetterStack endpoint. Optionally modify the test data or log levels for custom scenarios. Use Execute Workflow in any of your workflows to send logs here.

This workflow is designed for freelancers, solopreneurs, and business owners who receive a high volume of irrelevant messages in their Gmail inbox — from cold offers to spammy promotions — and want to automatically filter and delete them using AI. Its main purpose is to scan new emails with the help of OpenAI, classify their content, and automatically delete those considered marketing (OFFER) or junk (SPAM). The result is a cleaner inbox without the need to manually sift through low-value messages. The classification logic uses a detailed system prompt with practical examples, so even complex or borderline messages are categorized accurately. Important emails — such as payment confirmations, shipping updates, or genuine business inquiries — remain untouched. This helps maintain a professional inbox with only valuable and relevant communication. The entire process runs automatically in the background and can be customized further — for example, to archive instead of delete, or log deleted emails for review. How it works When triggered (every hour), the workflow fetches new Gmail messages using the Gmail Trigger node. Each message is passed to an AI classifier powered by OpenAI, which reads the message body (email snippet) and returns one of three labels: SPAM: Obvious junk messages, scams, or low-effort bulk messages OFFER: Cold outreach, discount promotions, cart reminders, or generic advertising IMPORTANT: Valuable information for the user, even if commercial (e.g., invoices, order updates, personal inquiries) The workflow then routes the result through an IF node. If the message is marked as SPAM or OFFER, it is immediately deleted from Gmail via the Gmail Delete node. Emails marked as IMPORTANT are ignored and remain in the inbox. The classification is entirely AI-driven based on message content — sender address, headers, or metadata are not used. How to set up To get started, simply connect two credentials: A Gmail account using OAuth2 (via the Gmail Trigger and Gmail Delete nodes) An OpenAI API key (used by the AI classifier node) No advanced setup is needed beyond these two connections. Optionally, you can review or modify the system prompt used for classification — it’s available inside the workflow’s LangChain AI Agent node. The prompt is in English, so it’s recommended to use this workflow with English-language emails for best results. By default, the workflow deletes matching emails immediately. If you prefer safer testing, you can modify the Gmail node to archive, label, or log emails instead of deleting them. The full workflow takes around 5–10 minutes to configure and includes a sticky note with additional instructions and warnings.

Who is this template for? This template is for any Microsoft Outlook user who wants a trained AI agent to reason and reply on their behalf. Teach your agent tone and writing style to replicate your own, or develop a persona for a shared inbox. Requirements Outlook with authentication credentials OpenAI account with authentication credentials A few sample email replies of various lengths and topics How it works: Connect your Outlook account. Select (filter) which email sender(s) your trained AI agent will reply to. [Tip: pick a sender that has some repeatability either with a topic (ie. sales) or an individual (coworker@yourcompany.com)] Connect your OpenAI account. Choose your AI model (ie. gpt-4o-mini) Add Prompt (User Message) and select "system message" from the option below Update the instructions by filling in your name (or persona), response style, and add full email replies from the topic or individual you want the AI agent to emulate. [Tip: Add actual replies from your email sent folder, including your greeting and sign off. Paste each email sample between a set of <example> .... </example> tags] Configure the reply (or reply all) to remain within the original email string Test it! Send an email from the address to which your agent wants to respond. Check your sent (or draft) folder for the result. Enjoy all the free time you now have!! If you have questions or need assistance, email us at: support@teambisonandbird.com ++This template does not include retrieving email addresses out of the message or body of the email.++

Description This template provides a simple and powerful backend for adding speech-to-text capabilities to any application. It creates a dedicated webhook that receives an audio file, transcribes it using OpenAI's gpt-4o-mini model, and returns the clean text. To help you get started immediately, you'll find a complete, ready-to-use HTML code example right inside the workflow in a sticky note. This code creates a functional recording interface you can use for testing or as a foundation for your own design. Who is this for? Developers:** Quickly add a transcription feature to your application by calling this webhook from your existing frontend or backend code. No-code/Low-code builders:** Embed a functional audio recorder and transcription service into your projects by using the example code found inside the workflow. API enthusiasts:** A lean, practical example of how to use n8n to wrap a service like OpenAI into your own secure and scalable API endpoint. What problem does this solve? Provides a ready-made API:** Instantly gives you a secure webhook to handle audio file uploads and transcription processing without any server setup. Decouples frontend from backend:** Your application only needs to know about one simple webhook URL, allowing you to change the backend logic in n8n without touching your app's code. Offers a clear implementation pattern:** The included example code provides a working demonstration of how to send an audio file from a browser and handle the response—a pattern you can replicate in any framework. How it works This solution works by defining a clear API contract between your application (the client) and the n8n workflow (the backend). The client-side technique: Your application's interface records or selects an audio file. It then makes a POST request to the n8n webhook URL, sending the audio file as multipart/form-data. It waits for the response from the webhook, parses the JSON body, and extracts the value of the Transcript key. You can see this exact pattern in action in the example code provided in the workflow's sticky note. The n8n workflow (backend): The Webhook node catches the incoming POST request and grabs the audio file. The HTTP Request node sends this file to the OpenAI API. The Set node isolates the transcript text from the API's response. The Respond to Webhook node sends a clean JSON object ({"Transcript": "your text here..."}) back to your application. Setup Configure the n8n workflow: In the Transcribe with OpenAI node, add your OpenAI API credentials. Activate the workflow to enable the endpoint. Click the "Copy" button on the Webhook node to get your unique Production Webhook URL. Integrate with the frontend: Inside the workflow, find the sticky note labeled "Example Frontend Code Below". Copy the complete HTML from the note below it. ⚠️ Important: In the code you just copied, find the line const WEBHOOK_URL = 'YOUR WEBHOOK URL'; and replace the placeholder with the Production Webhook URL from n8n. Save the code as an HTML file and open it in your browser to test. Taking it further Save transcripts:* Add an *Airtable* or *Google Sheets** node to log every transcript that comes through the workflow. Error handling:** Enhance the workflow to catch potential errors from the OpenAI API and respond with a clear error message. Analyze the transcript:* Add a *Language Model** node after the transcription step to summarize the text, classify its sentiment, or extract key entities before sending the response.