Workflow Templates

This n8n template demonstrates the beginnings of building your own n8n-powered WhatsApp chatbot! Under the hood, utilise n8n's powerful AI features to handle different message types and use an AI agent to respond to the user. A powerful tool for any use-case! How it works Incoming WhatsApp Trigger provides a way to get messages into the workflow. The message received is extracted and sent through 1 of 4 branches for processing. Each processing branch uses AI to analyse, summarize or transcribe the message so that the AI agent can understand it. The supported types are text, image, audio (voice notes) and video. The AI Agent is used to generate a response generally and uses a wikipedia tool for more complex queries. Finally, the response message is sent back to the WhatsApp user using the WhatsApp node. How to use Once you have setup and configured your WhatsApp account, you'll need to activate your workflow to start processing messages. Good to know: Large media files may negatively impact workflow performance. Requirements WhatsApp Buisness account Google Gemini for LLM. Gemini is used specifically because it can accept audio and video files whereas at time of writing, many other providers like OpenAI's GPT, do not. Customising this workflow For performance reasons, consider detecting large audio and video before sending to the LLM. Pre-processing such files may allow your agent to perform better. Go beyond and create rich and engagement customer experiences by responding using images, audio and video instead of just text!

This n8n workflow template lets you easily generate comprehensive FAQ (Frequently Asked Questions) content for multiple services (or any items or pages you need to add the FAQs to). Simply provide the Google Sheets document containing the items to scrape, and the workflow automatically creates detailed, AI-enhanced FAQ documents. How it works The workflow reads data from a Google Sheets document containing information about different services and categories (again, in your case - whatever objects you need). For each service and category, it generates a set of standard questions and answers covering setup, permissions, integrations, use cases, and pricing benefits. An AI model (OpenAI's GPT) is used to enhance or complete some of the answers, making the content more comprehensive and natural-sounding. The workflow formats the Q&A pairs, combining AI-generated content with predefined answers where applicable. It creates a text file (JSON) for each service or category, containing the formatted Q&A pairs. The generated files are saved to specific folders in Google Drive, organized by the type of integration (native, credential-only, non-native) or category. After processing each service or category, it updates the status in the original Google Sheets document to mark it as completed. Ideal for: Marketing teams: Rapidly create comprehensive FAQ documents for multiple products or services. Customer support: Generate consistent and detailed answers for common customer queries. Product managers: Easily maintain up-to-date documentation as products evolve. Content creators: Streamline the process of creating informative content about various offerings. Accounts required Google account (for Google Sheets and Google Drive) OpenAI API account (for AI-enhanced content generation) n8n.io account (for workflow execution) Set up instructions Set up the required credentials for Google Sheets, Google Drive, and OpenAI when you first open the workflow. Prepare your Google Sheets document with the service/category information. Here's an example of Google Sheet. Fill the "Define Sheets" node with your sheets Adjust the folder IDs in the "Prepare Job" node to match your Google Drive structure. Configure the OpenAI model settings in the "OpenAI Chat Model" node if needed. Test the workflow with a small subset of data before running it on your entire dataset. Adjust the questions asked in the "Create your Q&A templates" section After testing, activate your workflow for automated FAQ generation. 🙏 Big, big kudos to Jim Le for his ideas, input and support when building this workflow. Your approach to AI workflows is always super helpful!

Split Test Agent Prompts with Supabase and OpenAI Use Case Oftentimes, it's useful to test different settings for a large language model in production against various metrics. Split testing is a good method for doing this. What it Does This workflow randomly assigns chat sessions to one of two prompts, the baseline and the alternative. The agent will use the same prompt for all interactions in that chat session. How it Works When messages arrive, a table containing information regarding session ID and which prompt to use is checked to see if the chat already exists If it does not, the session ID is added to the table and a prompt is randomly assigned These values are then used to generate a response Setup Create a table in Supabase called split_test_sessions. It needs to have the following columns: session_id (text) and show_alternative (bool) Add your Supabase, OpenAI, and PostgreSQL credentials Modify the Define Path Values node to set the baseline and alternative prompt values. Activate the workflow and test by sending messages through n8n's inbuilt chat Experiment with different chat sessions to test see both prompts in action Next Steps Modify the workflow to test different LLM settings such as temperature Add a method to measure the efficacy of the two alternative prompts

Automate tweet engagement on X (formerly Twitter) Description Automate professional engagement on X (formerly Twitter) by searching for, filtering, liking, and replying to tweets that match your key topics. This workflow enables you to engage consistently and efficiently with relevant conversations, using your defined professional role and the power of GPT for filtering and replies. Save time and maintain high-quality interactions, while staying focused on your business or personal brand interests. How it Works Rotating Topic Selection The workflow selects one search term from your list on each run, using a rotating index based on the date. Search Tweets & Extract Essentials Searches X (formerly Twitter) for tweets matching the chosen topic, then extracts only the tweet id and text for further processing. GPT‑Based Filtering with Role Context Filters tweets based on your role and strict criteria, removing non-English tweets, memes, spam, Grok-generated content, political posts, internships, and more. Engagement Loop For every filtered tweet, the workflow likes the post, generates a professional, concise reply with GPT (matching language and context), and posts the reply. Wait nodes ensure compliance with Twitter’s API rate limits (can be adjusted for paid API tiers). Requirements X (Twitter) API credentials (for searching, liking, and replying to tweets) OpenAI API key (for GPT-based steps) Setup Steps Obtain your X (Twitter) API credentials. Obtain your OpenAI API key. Configure the schedule in the trigger node to your desired frequency (e.g., every 3 days or daily). Set your list of topics and professional role in the variables node. How to Customize the Workflow (Optional) Adjust prompts** in the GPT nodes to fine-tune filtering and reply style. Upgrade your Twitter API plan** to increase request limits and search for more tweets per run. Change tweet processing logic:** For high-volume engagement (e.g., analyzing 100+ tweets per run), consider switching to a per-tweet loop for advanced filtering and response handling. This workflow enables scalable, professional, and targeted engagement on X (formerly Twitter), fully customizable to your audience and objectives.

This n8n template demonstrates how you can automate community moderation using human-in-the-loop functionality for Discord. The use-case is for detecting and dealing with spam messages in a predefined and consistent way. Human-in-the-loop allows for a balance between overly aggressive bots and time and effort from the moderation team. How it works A scheduled trigger is used to scan the most recent messages in a Discord Channel. Messages are tagged via the "Remove Duplicates" node so they don't get processed again in the future. Messages are grouped by user to allow for minimising of number of notifications sent. An AI text classifier node is then used to detect for spam in each user's message. When detected, a notification is sent to a moderation channel using the Send-and-wait mode for Discord. This notification comes with an n8n form and dropdown list of predefined actions to take in dealing with the spam messages. Once sent the workflow waits until a response is received. Once a moderator selects an action, the workflow continues and carries out a predefined moderation action. How to use Depending on how busy your community is and subject to spammers, you may need to increase the scheduled interval. Add as many or few moderation actions as required. Remember to activate the workflow to get it started. Requirements Discord channel for messages to moderate OpenAI for text classification Customising this template It is possible to cover multiple channels. Add as many as your community needs. Not using Discord. The template can also work in slack or other services which offer the same bot functionality.

This n8n template combines an AI agent with n8n's multi-page forms to create a novel interaction which allows automated question-and-answer sessions. One of the more obvious use-cases of this interaction is what I'm calling the AI interviewer. You can read the full post here: https://community.n8n.io/t/build-your-own-ai-interview-agents-with-n8n-forms/62312 Live demo here: https://jimleuk.app.n8n.cloud/form/driving-lessons-survey How it works A form trigger is used to start the interview and a new session is created in redis to capture the transcript. An AI agent is then tasked to ask questions to the user regarding the topic of the interview. This is setup as a loop so the questions never stop unless the user wishes to end the interview. Each answer is recorded in our session set up earlier between questions. When the user requests to end the interview we break the loop and show the interview completion screen. Finally, the session is then saved in a Google Sheet which can then be shared with team members and for the purpose of data analysis. How to use You'll need to be on a n8n instance that is accessible to your target audience. Not technical enough to setup your own server? Try out n8n cloud and instantly deploy template! Remember to activate the workflow so the form trigger is published and available for users to use. Requirements Groq LLM for AI agent. Feel free to swap this out for any other LLM. Redis(-compatible) storage for capturing sessions Customising this workflow The next step would be adding tools! AI interviews with knowledge retrieval could definitely open up other possibilities. Eg. An onboarding wizard generating questions by pulling facts from internal knowledgebase.

Who is this for? BlueSky users who are looking to send a "welcome message" to their new followers as a private message. What this workflow does This worflow will check for new followers on BlueSky every 60 minutes and send a private message to the new ones. Setup You need to create a BlueSky app password with private messages access. Fill your credentials and the message text on the corresponding nodes (see sticky notes). Manually run once the `Save followers to file` node to generate your initial followers list. Enable the workflow How to customize this workflow to your needs You can adjust the check frecuency, but be careful to avoid hitting the 100 createSession per day rate limit Feedback or comments You can leave comments, feedback or improvements about this workflow on the n8n forums

Phishing Email Detection and Reporting with n8n Who is this for? This workflow is designed for IT teams, security professionals, and managed service providers (MSPs) looking to automate the process of detecting, analyzing, and reporting phishing emails. What problem is this workflow solving? Phishing emails are a significant cybersecurity threat, and manually detecting and reporting them is time-consuming and prone to errors. This workflow streamlines the process by automating email analysis, generating detailed reports, and logging incidents in a centralized system like Jira. What this workflow does This workflow automates phishing email detection and reporting by integrating Gmail and Microsoft Outlook email triggers, analyzing the content and headers of incoming emails, and generating Jira tickets for flagged phishing emails. Here’s what happens: Email Triggers: Captures incoming emails from Gmail or Microsoft Outlook. Email Analysis: Extracts email content, headers, and metadata for analysis. HTML Screenshot: Converts the email’s HTML body into a visual screenshot. AI Phishing Detection: Leverages ChatGPT to analyze the email and detect potential phishing indicators. Jira Integration: Automatically creates a Jira ticket with detailed analysis and attaches the email screenshot for review by the security team. Customizable Reports: Includes options to customize ticket descriptions and adapt the workflow to organizational needs. Setup Authentication: Set up Gmail and Microsoft Outlook OAuth credentials in n8n to access your email accounts securely. API Keys: Add API credentials for the HTML screenshot service (hcti.io) and ChatGPT. Jira Integration: Configure your Jira project and issue types in the workflow. Workflow Configuration: Update sticky notes and nodes to include any additional setup or configuration details unique to your system. How to customize this workflow to your needs Email Filters**: Modify email triggers to filter specific subjects or sender addresses. Analysis Scope**: Adjust the ChatGPT prompt to refine phishing detection logic. Integration**: Replace Jira with your preferred ticketing system or modify the ticket fields to include additional information. This workflow provides an end-to-end automated solution for phishing email management, enhancing efficiency and reducing security risks. It’s perfect for teams looking to minimize manual effort and improve incident response times.

Use case LLMs have provided a lot of value for several use cases. Especially some OpenAI models are proving to be quite valuable. However, it's sometimes not super accessible to chat with these models. This workflow enables you to chate directly with OpenAI's GPT-3.5 via Telegram. How it works A simple telegram bot that connects to your botfather bot to give AI responses, using OpenAI's GPT 3.5 model, to a user's messages with emojis. What to do Add your telegram API key and your OpenAI api key and have fun!

Purpose This ensures that executions of scheduled workflows do not overlap when they take longer than expected. How it works This is a separate workflow which monitors the execution of the main workflow Stores a flag in Redis (key dynamically named after workflow ID) which indicates if the main workflow is running or idle Only calls the main workflow if the last execution has finished Setup Update the credentials suitable for your Redis instance Replace the Schedule Trigger of your main workflow by an Execute Workflow Trigger Copy the workflow ID from the URL Paste the workflow ID in the Execute Workflow Node of this workflow Configure the Schedule Trigger Node

This n8n template demonstrates how to calculate the evaluation metric "Correctness" which in this scenario, measures the compares and classifies the agent's response against a set of ground truths. The scoring approach is adapted from the open-source evaluations project RAGAS and you can see the source here https://github.com/explodinggradients/ragas/blob/main/ragas/src/ragas/metrics/_answer_correctness.py How it works This evaluation works best where the agent's response is allowed to be more verbose and conversational. For our scoring, we classify the agent's response into 3 buckets: True Positive (in answer and ground truth), False Positive (in answer but not ground truth) and False Negative (not in answer but in ground truth). We also calculate an average similarity score on the agent's response against all ground truths. The classification and the similarity score is then averaged to give the final score. A high score indicates the agent is accurate whereas a low score could indicate the agent has incorrect training data or is not providing a comprehensive enough answer. Requirements n8n version 1.94+ Check out this Google Sheet for a sample data https://docs.google.com/spreadsheets/d/1YOnu2JJjlxd787AuYcg-wKbkjyjyZFgASYVV0jsij5Y/edit?usp=sharing

Usecase: When a new service ticket is created in Taiga, it's often unclear whether it contains sufficient details to begin work. This workflow automates the triage process by: Using an AI model to extract key information from the ticket description. Automatically assigning values for: Type (Bug, Enhancement, Onboarding, Question) Severity (Wishlist, Minor, Normal, Important, Critical) Priority (Low, Normal, High) Status (New, Needs More Info, etc.) Detecting missing critical data and blocking the ticket if incomplete. Setup instructions here: https://github.com/emooney/Service_Ticket_Triage_Helper