Workflow Templates

This workflow provides a robust solution for automatically backing up all your n8n workflows to a designated GitHub repository on a daily basis. By leveraging the n8n API and GitHub API, it ensures your workflows are version-controlled and securely stored, safeguarding against data loss and facilitating disaster recovery. How it works The automation follows these key steps: Scheduled trigger: The workflow is initiated automatically every day at a pre-configured time. List existing backups: It first connects to your GitHub repository to retrieve a list of already backed-up workflow files. This helps in determining whether a workflow's backup file needs to be created or updated. Retrieve n8n workflows: The workflow then fetches all current workflows directly from your n8n instance using the n8n REST API. Process and prepare: Each retrieved workflow is individually processed. Its data is converted into JSON format. This JSON content is then encoded to base64, a format suitable for GitHub API file operations. Commit to GitHub: For each n8n workflow: A standardized filename is generated (e.g., workflow-name-tag.json). The workflow checks if a file with this name already exists in the GitHub repository (based on the list fetched in step 2). If the file exists: It updates the existing file with the latest version of the workflow. If it's a new workflow (file doesn't exist): A new file is created in the repository. Each commit is timestamped for clarity. This process ensures that you always have an up-to-date version of all your n8n workflows stored securely in your GitHub version control system, providing peace of mind and a reliable backup history. Pre-requisites Before you can use this template, please ensure you have the following: An active n8n instance (self-hosted or cloud). A GitHub account. A GitHub repository created where you want to store the workflow backups. A GitHub Personal Access Token with repo scope (or fine-grained token with read/write access to the specific backup repository). This token will be used for GitHub API authentication. n8n API credentials (API key) for your n8n instance. Set up steps Setting up this workflow should take approximately 10-15 minutes if you have your credentials ready. Import the template: Import this workflow into your n8n instance. Configure n8n API credentials: Locate the "Retrieve workflows" node. In the "Credentials" section for "n8n API", create new credentials (or select existing ones). Enter your n8n instance URL and your n8n API Key (you can create your n8n api key in the settings of your n8n instance) Configure GitHub credentials: Locate the "List files from repo" node (and subsequently "Update file" / "Upload file" nodes which will use the same credential). In the "Credentials" section for "GitHub API", create new credentials. Select OAuth2/Personal Access Token authentication method. Enter the GitHub Personal Access Token you generated as per the pre-requisites. Specify repository details: In the "List files from repo", "Update file", and "Upload file" GitHub nodes: Set the Owner: Your GitHub username or organization name. Set the Repository: The name of your GitHub repository dedicated to backups. Set the Branch (e.g., main or master) where backups should be stored. (Optional) Specify a Path within the repository if you want backups in a specific folder (e.g., n8n_backups/). Leave blank to store in the root. Adjust schedule (Optional): Select the "Schedule Trigger" node. Modify the trigger interval (e.g., change the time of day or frequency) as needed. By default, it's set for a daily run. Activate the workflow: Save and activate the workflow. Explanation of nodes Here's a detailed breakdown of each node used in this workflow: Schedule trigger** Type: n8n-nodes-base.scheduleTrigger Purpose: This node automatically starts the workflow based on a defined schedule (e.g., daily at midnight). List files from repo** Type: n8n-nodes-base.github Purpose: Connects to your specified GitHub repository and lists all files, primarily to check for existing workflow backups. Aggregate** Type: n8n-nodes-base.aggregate Purpose: Consolidates the list of file names obtained from the "List files from repo" node into a single item for easier lookup later in the "Check if file exists" node. Retrieve workflows** Type: n8n-nodes-base.n8n Purpose: Uses the n8n API to fetch a list of all workflows currently present in your n8n instance. Json file** Type: n8n-nodes-base.convertToFile Purpose: Takes the data of each workflow (retrieved by the "Retrieve workflows" node) and converts it into a structured JSON file format. To base64** Type: n8n-nodes-base.extractFromFile Purpose: Converts the binary content of the JSON file (from the "Json file" node) into a base64 encoded string. This encoding is required by the GitHub API for file content. Commit date & file name** Type: n8n-nodes-base.set Purpose: Prepares metadata for the GitHub commit. It generates: commitDate: The current date and time for the commit message. fileName: A standardized file name for the workflow backup (e.g., my-workflow-vps-backups.json), typically using the workflow's name and its first tag. Check if file exists** Type: n8n-nodes-base.if Purpose: A conditional node. It checks if the fileName (generated by "Commit date & file name") is present in the list of files aggregated by the "Aggregate" node. This determines if the workflow backup already exists in GitHub. Update file** Type: n8n-nodes-base.github Purpose: If the "Check if file exists" node determines the file does exist, this node updates that existing file in your GitHub repository with the latest workflow content (base64 encoded) and a commit message. Upload file** Type: n8n-nodes-base.github Purpose: If the "Check if file exists" node determines the file does not exist, this node creates and uploads a new file to your GitHub repository with the workflow content and a commit message. Customization Here are a few ways you can customize this template to better fit your needs: Backup path**: In the GitHub nodes ("List files from repo", "Update file", "Upload file"), you can specify a Path parameter to store backups in a specific folder within your repository (e.g., workflows/ or daily_backups/). Filename convention**: Modify the "Commit date & file name" node (specifically the expression for fileName) to change how backup files are named. For example, you might want to include the workflow ID or a different date format. Commit messages**: Customize the commit messages in the "Update file" and "Upload file" GitHub nodes to include more specific information if needed. Error handling**: Consider adding error handling branches (e.g., using the "Error Trigger" node or checking for node execution failures) to notify you if a backup fails for any reason. Filtering workflows**: If you only want to back up specific workflows (e.g., those with a particular tag or name pattern), you can add a "Filter" node after "Retrieve workflows" to include only the desired workflows in the backup process. Backup frequency**: Adjust the "Schedule Trigger" node to change how often the backup runs (e.g., hourly, weekly, or on specific days). Template was created in n8n v1.92.2

Define Your ICP from Customer LinkedIn Profiles Use Case This automation helps marketing and sales teams define their Ideal Customer Profile (ICP) using real LinkedIn profiles of current high-fit customers. By enriching and analyzing profile data, it generates a clear ICP definition and scoring methodology for future targeting. What This Automation Does This automation analyzes LinkedIn profiles of your existing customers and produces: A structured ICP definition A scoring model to evaluate future prospects A Google Boolean search string to find similar prospects Input: LinkedIn profile URLs of existing high-fit customers (e.g., https://www.linkedin.com/in/amirashkenazi/) Output: A Google Doc containing the ICP analysis and scoring methodology How It Works Trigger: Waits for a chat message containing one or more LinkedIn profile URLs. AI Agent: Parses and processes the URLs. Airtop Data Enrichment: Uses Airtop to extract structured information from each LinkedIn profile (e.g., job title, company, experience, skills). Memory: Maintains state between inputs for consistent analysis. LLM Analysis: Uses Claude 3.7 Sonnet to synthesize enriched data into a meaningful ICP. Google Docs: Automatically creates a new doc with a timestamped title and appends the ICP definition. Setup Requirements Airtop Profile connected to LinkedIn, Insert the profile name in the Airtop Tool Airtop API credentials. Get it free here If you choose to activate saving the profiles in Google Docs you will need OAuth2 credentials (or just copy the ICP definition from the chat) Next Steps Use the ICP for Scoring**: Feed new LinkedIn profiles through the same Airtop enrichment and use the scoring function to evaluate fit. Automate Target Discovery**: Plug the Boolean search output into LinkedIn, Google, or People Data Labs for ICP-matching lead generation. Refine Continuously**: Repeat the workflow as your customer base grows or segments evolve. Read more about how to Define ICP from Customer Examples

Scoring LinkedIn Profiles Against Your ICP Use Case This automation scores individual LinkedIn profiles against your Ideal Customer Profile (ICP) based on interest in AI, technical depth, and seniority level. It's ideal for prioritizing leads and understanding how well a person fits your ICP criteria. What This Automation Does Given a LinkedIn profile and an Airtop profile, it: Extracts relevant data from the person's profile Determines levels of AI interest, seniority, and technical depth Calculates an ICP score based on weighted criteria Returns the full enriched profile with the score Input parameters: LinkedIn Profile URL** (e.g., https://linkedin.com/in/janedoe) Airtop Profile** connected to LinkedIn ICP scoring method** in the Airtop node prompt Output fields in JSON format: Full name, job title, employer, company LinkedIn URL, location, number of connections and followers, about section content and more Calculated ICP Score (out of 100) How It Works Form Trigger or Workflow Trigger: Accepts input from either a form or another workflow. Parameter Assignment: Ensures proper variable names for downstream nodes. Airtop Enrichment Tool: Extracts and scores the person based on a detailed prompt. Scoring: Uses this point system: AI Interest: beginner (5), intermediate (10), advanced (25), expert (35) Technical Depth: basic (5), intermediate (15), advanced (25), expert (35) Seniority Level: junior (5), mid-level (15), senior (25), executive (30) Output Formatting: Cleans and returns the result as JSON. Setup Requirements IMPORTANT: Enter your ICP scoring method in the prompt field of the Airtop node Airtop Profile connected to LinkedIn. Airtop API credentials configured in n8n. Optional: a front-end form to collect profile URLs and trigger the automation. Next Steps Embed in CRM**: Trigger this automation on new leads to auto-score them. Batch Process Leads**: Run it over a list of profile URLs for segmentation. Customize Scoring**: Adjust point weights based on your sales priorities. Read more about Scoring LinkedIn Profiles Against Your ICP

Monitor X for Relevant Posts Use Case This automation monitors X (formerly Twitter) search pages in real time and extracts high-signal posts that match your categories of interest. It’s ideal for community engagement, lead discovery, thought leadership tracking, or competitive analysis. What This Automation Does Given a search URL and a list of categories, it: Logs into X using Airtop Opens the specified search URL Scrolls through the results Extracts up to 10 valid, English-language posts Filters and classifies each post by category (or marks as [NA] if unrelated) Returns the structured results as JSON Input parameters: airtop_profile** — An Airtop browser profile authenticated on X x_url** — X search URL (e.g., https://x.com/search?q=ai agents&f=live) relevant_categories** — Text-based list of categories to classify posts (e.g., "Web automation use cases", "Thought leadership") Output: A JSON array of posts, each with: writer time text url category How It Works Trigger: This workflow is triggered by another workflow (e.g., a community engagement pipeline). Input Setup: Accepts the Airtop profile, search URL, and categories to use for classification. Session: Starts a browser session using the Airtop profile. Window Navigation: Opens the provided X search URL. Extraction: Scrapes up to 10 posts with /status/ in the URL and text in English. Classification: Each post is labeled with a category if relevant, or [NA] otherwise. Filtering: Discards [NA] posts. Output: Returns the list of classified posts. Setup Requirements Airtop profile with an active X login. Airtop API key connected in n8n. List of category definitions to guide post classification (used in prompt). Next Steps Feed into Engagement Workflows**: Pass the results to workflows that reply, retweet, or track posts. Use in Slack Alerts**: Push classified posts into Slack channels for review and reaction. Customize Classifier**: Refine the categorization logic to include sentiment or company mentions. Read more about Monitoring X for Relevant Posts

Do you consistently forget to set a Default Error Workflow when creating new workflows? Then this helper workflow is for you! When activated, this helper workflow will: Scan ALL other workflows every 4 hours Make sure ALL workflows have a default error workflow set (based on what Workflow ID you provide) This helper will SKIP OVER any workflows that have the default_error:false tag set (make sure your default error workflow has the default_error:false tag set, so that you don't end up with recursive loops during errors) Setup Nodes: Once imported, edit the Set Vars node with your default_error_workflow_id value. If you want to change the default_error:false tag to some other tag name, you can do so here as well. You need to update the Set Default Error Workflow node with your PostgreSQL credentials to access the n8n database.

📥 Gmail Attachment Backup to Google Drive — n8n Workflow This n8n workflow automatically backs up email attachments from a specific sender in Gmail to a designated folder in Google Drive. It polls Gmail every minute and uploads any new attachments from matching emails to the specified Google Drive folder with a timestamped filename. 📌 Use Case Primary Purpose: Automatically archive and back up attachments from a specific sender (e.g., test@gmail.com) to Google Drive for safekeeping, audit, or processing. Ideal For: Automating invoice/receipt collection from a vendor Archiving reports from a monitored email address Creating a searchable historical log of attachments for compliance 🧭 Workflow Overview Here’s how the workflow operates: 🔔 Gmail Trigger Polls Gmail every minute for new messages from a specific sender (test@gmail.com). 📩 Gmail Get Message Retrieves the full contents (including attachments) of the matched email. 🧠 Code (JS) Iterates over all binary attachments in the email and restructures them as individual binary items to upload separately. 📤 Google Drive Uploads each attachment to a target Google Drive folder (DOcs) with a timestamp and unique name. 📍 Replace Me (NoOp) Placeholder node to indicate workflow completion. You can replace this with Slack notifications, logs, or alerts. 🔧 How to Use Prerequisites An n8n instance (self-hosted or cloud) A connected Gmail account with OAuth2 credentials A connected Google Drive account with OAuth2 credentials Permissions for n8n to access your Gmail and Google Drive Setup Instructions Import the Workflow Copy and paste the workflow JSON into your n8n editor. Set Up Credentials Ensure the following credentials exist and are authorized: `Gmail (for Gmail nodes) `Google Drive (for Google Drive node) Configure the Folder Update the folderId in the Google Drive node if you want to use a different target folder. Activate the Workflow Enable the workflow in n8n. It will start polling Gmail every minute. ✏️ How to Customize | Task | How to Customize | |------|------------------| | Change sender filter | Modify the sender field in the Gmail Trigger node | | Adjust polling frequency | Change the pollTimes configuration in the trigger node | | Change destination folder | Update folderId in the Google Drive node | | Modify filename format | Edit the name expression in the Google Drive node | | Add post-upload logic | Replace or extend the Replace Me node with notifications, logs, etc. | | Process only specific attachments | Add logic in the Code node to filter by filename or MIME type | 📂 Filename Format Example [MessageID]_[Timestamp]_backup_attachment This naming convention ensures uniqueness and traceability back to the original message. ✅ Future Improvements Email subject filtering** to narrow down the match Slack/Email notifications** after upload Deduplication check** to avoid reuploading the same files Virus scan or file validation** before upload 💬 Support For any issues using this workflow: Double-check your credential permissions Review n8n logs for Gmail or Google Drive errors Visit the n8n community forums

🧑‍💼 Who is this for? This workflow is for anyone who receives too many emails and wants to stay informed without drowning in their inbox. If you're constantly checking your Gmail and wish you had someone summarizing messages and sending just the important parts to your phone, this is for you. Especially useful for solopreneurs, customer support, busy professionals, or newsletter addicts. 🧠 What problem is this workflow solving? Email is powerful, but also overwhelming. Important info gets buried in threads, and staying on top of things can mean hours wasted scanning messages. This workflow turns that chaos into clarity: as soon as a new email arrives, you get a concise AI-generated summary in Telegram — straight to your pocket. No more checking Gmail constantly. No more missing key updates. Just a clean, human-style summary, written in the language you choose. ⚙️ What this workflow does Watches your Gmail inbox for new messages Prepares the content, including sender, subject, and message body Sends it to OpenAI to generate a friendly, casual summary Delivers that summary to your Telegram chat All in seconds, completely automated. 🛠️ Setup Connect your accounts: Gmail, Telegram, and OpenAI credentials must be added to the respective nodes. Set your Telegram chat ID: Use a bot like @userinfobot to get it. Customize the language in the Set summary language node (default is English). Activate the workflow — and watch it go. 🧩 How to customize this workflow to your needs You can make this workflow your own in a few easy ways: Summarize only some emails**: Add a Filter node after the Gmail trigger (e.g., only messages from certain senders). Change the tone or detail of summaries**: Tweak the system prompt in the Summary generation agent. Use a different model**: Swap OpenAI’s GPT-4o for another provider like Claude or DeepSeek. Translate to your preferred language**: Just change "english" to "español", "français", etc.

Automating LinkedIn Company Data Extraction Use Case This automation extracts detailed company insights from a LinkedIn company page, including identity, scale, classification, and funding data. Ideal for investors, sales teams, and market researchers. What This Automation Does This automation accepts the following inputs: Company's LinkedIn URL**: The public LinkedIn page URL of the company. Airtop Profile (connected to LinkedIn)**: Your Airtop Profile authenticated on LinkedIn. It then extracts and returns structured data with: 1. Company Identity Full name Tagline Headquarters location (city, state, country) About section Website 2. Company Scale Current employee count Employee size bracket: [0-9], [10-150], [150+] 3. Business Classification Is the company an automation agency? (true/false) AI implementation level: Low / Medium / High Technical sophistication: Basic / Intermediate / Advanced / Expert 4. Funding Profile Most recent funding round Total amount raised Key investors Last funding update date How It Works Creates an Airtop session using the provided profile. Navigates to the company LinkedIn page. Executes an Airtop query to extract data. Outputs the result in a standardized JSON schema. Setup Requirements Airtop API Key A LinkedIn-authenticated Airtop Profile Next Steps Feed into CRM**: Enrich your accounts with detailed LinkedIn data. Prioritize Leads**: Use classification and funding data to prioritize outreach. Combine with People Data**: Integrate with individual-level enrichment for full context. Read more about how to extract company data from Linkedin with Airtop and n8n

When you collect leads from a form, you need to format the incoming data such as the lead's name and also apply a basic validation of the email entered. Lucky for us, N8N offers all of these features with simple expressions that can easily be applied to data. This workflow aims to show how you can process your lead data before saving it in Mautic. How it Works This workflow receives data from a Wordpress form; applies name formatting and basic validation to the email; Creates the contact in Mautic; If e-mail is invalid, add the lead in Dot Not Contact list. Setup Steps Set up credentials when you first open the workflow. You'll need a Mautic account. You need to configure a form in Wordpress (Elementor, WPForms, etc.) and send it to the N8N Webhook address; Now map the fields you need to apply formatting and validation. After testing your workflow, swap the Test URL to Production URL in Discourse and activate your workflow

✉️ Telegram Email Agent with GPT + Gmail Category: Messaging / AI Agent Level: Beginner-Friendly Tags: Telegram, Email Automation, AI Agent, Gmail, GPT Model Watch Step-by-step video guide here: https://www.youtube.com/watch?v=nyI40s9QOuw&t=420s&pp=0gcJCb4JAYcqIYzv 🤖 What This Workflow Does This workflow turns your Telegram bot into a personal email assistant powered by AI. With just a message on Telegram, users can: Send an email via Gmail Automatically generate the email content using OpenAI Models. Get confirmation or responses directly in Telegram It's like ChatGPT meets Gmail, inside your Telegram chat. 🔧 How It Works Telegram Trigger – Listens for incoming messages from your bot. AI Agent – Processes the input using OpenAI Model and converts it into structured email content (To, Subject, Body). Memory Node – Stores short-term context per user (via chat ID), so the agent can hold simple conversations. Gmail Node – Sends the generated email using your Gmail account. Telegram Node – Replies to the user confirming the output or status. 🧠 Why This is Useful Ever wanted to send an email while on the go, without typing the whole thing out in Gmail? This is a fast, intuitive, and AI-powered way to: Dictate or draft emails from anywhere Create an AI-powered virtual assistant via Telegram Integrate n8n's Langchain Agent with real-world productivity use cases 🪜 Setup Instructions Connect your Telegram bot via BotFather and add the credentials in n8n. Set up your OpenAI API key (GPT-4o-mini recommended). Add your Gmail OAuth credentials. Activate the workflow and start messaging your bot!

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" } } } }

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