Workflow Templates

Pizza Ordering Chatbot with OpenAI - Menu, Orders & Status Tracking Introduction This workflow template is designed to automate order processing for a pizza store using OpenAI and n8n. The chatbot acts as a virtual assistant to handle customer inquiries related to menu details, order placement, and order status tracking. Features The chatbot provides an interactive experience for customers by performing the following functions: Menu Inquiry: When a customer asks about the menu, the chatbot responds with a list of available pizzas, prices, and additional options. Order Placement: If a customer places an order, the chatbot confirms order details, provides a summary, informs the customer that the order is being processed, and expresses gratitude. Order Status Tracking: If a customer asks about their order status, the chatbot retrieves details such as order date, pizza type, and quantity, providing real-time updates. Prerequisites Before setting up the workflow, ensure you have the following: OpenAI account** (Sign up here) OpenAI API key** to interact with GPT-3.5 n8n instance** running locally or on a server (Installation Guide) Configuration Steps Step 1: Set Up OpenAI API Credentials Log in to OpenAI's website. Navigate to API Keys under your account settings. Click Create API Key and copy the key for later use. Step 2: Configure OpenAI Node in n8n Open n8n and create a new workflow. Click Add Node and search for OpenAI. Select OpenAI from the list. In the OpenAI node settings, click "Create New" under the Credentials section. Enter a name for the credentials (e.g., "PizzaBot OpenAI Key"). Paste your API Key into the field. Click Save. Step 3: Set Up the Chatbot Logic Connect the AI Agent Builder Node to the OpenAI Node and HTTP Request Node. Configure the OpenAI Node with the following settings: Model: gpt-3.5-turbo Prompt: Provide dynamic text based on customer inquiries (e.g., "List available pizzas," "Place an order for Margherita pizza," "Check my order status"). Temperature: Adjust based on desired creativity (recommended: 0.7). Max Tokens: Limit response length (recommended: 150). Add multiple HTTP Request Node: For Get Products: Fetch stored menu data and return details. For Order Product: Capture order details, generate an order ID, and confirm with the customer. For Get Order: Retrieve order details based on the order ID and display progress. Step 4: Testing and Deployment Click Execute Workflow to test the chatbot. Open the Chat Message node, then copy the chat URL to access the chatbot in your browser. Interact with the chatbot by asking different queries (e.g., "What pizzas do you have?" or "I want to order a Pepperoni pizza"). Verify responses and adjust prompts or configurations as needed. Deploy the workflow and integrate it with a messaging platform (e.g., Telegram, WhatsApp, or a website chatbot). Conclusion This n8n workflow enables a fully functional pizza ordering chatbot using OpenAI's GPT-3.5. Customers can view menus, place orders, and track their order status efficiently. You can further customize the chatbot by refining prompts, adding new features, or integrating with external databases for order management. 🚀 Happy automating!

5 nodes5536 views

Enrich Company Data from Google Sheet with OpenAI Agent and ScrapingBee

by Dataki

This workflow demonstrates how to enrich data from a list of companies in a spreadsheet. While this workflow is production-ready if all steps are followed, adding error handling would enhance its robustness. Important notes Check legal regulations**: This workflow involves scraping, so make sure to check the legal regulations around scraping in your country before getting started. Better safe than sorry! Mind those tokens**: OpenAI tokens can add up fast, so keep an eye on usage unless you want a surprising bill that could knock your socks off! 💸 Main Workflow Node 1 - Webhook This node triggers the workflow via a webhook call. You can replace it with any other trigger of your choice, such as form submission, a new row added in Google Sheets, or a manual trigger. Node 2 - Get Rows from Google Sheet This node retrieves the list of companies from your spreadsheet. here is the Google Sheet Template you can use. The columns in this Google Sheet are: Company**: The name of the company Website**: The website URL of the company These two fields are required at this step. Business Area**: The business area deduced by OpenAI from the scraped data Offer**: The offer deduced by OpenAI from the scraped data Value Proposition**: The value proposition deduced by OpenAI from the scraped data Business Model**: The business model deduced by OpenAI from the scraped data ICP**: The Ideal Customer Profile deduced by OpenAI from the scraped data Additional Information**: Information related to the scraped data, including: Information Sufficiency: Description: Indicates if the information was sufficient to provide a full analysis. Options: "Sufficient" or "Insufficient" Insufficient Details: Description: If labeled "Insufficient," specifies what information was missing or needed to complete the analysis. Mismatched Content: Description: Indicates whether the page content aligns with that of a typical company page. Suggested Actions: Description: Provides recommendations if the page content is insufficient or mismatched, such as verifying the URL or searching for alternative sources. Node 3 - Loop Over Items This node ensures that, in subsequent steps, the website in "extra workflow input" corresponds to the row being processed. You can delete this node, but you'll need to ensure that the "query" sent to the scraping workflow corresponds to the website of the specific company being scraped (rather than just the first row). Node 4 - AI Agent This AI agent is configured with a prompt to extract data from the content it receives. The node has three sub-nodes: OpenAI Chat Model: The model used is currently gpt4-o-mini. Call n8n Workflow: This sub-node calls the workflow to use ScrapingBee and retrieves the scraped data. Structured Output Parser: This parser structures the output for clarity and ease of use, and then adds rows to the Google Sheet. Node 5 - Update Company Row in Google Sheet This node updates the specific company's row in Google Sheets with the enriched data. Scraper Agent Workflow Node 1 - Tool Called from Agent This is the trigger for when the AI Agent calls the Scraper. A query is sent with: Company name Website (the URL of the website) Node 2 - Set Company URL This node renames a field, which may seem trivial but is useful for performing transformations on data received from the AI Agent. Node 3 - ScrapingBee: Scrape Company's Website This node scrapes data from the URL provided using ScrapingBee. You can use any scraper of your choice, but ScrapingBee is recommended, as it allows you to configure scraper behavior directly. Once configured, copy the provided "curl" command and import it into n8n. Node 4 - HTML to Markdown This node converts the scraped HTML data to Markdown, which is then sent to OpenAI. The Markdown format generally uses fewer tokens than HTML. Improving the Workflow It's always a pleasure to share workflows, but creators sometimes want to keep some magic to themselves ✨. Here are some ways you can enhance this workflow: Handle potential errors Configure the scraper tool to scrape other pages on the website. Although this will cost more tokens, it can be useful (e.g., scraping "Pricing" or "About Us" pages in addition to the homepage). Instead of Google Sheets, connect directly to your CRM to enrich company data. Trigger the workflow from form submissions on your website and send the scraped data about the lead to a Slack or Teams channel.

CoinMarketCap Telegram Price Bot

by Don Jayamaha Jr

Get real-time cryptocurrency prices directly in Telegram! This workflow integrates CoinMarketCap API with Telegram, allowing users to request live crypto prices simply by sending a message to the bot. Ideal for crypto traders, analysts, and enthusiasts who need quick and easy access to market data. How It Works A Telegram bot listens for user input (e.g., "BTC" for Bitcoin). The workflow sends a request to the CoinMarketCap API to fetch the latest price. The response is processed using an AI-powered language model (GPT-4o-mini) for structured messaging. The workflow logs session data using a memory buffer for better response tracking. The latest price is sent back to the user via Telegram. Set Up Steps Create a Telegram Bot Use @BotFather on Telegram to create a bot and obtain an API token. Get a CoinMarketCap API Key Sign up at CoinMarketCap and retrieve your API key. Configure API Credentials in n8n Add the CoinMarketCap API key under HTTP Header Auth. Add your Telegram bot token under Telegram API credentials. Deploy and Test Send a message (e.g., "BTC") to your Telegram bot and receive live price updates instantly! Automate your crypto price tracking today with this powerful Telegram bot!

5 nodes5842 views

Advanced Retry and Delay Logic

by Viktor Klepikovskyi

Advanced Retry and Delay Logic This template provides a robust solution for handling API rate limits and temporary service outages in n8n workflows. It overcomes the limitations of the default node retry settings, which cap retries at 5 and delays at 5 seconds. By using a custom loop with a Set, If, and Wait node, this workflow gives you complete control over the number of retries and the delay between them. Instructions: Replace the placeholder HTTP Request node with your target node (the one that might fail). In the initial Set Fields node, modify the max_tries value to set the total number of attempts for your workflow. Adjust the delay_seconds value to define the initial delay between retries. Optionally, configure the Edit Fields node to implement exponential backoff by adjusting the delay_seconds expression (e.g., {{$json.delay_seconds * 2}}). For a more detailed breakdown and tutorial of this template, you can find additional information here.

AI-Powered Asana Task Prioritization with GPT-4 and Pinecone Memory

by Yaron Been

Replace manual task prioritization with intelligent AI reasoning that thinks like a Chief Operating Officer. This workflow automatically fetches your Asana tasks every morning, analyzes them using advanced AI models, and delivers the single most critical task with detailed reasoning - ensuring your team always focuses on what matters most. ✨ What This Workflow Does: 📋 Automated Task Collection**: Fetches all assigned Asana tasks daily at 9 AM 🤖 AI-Powered Analysis**: Uses OpenAI GPT-4 to evaluate urgency, impact, and strategic importance 🎯 Smart Prioritization**: Identifies the #1 most critical task with detailed reasoning 🧠 Contextual Memory**: Leverages vector database for historical context and pattern recognition 💾 Structured Storage**: Saves prioritized tasks to PostgreSQL with full audit trail 🔄 Continuous Learning**: Builds organizational knowledge over time for better decisions 🔧 Key Features: Daily automation** with zero manual intervention Context-aware AI** that learns from past prioritization decisions Strategic reasoning** explaining why each task is prioritized Vector-powered memory** using Pinecone for intelligent context retrieval Clean structured output** with task names, priority levels, and detailed justifications Database integration** for reporting and historical analysis 📋 Prerequisites: Asana account with API access OpenAI API key (GPT-4 recommended) PostgreSQL database Pinecone account (for vector storage and context) 🎯 Perfect For: Operations teams managing multiple competing priorities Startups needing systematic task management Project managers juggling complex workflows Leadership teams requiring strategic focus Any organization wanting AI-driven operational intelligence 💡 How It Works: Morning Automation: Triggers every day at 9 AM Data Collection: Pulls all relevant tasks from Asana AI Analysis: Evaluates each task using COO-level strategic thinking Context Retrieval: Searches vector database for similar past tasks Smart Prioritization: Identifies the single most important task Structured Output: Delivers priority level with detailed reasoning Data Storage: Saves results for reporting and continuous improvement 📦 What You Get: Complete n8n workflow with all AI components configured PostgreSQL database schema for task storage Vector database setup for contextual intelligence Comprehensive documentation and setup guide Sample task data and output examples 💡 Need Help or Want to Learn More? Created by Yaron Been - Automation & AI Specialist 📧 Support: Yaron@nofluff.online 🎥 YouTube Tutorials: https://www.youtube.com/@YaronBeen/videos 💼 LinkedIn: https://www.linkedin.com/in/yaronbeen/ Discover more advanced automation workflows and AI integration tutorials on my channels! 🏷️ Tags: AI, OpenAI, Asana, Task Management, COO, Prioritization, Automation, Vector Database, Operations, GPT-4

8 nodes616 views

Form-Based X/Twitter Poster

by Akhil Varma Gadiraju

🚀 Form-Based X/Twitter Poster (v2) A user-friendly n8n workflow that enables users to submit tweets through a simple web form — with optional image, video, or GIF uploads — and posts them to a connected X/Twitter account. Designed for ease of use, this workflow handles both media and text-only posts, providing clear feedback upon submission. 🧭 Overview Workflow Name: Form-Based X/Twitter Poster (v2) Goal: Provide a web form for users to create tweets, upload optional media, and post directly to X/Twitter. 🛠 How It Works 1. Form Submission Trigger Node:** On form submission Type:** formTrigger Purpose:** Renders a web form for tweet creation. Fields:** Post Content: Required textarea for tweet text. Media: Optional file upload (.jpg, .png, .gif, .mp4, etc.). Button:** "Submit" Output:** JSON with text and binary media (if any). 2. Extract Media Details Node:** Extract Media Details Type:** code Purpose:** Extracts tweet text, checks for media, determines media type. Output Example:** { "content": "My tweet!", "mime_type": "image/jpeg", "media_type": "IMAGE" } 3. If Media Exists Node:** If Media Exists Type:** if Purpose:** Checks whether media was uploaded. True Path:** Media was uploaded. False Path:** No media uploaded. 4. Upload Media to X/Twitter (True path only) Node:** Upload Media (X) Type:** httpRequest Purpose:** Uploads media to Twitter via API v1.1. Media Category:** TWEET_IMAGE (can be customized) Auth:** Twitter OAuth1 API Output:** Includes media_id_string 5. Post Tweet with Media (True path) Node:** X Type:** twitter Purpose:** Posts tweet with uploaded media. Auth:** Twitter OAuth2 API 6. Post Text-Only Tweet (False path) Node:** X1 Type:** twitter Purpose:** Posts tweet without media. Auth:** Twitter OAuth2 API 7. Show Confirmation Message Node:** End Form Type:** form Purpose:** Displays thank-you message post-submission. Title:** Thank you so much for sharing your experience on X! 🖤 Message:** We truly appreciate your support and are so glad we could make a positive impact. Your words mean the world to us! 🛠 How to Customize Form Fields:** Change form title, labels, help texts, or file formats. Media Logic:** Add logic for distinguishing GIF vs VIDEO. Adjust media upload URL dynamically: https://upload.twitter.com/1.1/media/upload.json?media_category={{ $json.media_type === 'VIDEO' ? 'TWEET_VIDEO' : ($json.media_type === 'GIF' ? 'TWEET_GIF' : 'TWEET_IMAGE') }} Error Handling:** Add Error Trigger nodes to catch and manage failures gracefully. Tweet Text:** Customize tweet text with extra formatting or default content. Advanced Ideas:** Schedule tweets Post to multiple accounts Add content approval steps 🔐 Required Credentials 1. Twitter OAuth1 API Used by:** Upload Media (X) Required for:** Media upload via v1.1 Credentials:** Consumer Key, Consumer Secret, Access Token, Access Token Secret Workflow Credential Name:** X OAuth - Akhil 2. Twitter OAuth2 API Used by:** X, X1 Required for:** Posting tweets Scopes:** tweet.read, tweet.write, users.read, offline.access Workflow Credential Name:** X OAuth2 - Akhil 💡 Use Cases Easy Tweet Tool:** For non-technical users to share content. Content Approval:** Internal review system before posting. Announcements:** Quickly broadcast updates. Campaign Posting:** Streamline recurring content sharing. 🧑‍💻 Node Naming Suggestions | Old Name | Suggested Name | |--------------------|--------------------------| | If Image Exists | If Media Exists | | X | Post Tweet with Media | | X1 | Post Text-Only Tweet | ❤️ Made with love by Akhil using n8n

Automated Invoice Generator from Google Sheets to Google Docs

by Robert Breen

💬Communication & Collaboration

This workflow automates invoice creation using Google Sheets for structured input and Google Docs for templated output — all built inside n8n. 🛠️ Step-by-Step Instructions ### Step 1: Manual Trigger Start the workflow manually for testing or development purposes. ### Step 2: Google Sheets — Load Invoice Data Pulls invoice data from a Google Sheet. 📄 Sheet URL: Copy This Sheet Expected Columns**: Company From Company To Terms Invoice Description Amount > 🔑 Credentials Required: > Connect to Google Sheets OAuth2 API in n8n. > Be sure your sheet is shared with the connected Google account. ### Step 3: Get Invoice Template — Load Google Doc Loads a static Google Docs template containing placeholder values. 🧾 Template URL: Copy This Template Required Placeholders** in the document: FromCompany# ToCompany# Terms# Invoice# Description# Amount# > 🔑 Credentials Required: > Connect to Google Docs OAuth2 API in n8n. ### Step 4: Create New Doc — Make Invoice File Creates a new Google Doc by duplicating the invoice template. Title Format**: Invoice: {{ $json.Invoice }} Destination Folder ID**: 1TnDibwPPPUm3VbmETiqWDVhtaUTLJ6mn (You can change this to your own Google Drive folder) > 🔐 Make sure your Google Docs credential has write access to this folder. ### Step 5: Merge — Combine Data Merges the loaded document and spreadsheet row together for downstream updates. ### Step 6: Insert Content into Doc (Optional) You can insert additional content here if needed. For example, a note, header, or footer pulled from your database or a custom field. ### Step 7: Input Invoice Details — Replace Fields Uses Google Docs API to replace all placeholders from the original template with the actual values. Replacements: | Placeholder | Replaced With | |----------------|------------------------------| | FromCompany# | Company From from sheet | | ToCompany# | Company To from sheet | | Terms# | Terms from sheet | | Invoice# | Invoice number | | Description# | Description of service | | Amount# | Amount of invoice | 📤 Final Output Each row from the Google Sheet results in a completed, branded Google Doc invoice stored in your Drive. 🙋 Need Help? Robert Breen Automation Consultant 🌐 ynteractive.com 📧 robert.j.breen@gmail.com 🔗 LinkedIn 🔒 Required APIs | Service | Purpose | |------------------|--------------------------| | Google Sheets API | Pull structured invoice data | | Google Docs API | Load & modify invoice documents | | n8n OAuth2 | Connect both services securely | Let me know if you'd like a follow-up step to export invoices as PDFs or auto-email them to clients!

2 nodes2 views

Automated Server Log Cleanup via Email Alerts with SSH - Nginx, Docker, System

by Oneclick AI Squad

💬Communication & Collaboration

This n8n workflow monitors email alerts for disk utilization exceeding 80%, extracts the server IP, logs into the server, and purges logs from Nginx, PM2, Docker, and system files to clear disk space. Key Insights Ensure email alerts are consistently formatted with server IP details. SSH access must be properly configured to avoid authentication failures. Workflow Process Initiate the workflow with the Check Disk Alert Emails node when an email triggers on high disk usage. Parse the email to extract the server IP using the Extract Server IP from Email node. Set up SSH credentials and paths manually with the Prepare SSH Variables node. Execute cleanup commands to delete logs from Nginx, PM2, Docker, and system files using the Run LogCleanup Commands via SSH node. Usage Guide Import the workflow into n8n and configure email and SSH credentials. Test with a sample email alert to verify IP extraction and log deletion. Prerequisites Email service (e.g., IMAP or API) for alert monitoring SSH access with valid credentials Customization Options Modify the Prepare SSH Variables node to target specific log directories or adjust cleanup commands for different server setups.

1 nodes123 views

🛻 AI Agent for Logistics Order Processing with GPT-4o, Gmail and Google Sheet

by Samir Saci

Tags: Supply Chain, Logistics, AI Agents Context Hey! I’m Samir, a Supply Chain Data Scientist from Paris, and the founder of LogiGreen Consulting. We design tools to help companies improve their logistics processes using data analytics, AI, and automation—to reduce costs and minimize environmental impacts. >Let’s use N8N to improve logistics operations! 📬 For business inquiries, you can add me on LinkedIn Who is this template for? This workflow template is designed for logistics or manufacturing operations that receive orders by email. The example above illustrate the challenge we want to tackle using an AI Agent to parse the information and load them in a Google sheet. If you want to understand how I built this workflow, check my detailed tutorial: 🎥 Step-by-Step Tutorial How does it work? The workflow is connected to a Gmail Trigger to open all the emails that include Inbound Order in their subject. The email is parsed by an AI Agent equipped with OpenAI's GPT to collect all the information. The results are pulled in a Google Sheet. These orderlines can then be transferred to warehouse teams to prepare *order receiving. What do I need to get started? You’ll need: Gmail and Google Drive Accounts** with the API credentials to access it via n8n An OpenAI API key (GPT-4o) for the chat model. A Google Sheet with these columns: PO_NUMBER, EXPECTED_DELIVERY DATE, SKU_ID, QUANTITY Next Steps Follow the sticky notes in the workflow to configure each node and start using AI to support your logistic operations. 🚀 Curious how N8N can transform your logistics operations? 📬 Let’s connect on LinkedIn Notes An example of email is included in the template so you can try it with your mailbox. This workflow was built using N8N version 1.82.1 Submitted: March 28, 2025

5 nodes8476 views

Automated AI image tagging and writing keywords into image (via community node)

by Friedemann Schuetz

Welcome to my Automated Image Metadata Tagging Workflow! DISCLAIMER: This workflow only works with self-hosted n8n instances! You have to install the n8n-nodes-exif-data Community Node! This workflow automatically analyzes the image content with the help of AI and writes it directly back into the image file as keywords. (https://n8n.io/workflows/2995).** This workflow has the following steps: Google Drive trigger (scan for new files added in a specific folder) Download the added image file Analyse the content of the image Merge Metadata and image file Write the Keywords into the Metadata (dc:subject/keywords) and create new image file Update the original file in the Google Drive folder The following accesses are required for the workflow: You have to install the n8n-nodes-exif-data Community Node** Google Drive: Documentation AI API access (e.g. via OpenAI, Anthropic, Google or Ollama) You can contact me via LinkedIn, if you have any questions: https://www.linkedin.com/in/friedemann-schuetz

2 nodes1036 views

(De)activate n8n workflows using Telegram commands

by MilanWR

💬Communication & Collaboration

Telegram N8N workflow (de)activator What does it do? This workflow helps you to quickly activate or deactivate a workflow through Telegram. Sometimes we are not able to access a PC to resolve an issue if something goes wrong with a workflow. If you, like me, use Telegram to send yourself error reports, you can quickly react in case of urgency. Just by sending '/stop' combined with the name you use for a workflow, you can deactivate a workflow, or reactivate it with '/start'. For example '/stop marketing'. Walkthrough: https://watch.screencastify.com/v/uWQ88gZKj57WTGOOqSW2 (6min) Instructions Create a Telegram API key through botfather (https://t.me/botfather). Add it to the telegram credentials. For the N8N nodes, go to settings in your n8n instance. Then 'n8n API' and 'create an API key'. To ensure that only we can send commands to the bot, we need the chat ID of our DM with our newly created bot. Open the the Telegram trigger and click on 'listen to events'. Go to Telegram and send a direct message to the bot, this will trigger the Telegram node. Go to the filter node and fill in the chat id you want to filter for with the data you got from the test event in the Telegram node. In the first Switch node you can find the commands, in this case it is '/start' and '/stop'. When you send a message to your bot starting with either of those, it will go to the next switch nodes. Next it will check what other word it contains. As an example I have used the words 'marketing' and 'sales', both corresponding to a marketing and sales workflow. The last nodes will either activate or deactivate a workflow.