Workflow Templates

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.++

What it is: In version 1.78, n8n introduced a dedicated node to use the OpenRouter service, which lets you to use a lot of different LLM models and providers and change models on the fly in an agentic workflow. For prior n8n versions, there's a workaround to make OpenRouter accessible, by using the OpenAI node with a OpenRouter-specific BaseURL. This trivial workflow demonstrates this for version before 1.78, so that you can use different LLM model dynamically with the available n8n nodes for OpenAI LLM and OpenAI credentials. What you can do: Use any of the OpenRouter models Have the model even dynamically configured or changing (by some external config, some rule, or some specific chat message) Setup steps: Import the workflow Ensure you have registered and account, purchased some credits and created and API key for OpenRouter.ai Configure the "OpenRouter" credentials with your own credentials, using an OpenAI type credential, but making sure in the credential's config form its "Base URL" is set to https://openrouter.ai/api/v1 so OpenRouter is used instead of OpenAI. Open the "Settings" node and change the model value to any valid model id from the OpenRouter models list or even have the model property set dynamically

Intro This template is for project managers, team leads, or anyone who wants to automatically remind teammates of tasks due today—no manual copy‑and‑paste required. How it works Schedule Trigger runs every morning at 8 AM. Google Sheets node reads your “Tasks” sheet. If node filters rows where Due Date = today. Summarize (ChatGPT HTTP Request) generates a friendly reminder per person. Message a model sends the prompt to your ChatGPT Assistant and returns the AI response. Send a message (Gmail) emails each assignee their personalized reminder. Required Google Sheet Structure | Column Name | Type | Example | Notes | |-------------|--------|---------------------------|-------------------------| | Name | string | Alice Johnson | Person to remind | | Email | string | user@example.com | Recipient email address | | Task | string | Submit quarterly report | Task description | | Due Date | date | 2025‑07‑29 | Format: YYYY‑MM‑DD | Detailed Setup Steps Google Sheets Create your sheet with the columns above. In n8n → Credentials, add Google Sheets API (do not include real sheet IDs in the name). ChatGPT Assistant In the OpenAI Dashboard → Assistants, click Create Assistant. Choose a model (e.g., gpt-4), copy the Assistant ID. In n8n → Credentials → OpenAI, add your API Key and Assistant ID. Gmail In n8n → Credentials → Gmail (OAuth2 or SMTP), connect your account without embedding your real address in the credential name. Import & Configure Export this workflow’s JSON (three‑dot menu → Export). Paste it under Template Code in the Creator form. In each node, select your Google Sheets, OpenAI, and Gmail credentials. Sticky Notes A note on the Schedule node: “Set your desired run time.” A note on the ChatGPT node: “Customizes reminder text.” A note on the Gmail node: “Sends reminder email.” Customization Guidance Change schedule: edit the Cron expression in **Schedule Trigger. Adjust tone**: modify the system prompt in your ChatGPT Assistant. Email format: update **Subject and Body in the Gmail node. Batch processing: insert a **SplitInBatches node before Summarize for large sheets. Troubleshooting Ensure your Google Sheet is shared with the connected service account. Verify Due Date format (YYYY‑MM‑DD). If ChatGPT fails, check your API key and quota. Security & Best Practices Do not** hard‑code API keys, sheet IDs, or real emails. Use n8n Credentials or environment variables only. Remove any private information before submitting.

This workflow contains community nodes that are only compatible with the self-hosted version of n8n. How it works This workflow demonstrates how to create a resilient AI Agent that automatically falls back to a different language model if the primary one fails. This is useful for handling API errors, rate limits, or model outages without interrupting your process. State Initialization: The Agent Variables node initializes a fail_count to 0. This counter tracks how many models have been attempted. Dynamic Model Selection: The Fallback Models (a LangChain Code node) acts as a router. It receives a list of all connected AI models and, based on the current fail_count, selects which one to use for this attempt (0 for the first model, 1 for the second, etc.). Agent Execution: The AI Agent node attempts to run your prompt using the model selected by the router. The Fallback Loop: On Success: The workflow completes successfully. On Error: If the AI Agent node fails, its "On Error" output is triggered. This path loops back to the Agent Variables node, which increments the fail_count by 1. The process then repeats, causing the Fallback Models router to select the next model in the list. Final Failure: If all connected models are tried and fail, the workflow will stop with an error. Set up steps Setup time: ~3-5 minutes Configure Credentials: Ensure you have the necessary credentials (e.g., for OpenAI, Google AI) configured in your n8n instance. Define Your Model Chain: Add the AI model nodes you want to use to the canvas (e.g., OpenAI, Google Gemini, Anthropic). Connect them to the Fallback Models node. Important: The order in which you connect the models determines the fallback order. The model nodes first created/connected will be tried first. Set Your Prompt: Open the AI Agent node and enter the prompt you want to execute. Test: Run the workflow. To test the fallback logic, you can temporarily disable the First Model node or configure it with invalid credentials to force an error.

Who is this tempate 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 👉 Setup Google sheets credentials 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 Template Stock sheet |Case ID|Phone Model|Case Name|Case Type|Image URL|Quantity Avaialble|Initital 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

Who is this for? This workflow is designed for SEO specialists, content creators, marketers, and website developers who want to ensure their web content is easily accessible, understandable, and indexable by Large Language Models (LLMs) like ChatGPT, Perplexity, and Google AI Overviews. If you're looking to optimize your site for the evolving AI-driven search landscape, this template is for you. What problem is this workflow solving? / Use case Modern AI tools often crawl websites without executing JavaScript. This can lead to them "seeing" a very different version of your page than a human user or traditional search engine bot might. This workflow helps you: Identify how much of your content is visible without JavaScript. Check for crucial on-page SEO elements that AI relies on (headings, meta descriptions, structured data). Detect if your site presents JavaScript-blocking warnings. Get an AI-generated readability score and actionable recommendations to improve AI-friendliness. What this workflow does Receives a URL via a chat interface. Sanitizes the input URL to ensure it's correctly formatted. Fetches the website's HTML content, simulating a non-JavaScript crawler (like Googlebot). Extracts key HTML features: visible text length, presence of H1/H2/H3 tags, meta description, Open Graph data, structured data (JSON-LD), and <noscript> tags. It also checks for common JavaScript-blocking messages. Performs an AI SEO Analysis using an LLM (via OpenAI) based on the extracted features. Provides a report including an AI Readability Score (0-10), a summary, actionable recommendations, and a reminder to check the robots.txt file for AI bot access. Setup Estimated setup time:** 2-5 minutes. Import this workflow into your n8n instance. Ensure you have an OpenAI account and API key. Configure the "OpenAI Chat Model" node with your OpenAI API credentials. If you don't have credentials set up yet, create new ones in n8n. Activate the workflow. Interact with the chat interface provided by the "When chat message received" trigger node (you can access this via its webhook URL). How to customize this workflow to your needs Change LLM Model:** In the "OpenAI Chat Model" node, you can select a different model that suits your needs or budget. Adjust AI Prompt:** Modify the prompt in the "AI SEO Analysis" node (Chain Llm) to change the focus of the analysis or the format of the report. For example, you could ask for more technical details or a different scoring system. User-Agent:** The "Get HTML from Website" node uses a Googlebot User-Agent. You can change this to simulate other bots if needed. JS Block Indicators:** The "Extract HTML Features" node contains a list of common JavaScript-blocking phrases. You can expand this list with other languages or specific messages relevant to your checks.

Overview This workflow answers user requests sent via Mac Shortcuts Several Shortcuts call the same webhook, with a query and a type of query Types of query are: translate to english translate to spanish correct grammar (without changing the actual content) make content shorter make content longer How it works Select a text you are writing Launch the shortcut The text is sent to the webhook Depending on the type of request, a different prompt is used Each request is sent to an OpenAI node The workflow responds to the request with the response from GPT Shortcut replace the selected text with the new one For a demo and setup instructions: How to use it Activate the workflow Download this Shortcut template Install the shortcut In step 2 of the shortcut, change the url of the Webhook In Shortcut details, "add Keyboard Shortcut" with the key you want to use to launch the shortcut Go to settings, advanced, check "Allow running scripts" You are ready to use the shortcut. Select a text and hit the keyboard shortcut you just defined

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.

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.

What This Workflow Does: This n8n workflow automatically generates an AI-powered summary and relevant tags whenever a new row is added to your Notion database. Simply save any URL to your Notion database using the [Notion Web Clipper] Chrome extension or [Save to Notion]—on both desktop and mobile. This keeps all your saved content organized in one place instead of scattered across different platforms. How it works: The workflow is triggered when a new row is added to your Notion database (it checks for updates every minute). It retrieves the content from the saved URL. An AI agent analyzes the content to generate a summary and relevant tags. The AI output is then formatted properly. Finally, the formatted summary and tags are saved into the appropriate columns in your Notion database. Notes: Make sure your Notion database includes the following columns: URL – Stores the content URL you want to summarize. AI Summary – Where the AI-generated summary will be added. Tags – Where the AI-generated tags will be saved.

Intro: The purpose of this workflow is to simply convert you planned Grocery delivery confirmation email to a Google Calendar event in your family calendar. While based on a Monoprix.fr email format, it is applicable/adaptable to almost anything else. How it works: It is triggered by reception of the confirmation email on your Gmail. The workflow then extracts relevant data using ChatGPT, formats it, and creates a Google Calendar event. Steps to use it: Import template in your n8n Update credentials for Gmail, Google Calendar, and ChatGPT Test workflow based on confirmation email received Activate workflow

This workflow analyzes images submitted via a form using OpenAI Vision, then delivers the analysis result directly to your Telegram chat. ✅ Use case examples: • Users submit screenshots for instant AI interpretation • Automated document or receipt analysis with Telegram delivery • Quick OCR or image classification workflows ⸻ ⚙️ Setup Guide Form Submission Trigger • Connect your form app (e.g. Typeform, Tally, or n8n’s own webhook form) to the On form submission trigger node. • Ensure it sends the image file or URL as input. OpenAI Vision Analysis • In the OpenAI node, select Analyze Image operation. • Provide your OpenAI API key and configure the prompt to instruct the model on what to analyze (e.g. “Describe this receipt in detail”). Set Telegram Chat ID • Use this manual node to input your Telegram Chat ID for delivery. • Alternatively, automate this with a database lookup or user session if building for multiple users. Telegram Delivery Node • Connect your Telegram Bot to n8n using your bot token. • Set up the sendMessage operation, using the analysis result from the previous node as the message text. Testing • Click Execute workflow. • Submit an image via your form and confirm it delivers to your Telegram as expected.