Workflow Templates

How It Works This workflow automates the analysis of security alerts from Sophos Central, turning raw events into actionable intelligence. It uses the official Sophos SIEM integration tool to fetch data, enriches it with VirusTotal, and leverages Google Gemini to provide a real-time threat summary and mitigation plan via Telegram. Prerequisite (Important): This workflow is triggered by a webhook that receives data from an external Python script. You must first set up the Sophos-Central-SIEM-Integration script from the official Sophos GitHub. This script will fetch data and forward it to your n8n webhook URL. Tool Source Code: Sophos/Sophos-Central-SIEM-Integration The n8n Workflow Steps Webhook: Receives enriched event and alert data from the external Python script. IF (Filter): Immediately filters the incoming data to ensure only events with a high or critical severity are processed, reducing noise from low-priority alerts. Code (Prepare Indicator): Intelligently inspects the Sophos event data to extract the primary threat indicator. It prioritizes indicators in the following order: File Hash (SHA256), URL/Domain, or Source IP. HTTP Request (VirusTotal): The extracted indicator is sent to the VirusTotal API to get a detailed reputation report, including how many security vendors flagged it as malicious. Code (Prompt for Gemini): The raw JSON output from VirusTotal is processed into a clean, human-readable summary and a detailed list of flagging vendors. AI Agent (Google Gemini): All collected data—the original Sophos log, the full alert details, and the formatted VirusTotal reputation—is compiled into a detailed prompt for Gemini. The AI acts as a virtual SOC analyst to: Create a concise incident summary. Determine the risk level. Provide a list of concrete, actionable mitigation steps. Telegram: The complete analysis and mitigation plan from Gemini is formatted into a clean, easy-to-read message and sent to your specified Telegram chat. Setup Instructions Configure the external Python script to forward events to this workflow's Production URL. In n8n, create Credentials for Google Gemini, VirusTotal, and Telegram. Assign the newly created credentials to the corresponding nodes in the workflow.

The Error Notification workflow is designed to instantly notify you whenever any other n8n workflow encounters an error, using popular communication channels like Telegram and Gmail—with optional support for Discord, Slack, and WhatsApp. 💡 Why Use Error Notification workflow? Immediate Awareness:** Get instant alerts when workflows fail, preventing unnoticed errors and downtime. Multi-Channel Flexibility:** Notify your team via Telegram, Gmail, and optionally Slack, Discord, or WhatsApp. Detailed Context:** Receive rich error information including the error message, node name, time, and execution link for quicker fixes. Easy Integration:** Built with native n8n nodes and customizable code, simple to adopt without complex setup. Open Source & Free:** Use and adapt this workflow at no cost, making professional error monitoring accessible. ⚡ Who Is This For? n8n Workflow Developers:** Quickly spot and respond to automation issues in development or production. Operations Teams:** Maintain uptime and swiftly troubleshoot errors across multiple workflows. Small to Medium Businesses:** Gain professional error alerting without expensive monitoring tools. Automation Enthusiasts:** Enhance your automation reliability with real-time failure notifications. ❓ What Problem Does It Solve? This workflow embedd error detection and notification directly within your n8n instance. It automates the process of catching errors as they occur, compiling meaningful context, and delivering it instantly via your preferred messaging platforms. This drastically reduces your response time to issues and streamlines error management, improving your automation reliability and operational confidence. 🔧 What This Workflow Does ⏱ Trigger: Listens for any error generated in your n8n workflows using the n8n Error Trigger node. 📎 Step 2: Executes a Code node that formats a detailed error message capturing workflow name, error node, description, timestamp, and an execution URL. 🔍 Step 3: Sends the formatted error notification to multiple communication channels: Telegram and Gmail by default, plus optionally Discord, Slack, and WhatsApp (disabled by default). 💌 Step 4: Delivers rich, parsed HTML-formatted messages to ensure error readability and immediate actionability. 🔐 Setup Instructions Import the provided .json file into your n8n instance (Cloud or self-hosted). Set up credentials: Gmail OAuth credentials for sending emails via Gmail node Telegram API credentials for Telegram notifications (Optional) Discord Webhook URL credential for Discord notifications (Optional) Slack Webhook credential for Slack notifications (Optional) WhatsApp connection credentials (if enabled) Customize the Code node if needed to adjust the error message format or target chat IDs. Update the chat IDs and recipient details in each notification node according to your channels. Test the workflow by manually triggering an error in another workflow to verify proper notifications. 🧩 Pre-Requirements Active n8n instance (cloud or self-hosted) with version supporting Error Trigger node Telegram bot credentials and chat ID (Optional) Gmail, Discord, Slack, or WhatsApp accounts and webhook credentials if you want to use those channels 🛠️ Customize It Further Enable and configure additional notification nodes like Slack or WhatsApp to fit your team's communication style. Customize the error message template in the Code node to include extra metadata or format it differently (e.g., markdown). Integrate with incident management tools via webhook nodes or create tickets automatically on error. 🧠 Nodes Used Error Trigger Code Telegram Gmail Discord (disabled) Slack (disabled) WhatsApp (disabled) Sticky Note (for description) 📞 Support Made by: khaisa Studio Tag: notification,error,monitoring,workflow,automation,alerts Category: Monitoring & Alerts Need a custom? Need a custom? contact me on LinkedIn or Web

This n8n workflow automates personalized travel assistance via WhatsApp through a friendly virtual agent named Alex. It helps users plan trips, explore destinations, get visa/weather/hotel information, and book packages—all through a conversational interface. The system ensures quick, human-like support 24/7, improving customer experience and reducing manual handling by travel agents. Key Features The Travel Assistant agent provides contextual responses based on conversation history stored in memory. Alex maintains a friendly, professional tone throughout all interactions to enhance user experience. The workflow includes intelligent waiting mechanisms to ensure proper response processing. Memory functionality allows for seamless continuation of conversations across multiple interactions. Workflow Process The Get WhatsApp Message node captures incoming messages from users on WhatsApp, initiating the travel assistance process. The Travel Assistant node processes user queries using AI to understand travel needs and generate appropriate responses for trip planning, destination information, visa requirements, weather updates, and booking assistance. The Travel Plan Creator agent works in conjunction with the main assistant to generate detailed itineraries and travel recommendations based on user preferences. The Memory node stores conversation context and user preferences, enabling personalized responses and seamless conversation flow across multiple interactions. The Wait For Response node introduces intelligent delays to ensure proper message processing and natural conversation pacing. The Send Reply On WhatsApp node delivers the AI-generated travel assistance back to the user through WhatsApp messaging. Setup Instructions Import the workflow into n8n and configure WhatsApp Business API credentials for message handling. Set up the AI service for the Travel Assistant and Travel Plan Creator agents with your preferred language model. Configure the Memory node with appropriate storage settings for conversation persistence. Test the workflow by sending various travel-related queries through WhatsApp to ensure proper responses. Monitor conversation quality and adjust AI parameters as needed for optimal user experience. Prerequisites WhatsApp Business API access or WhatsApp integration service AI/LLM service for travel assistance (OpenAI, Anthropic, or similar) Database or storage service for conversation memory Access to travel data APIs for real-time information (weather, visa requirements, hotel availability) Modification Options Modify the Travel Assistant node to include specific travel databases, local recommendations, or branded responses. Adjust the conversation memory settings to control how much context is retained across interactions. Customize the Travel Plan Creator to include preferred booking platforms, hotel chains, or travel partners. Add additional specialized agents for specific travel services like flight booking, car rentals, or activity reservations. Configure response timing in the Wait For Response node to match your desired conversation flow.

This n8n workflow demonstrates how we can use Multimodal LLMs to parse and extract from PDF documents in n8n. In this particular scenario, we're passing a candidate's CV/resume to an AI which filters out unqualified applications. However, this sneaky candidate has added in hidden prompt to bypass our bot! Whatever will we do? No fret, using AI Vision is one approach to solve this problem... read on! How it works Our candidate's CV/Resume is a PDF downloaded via Google Drive for this demonstration. The PDF is then converted into an image PNG using a tool called Stirling PDF. Since the hidden prompt has a white font color, it is is invisible in the converted image. The image is then forwarded to a Basic LLM node to process using our multimodal model - in this example, we'll use Google's Gemini 1.5 Pro. In the Basic LLM node, we'll need to set a User Message with the type of Binary. This allows us to directly send the image file in our request. The LLM is now immune to the hidden prompt and its response is has expected. The example CV/Resume with hidden prompt can be found here: https://drive.google.com/file/d/1MORAdeev6cMcTJBV2EYALAwll8gCDRav/view?usp=sharing Requirements Google Gemini API Key. Alternatively, GPT4 will also work for this use-case. Stirling PDF or another service which can convert PDFs into images. Note for data privacy, this example uses a public API and it is recommended that you self-host and use a private instance of Stirling PDF instead. Customising the workflow Swap out the manual trigger for another trigger such as a webhook to integrate into your existing services. This example demonstrates a validation use-case ie. "does the candidate look qualified?". You can try additionally extracting data points instead such as years of experiences, previous companies etc.

This n8n workflow automatically creates friendly, personalized travel itineraries based on messages received via email or WhatsApp. When a user says "I want to go to Dubai with friends for 5 days" or something similar, the AI agent understands the request, generates a detailed daily plan with suggested activities, transport tips, and hotel ideas — all in a warm, human tone. It saves time, adds value for travelers, and delivers ready-to-send itineraries without any manual effort. Good to know The AI agent uses advanced language processing to understand natural travel requests in multiple formats. Itineraries are generated with personalized recommendations based on travel preferences, group size, and duration. The workflow supports both email and WhatsApp communication channels for maximum accessibility. All responses maintain a warm, friendly tone to enhance user experience. How it works The Get Query from Email node captures travel requests sent via email, parsing the message content for trip details. The Get Query from WhatsApp node simultaneously monitors WhatsApp messages for travel planning requests. Both inputs feed into the Itinerary Creator Agent node, which uses AI to analyze the request and generate comprehensive travel plans including activities, accommodations, and transportation suggestions. The Check Proper Data node validates the generated itinerary to ensure all essential information is included and properly formatted. The Check where to send Answer node determines the appropriate response channel (email or WhatsApp) based on the original request source. If the request came via email, the Sending Itinerary from Email node sends the personalized itinerary back to the user's email address. If the request came via WhatsApp, the Send Itinerary from message node delivers the travel plan through WhatsApp messaging. How to use Import the workflow into n8n and configure the nodes with your email service credentials and WhatsApp API access. Set up the AI agent with your preferred travel data sources and recommendation algorithms. Test the workflow by sending sample travel requests through both email and WhatsApp channels. Monitor the generated itineraries to ensure quality and adjust the AI agent parameters as needed. Requirements Email service API credentials (SMTP or email provider API) WhatsApp Business API access or WhatsApp integration service AI/LLM service for the Itinerary Creator Agent (OpenAI, Anthropic, or similar) Access to travel data sources for recommendations (optional but recommended) Customising this workflow Modify the Itinerary Creator Agent node to include specific travel preferences, local recommendations, or branded content. Adjust the data validation rules in the Check Proper Data node to match your quality standards. Customize response templates in both sending nodes to align with your brand voice and style. Add additional input channels or integrate with other messaging platforms as needed.

Purpose of workflow: The purpose of this workflow is to automate scraping of a website, transforming it into a structured format, and loading it directly into a Google Sheets spreadsheet. How it works: Web Scraping: Uses the Jina AI service to scrape website data and convert it into LLM-friendly text. Information Extraction: Employs an AI node to extract specific book details (title, price, availability, image URL, product URL) from the scraped data. Data Splitting: Splits the extracted information into individual book entries. Google Sheets Integration: Automatically populates a Google Sheets spreadsheet with the structured book data. Step by step setup: Set up Jina AI service: Sign up for a Jina AI account and obtain an API key. Configure the HTTP Request node: Enter the Jina AI URL with the target website. Add the API key to the request headers for authentication. Set up the Information Extractor node: Use Claude AI to generate a JSON schema for data extraction. Upload a screenshot of the target website to Claude AI. Ask Claude AI to suggest a JSON schema for extracting required information. Copy the generated schema into the Information Extractor node. Configure the Split node: Set it up to separate the extracted data into individual book entries. Set up the Google Sheets node: Create a Google Sheets spreadsheet with columns for title, price, availability, image URL, and product URL. Configure the node to map the extracted data to the appropriate columns.

This n8n workflow shows how using multimodal LLMs with AI vision can tackle tricky image validation tasks which are near impossible to achieve with code and often impractical to be done by humans at scale. You may need image validation when users submitted photos or images are required to meet certain criteria before being accepted. A wine review website may require users only submit photos of wine with labels, a bank may require account holders to submit scanned documents for verification etc. In this demonstration, our scenario will be to analyse a set of portraits to verify if they meet the criteria for valid passport photos according to the UK government website (https://www.gov.uk/photos-for-passports). How it works Our set of portaits are jpg files downloaded from our Google Drive using the Google Drive node. Each image is resized using the Edit Image node to ensure a balance between resolution and processing speed. Using the Basic LLM node, we'll define a "user message" option with the type of binary (data). This will allow us to pass our portrait to the LLM as an input. With our prompt containing the criteria pulled off the passport photo requirements webpage, the LLM is able to validate the photo does or doesn't meet its criteria. A structured output parser is used to structure the LLM's response to a JSON object which has the "is_valid" boolean property. This can be useful to further extend the workflow. Requirements Google Gemini API key Google Drive account Customising this workflow Not using Gemini? n8n's LLM node works with any compatible multimodal LLM so feel free to swap Gemini out for OpenAI's GPT4o or Antrophic's Claude Sonnet. Don't need to validate portraits? Try other use cases such as document classification, security footage analysis, people tagging in photos and more.

This workflow contains community nodes that are only compatible with the self-hosted version of n8n. ❓ What Problem Does It Solve? Manual transcription and action planning from meeting notes is often error-prone, time-consuming, and inconsistent. Important tasks, decisions, or deadlines can be overlooked or delayed. This workflow solves these pain points by automatically analyzing notes using AI and turning them into actionable, structured data. It drastically reduces follow-up delays, miscommunications, and administrative effort, letting teams focus on execution instead. 💡 Why Use Google Meet Automation? Save Hours of Manual Work:** Automatically transform raw meeting notes into structured tasks and emails without lifting a finger. Ensure Accurate Follow-up:** Never miss important action items or decisions buried in text; everything is extracted and assigned clearly. Improve Team Collaboration:** Instantly distribute meeting summaries and next steps to attendees, keeping everyone aligned. Leverage Advanced AI:** Utilize Google Gemini’s powerful natural language processing tailored specifically for meetings. Fully End-to-End Automated:** From receiving notes to task creation and email dispatch — your post-meeting workflow is completely hands-free. ⚡ Who Is This For? Project Managers:** Streamline task delegation and keep project timelines on track. Team Leads:** Quickly communicate key takeaways and follow-ups to team members. Sales and Account Teams:** Document client meetings efficiently and automate follow-up outreach. Remote Teams:** Ensure clarity and continuity after virtual meetings. Executives:** Get concise summaries and important decision logs automatically. 🔧 What This Workflow Does ⏱ Trigger: Activated via a POST webhook receiving meeting notes, title, attendees, date, and duration. 📎 Step 2: Validates inputs; if missing required fields, sends an error response. 🔍 Step 3: Extracts and formats meeting data into structured variables for processing. 🤖 Step 4: Sends meeting notes to Google Gemini AI for advanced analysis to identify action items, decisions, summaries, follow-ups, and dates. 💌 Step 5: Splits AI responses to create Google Tasks from action items and send personalized follow-up emails via Gmail. 🗂 Step 6: Generates a Google Docs meeting summary document and finally returns a success response with all processed results. 🔐 Setup Instructions Import the provided Google Meet Automation.json file into your n8n instance. use Payload example Set up credentials for: Google OAuth2 API (Google Tasks, Google Docs) Gmail OAuth2 API for sending emails Google Palm API (for Google Gemini AI access) Customize workflow parameters: Webhook URL and access permissions Google Tasks project or folders if applicable Email templates if desired (subject line, branding) Update any API endpoints or credential references to match your account setup. Thoroughly test with sample meeting note payloads to ensure smooth execution. 🧩 Pre-Requirements Active n8n instance (Cloud or Self-hosted) Google Cloud Platform project with: Google Tasks API enabled Google Docs API enabled Gmail API enabled Google Palm API access (Google Gemini AI) Valid OAuth2 credentials configured in n8n for above services API quota and permissions for sending emails, creating docs, and tasks 🛠️ Customize It Further Integrate with calendar apps (Google Calendar, Outlook) to auto-schedule next meetings. Add Slack or Microsoft Teams notifications for real-time alerts. Extend AI prompt for deeper insights like sentiment analysis or risk flags. Customize email templates with branding, signatures, or attachments. Connect task outputs with project management tools like Asana, Trello, or Jira. 📞 Support Made by: khaisa Studio Tag: automation, google meet, meeting notes, AI, google tasks, gmail, google docs Category: Productivity Need a custom? Contact Us

What this workflow does This workflow helps HR teams screen CVs with AI, store compatibility ratings in Google Sheets, and send email notifications to candidates and HR. It simplifies the recruitment process. CV Submission Form: Candidates submit their details and CV (PDF) through a web form, triggering the workflow in n8n. PDF Extraction & AI Rating: The submitted CV is processed to extract text, and AI analyzes it to generate a compatibility rating. Results Storage & Notifications: Ratings are stored in a Google Sheet for easy access and organization. Confirmation emails are automatically sent to both HR and the candidate. Setup Use the provided template to configure your form and connect it to n8n. Ensure your Google Sheets and email service integrations are active. Customization Instructions: Modify the email template to match your organization’s branding. Adjust the AI compatibility rating thresholds based on your requirements. Ensure you have updated the prompt for cv screening.

Company Website Chatbot Agent Overview This workflow implements a modular Website AI Chatbot Assistant capable of handling multiple types of customer interactions autonomously. Instead of relying on a single large agent to handle all logic and tools, this system routes user queries to specialized sub-agents—each dedicated to a specific function. By using a manager-style orchestration layer, this approach prevents overloading a single AI model with excessive context, leading to cleaner routing, faster execution, and easier scaling as your automation needs grow. How It Works 1. Chat Trigger The flow is initiated when a chat message is received via the website widget. 2. Manager Agent (Ultimate Website AI Assistant) The central LLM-based agent is responsible for parsing the message and deciding which specialized sub-agent to route it to. It uses an OpenAI GPT model for natural language understanding and a lightweight memory system to preserve recent context. 3. Sub-Agent Routing calendarAgent: Handles availability checks and books meetings on connected calendars. RAGAgent: Searches company documentation or FAQs to provide accurate responses from your internal knowledge base. ticketAgent: Forwards requests to human support by generating and sending support tickets to a designated email. Setup Instructions Embed the Chatbot Use a custom HTML widget or script to embed the chatbot interface on your website. Connect the frontend to the webhook that triggers the When chat message received node. Configure Your OpenAI Key Insert your API key in the OpenAI Chat Model node. Adjust the model parameters for temperature, max tokens, etc., based on how formal or creative you want the bot to be. Customize Sub-Agents calendarAgent: Connect to your Google or Outlook calendar. RAGAgent: Link to a vector store or document database via API or native integration. ticketAgent: Set the destination email and format for ticket generation (e.g. via SendGrid or SMTP). Deploy in Production Host on n8n Cloud or your self-hosted instance. Monitor usage through the Executions tab and refine prompts based on user behavior. Benefits Modular system with dedicated logic per function Reduces token bloat by offloading complexity to sub-agents Easy to scale by adding more tools (e.g. CRM, analytics) Fast and responsive user experience for customers on your site Cleaner code structure and easier debugging

Who is this for? This template is designed for internal support teams, product specialists, and knowledge managers in technology companies who want to automate ingestion of product documentation and enable AI-driven, retrieval-augmented question answering. What problem is this workflow solving? Support agents often spend too much time manually searching through lengthy documentation, leading to inconsistent or delayed answers. This solution automates importing, chunking, and indexing product manuals, then uses retrieval-augmented generation (RAG) to answer user queries accurately and quickly with AI. What these workflows do Workflow 1: Document Ingestion & Indexing Manually triggered to import product documentation from Google Docs. Automatically splits large documents into chunks for efficient searching. Generates vector embeddings for each chunk using OpenAI embeddings. Inserts the embedded chunks and metadata into a MongoDB Atlas vector store, enabling fast semantic search. Workflow 2: AI-Powered Query & Response Listens for incoming user questions (can be extended to webhook). Converts questions to vector embeddings and performs similarity search on MongoDB vector store. Uses OpenAI’s GPT-4o-mini model with retrieval-augmented generation to produce direct, context-aware answers. Maintains short-term conversation context using a memory buffer node. Setup Setting up vector embeddings Authenticate Google Docs and connect your Google Docs URL containing the product documentation you want to index. Authenticate MongoDB Atlas and connect the collection where you want to store the vector embeddings. Create a search index on this collection to support vector similarity queries. Ensure the index name matches the one configured in n8n (data_index). See the example MongoDB search index template below for reference. Setting up chat Configure the AI system prompt in the “Knowledge Base Agent” node to reflect your company’s tone, answering style, and any business rules. Update the workflow description and instructions to help users understand the chat’s purpose and capabilities. Connect the MongoDB collection used for vector search in the chat workflow and update the vector search index if needed to match your setup. Make sure Both MongoDB nodes (in ingestion and chat workflows) are connected to the same collection, with: An embedding field storing vector data, Relevant metadata fields (e.g., document ID, source), and The same vector index name configured (e.g., data_index). Search Index Example: { "mappings": { "dynamic": false, "fields": { "_id": { "type": "string" }, "text": { "type": "string" }, "embedding": { "type": "knnVector", "dimensions": 1536, "similarity": "cosine" }, "source": { "type": "string" }, "doc_id": { "type": "string" } } } }

How it works Trigger: Listens for an incoming chat message Copy Assistant: Feeds the message (plus memory) into an OpenAI Chat Model and exposes two “tools” Cold Email Writer Tool Sales Letter Tool• Tool execution: Depending on the user’s intent, the appropriate tool generates the copy • Save output: Writes the generated email or sales letter into your target document via the Update a document node Set up steps • Configure your OpenAI Chat Model credentials in n8n (no hard-coded keys!) • Add and authenticate the Simple Memory credential (to keep context across messages) • Create Google Docs (or MS Word) credentials for the Update a document node • Ensure your Chat trigger is pointing at your incoming-message endpoint • Mandatory: Drop sticky-note annotations on each tool node explaining where to enter API keys and how to tweak prompts Once everything’s wired up, send a test chat message like “Write me a cold email for a fintech startup” and watch the workflow spin up a polished draft in your document. How to use Import the workflow JSON into n8n. Configure your Chat trigger (webhook or form) to receive incoming messages. Send a chat prompt like: “Write me a cold email for a B2B SaaS offering.” The “Copy Assistant” custom GPT picks the right tool (Cold Email or Sales Letter). Generated copy is written directly into your linked Google Doc or Word document. Requirements OpenAI API Key (with Chat Completions & Custom GPTs enabled) Custom Assistant created in your ChatGPT dashboard (Assistant ID pasted into the Chat Model node) n8n instance (Cloud or self-hosted) with credentials set up for: Simple Memory (to persist context) Google Docs or Microsoft Word (for document output) Customising this workflow Tweak system and user prompts inside the Copy Assistant node to fit your brand voice. Swap in Slack, Teams or email nodes instead of a document writer to deliver copy where you need it. Add or remove tools (e.g., “Follow-up Email Writer”) by duplicating the existing tool pattern. Use sticky-note annotations on every node to explain where to enter API keys, Assistant IDs, or prompt tweaks.