Workflow Templates

🚀 What the “Agent Builder” template does Need to turn a one-line chat request into a fully-wired n8n workflow template—complete with AI agents, RAG, and web-search super-powers—without lifting a finger? That’s exactly what Agent Builder automates: Listens to any incoming chat message (via the Chat Trigger). Spins up an AI architect that analyses the request, searches the web, reads n8n docs from a Pinecone vector store, and designs the smallest possible set of nodes. Auto-generates a ready-to-import JSON template and hands it back as a downloadable file—plus all the supporting assets (embeddings, vector store etc.) so the next prompt is even smarter. Think of it as your personal “workflow chef”: you shout the order, it shops for ingredients, cooks, plates, and serves the meal. All you do is eat. 🤗 Who will love this? No-code builders / power users** who don’t want to wrestle with AI node wiring. Agencies & consultants** delivering lots of bespoke automations. Internal platform teams** who need a “workflow self-service portal” for non-technical colleagues. 🧩 How it’s wired | Sub-process | What happens inside | Key nodes | | -------------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------ | -------------------------------------------------------------------------------------- | | Web Crawler (optional) | Firecrawl scrapes docs.n8n.io (or any URL you drop in) and streams raw markdown back. | Set URL → HTTP Request (Extract) → Wait & Retry | | RAG Trainer | Splits the scraped docs, embeds them with OpenAI, and upserts vectors into Pinecone. | Recursive Text Splitter → Embeddings OpenAI → Train Pinecone | | Agent Builder | The star of the show – orchestrates GPT-4o (via OpenRouter), SerpAPI web-search, your Pinecone index and a Structured Output Parser to produce → validate → prettify the final n8n template. | Chat Trigger → AI Agent → OpenAI (validator) → Code (extract) → Convert to JSON file | Every arrow in the drawn workflow is pre-connected, so the generated template always passes n8n’s import check. 🛠️ Getting set up (5 quick creds) | Service | Credential type | | --------------------------------------------------- | ---------------------------------------------------------- | | OpenAI / Azure OpenAI – embeddings & validation | OpenAI API | | Pinecone – vector store | Pinecone API | | OpenRouter – GPT-4o LLM | OpenRouter API Key | | SerpAPI – web search | SerpAPI Key | | Firecrawl (only if you plan to crawl) | Generic Header Auth → Authorization: Bearer YOUR_KEY | Each node already expects those creds; just create them once, select in the dropdown, hit Activate. 🏃‍♀️ What a typical run looks like User says: “Build me a workflow that monitors our support inbox, summarises new tickets with GPT and posts to Slack.” Chat Trigger captures the message. AI Agent: queries Pinecone for relevant n8n docs, fires a SerpAPI search for “n8n gmail trigger example”, sketches an architecture (Gmail Trigger → GPT Model → Slack). The agent returns JSON ➜ OpenAI node double-checks field names, connections, type versions. A tiny JS Code node slices the JSON out of the chat blob and saves it as template.json ready for download. You download, import, and… done. ✏️ Customising Switch the LLM* – plug in Claude 3, Gemini 1.5, or a local model; just swap the *OpenRouter Chat Model node. Point the RAG at your own docs* – change the crawl URL or feed PDFs via the *Default Data Loader. Hard-code preferred nodes* – edit the “User node preferences” in the system message so the agent always chooses *Notion for databases, etc. 🥡 Take-away notes It's a prototype feel free to experiment with it to improve its capabilities. Have fun building!**

This node is designed to cleanse URLs and extract their domain names efficiently. It effectively handles a wide range of URL formats, including those with unconventional or complex top-level domains (TLDs), such as 'co.uk'. You can also use it to extract the domain from an email. The node will also check if the domain is from a free email provider (gmail.com / outlook.com...etc) or not. How It Works The node analyzes the provided URL, removing any unnecessary elements. It then identifies and extracts the domain name, ensuring compatibility with a diverse array of TLDs. The node utilizes an extensive list of TLDs to guarantee accurate domain extraction for virtually any URL. To view the complete list of supported top-level domains, please visit: TLD List on GitHub How to use it Call this workflow using the "execute workflow" node You can pass either an email variable or a url variable. For email, the node also detect free mail provider such as Yahoo / Google...etc

Talk to Your Apps: Building a Personal Assistant MCP Server with Google Gemini Wouldn't it be cool to just tell your computer or phone to "schedule a meeting with Sarah next Tuesday at 3 PM" or "find John Doe's email address" and have it actually do it? That's the dream of a personal assistant! With n8n and the power of MCP and AI models like Google Gemini, you can actually build something pretty close to that. We've put together a workflow that shows you how you can use a natural language chat interface to interact with your other apps, like your CRM, email, and calendar. What You Need to Get Started Before you dive in, you'll need a few things: n8n:** An n8n instance (either cloud or self-hosted) to build and run your workflow. Google Gemini Access:** Access to the Google Gemini model via an API key. Credentials for Your Apps:** API keys or login details for the specific CRM, Email, and Calendar services you want to connect (like Google Sheets for CRM, Gmail, Google Calendar, etc., depending on your chosen nodes). A Chat Interface:** A way to send messages to n8n to trigger the workflow (e.g., via a chat app node or webhook). How it Works (In Simple Terms) Imagine this workflow is like a helpful assistant who sits between you and your computer. Step 1: You Talk, the AI Agent Listens It all starts when you send a message through your connected chat interface. Think of this as you speaking directly to your assistant. Step 2: The Assistant's Brain (Google Gemini) Your message goes straight to the assistant's "brain." In this case, the brain is powered by a smart AI model like Google Gemini. In our template we are using the latest Gemini 2.5 Pro. But this is totally up to you. Experiment and track which model fits the kind of tasks you will pass to the agent. Its job is to understand exactly what you're asking for. Are you asking to create something? Are you asking to find information? Are you asking to update something? The brain also uses a "memory" so it can remember what you've talked about recently, making the conversation feel more natural. We are using the default context window, which is the past 5 interactions. Step 3: The Assistant Decides What Tool to Use Once the brain understands your request, the assistant figures out the best way to help you. It looks at the request and thinks, "Okay, to do this, I need to use one of my tools." Step 4: The Assistant's Toolbox (MCP & Your Apps) Here's where the "MCP" part comes in. Think of "MCP" (Model Context Protocol) as the assistant's special toolbox. Inside this toolbox are connections to all the different apps and services you use – your CRM for contacts, your email service, and your calendar. The MCP system acts like a manager for these tools, making them available to the assistant whenever they're needed. Step 5: Using the Right Tool for the Job Based on what you asked for, the assistant picks the correct tool from the toolbox. If you asked to find a contact, it grabs the "Get Contact" node from the CRM section. If you wanted to schedule a meeting, it picks the "Create Event" node from the Calendar section. If you asked to draft an email, it uses the "Draft Email" node. Step 6: The Tool Takes Action Now, the node or set of nodes get to work! It performs the action you requested within the specific app. The CRM tool finds or adds the contact. The Email tool drafts the message. The Calendar tool creates the event. Step 7: Task Completed! And just like that, your request is handled automatically, all because you simply told your assistant what you wanted in plain language. Why This is Awesome This kind of workflow shows the power of combining AI with automation platforms like n8n. You can move beyond clicking buttons and filling out forms, and instead, interact with your digital life using natural conversation. n8n makes it possible to visually build these complex connections between your chat, the AI brain, and all your different apps. Taking it Further (Possible Enhancements) This is just the start! You could enhance this personal assistant by: Connecting more apps and services (task managers, project tools, etc.). Adding capabilities to search the web or internal documents. Implementing more sophisticated memory or context handling. Getting a notification when the AI agent is done completing each task such as in Slack or Microsoft Teams. Allowing the assistant to ask clarifying questions if needed. Building a robust prompt for the AI agent. Ready to Automate Your Workflow? Imagine the dozens of hours your team could save weekly by automating repetitive tasks through a simple, natural language interface. Need help? Feel free to contact us at 1 Node. Get instant access to a library of free resources we created.

This workflow allows users to convert a 2D image into a 3D model by integrating multiple AI and web services. The process begins with a user uploading or providing an image URL, which is then sent to a generative AI model capable of interpreting the content and generating a 3D representation in .glb format. The model is then stored and a download link is returned to the user. Main Steps Trigger Node: Initiates the workflow either via HTTP request, webhook, or manual execution. Image Upload or Input: The image is acquired via direct upload or URL input. API Integration: The image is sent to a 3D generation API (e.g., a service like Kaedim, Luma Labs, or a custom AI model). Model Generation: The external API processes the image and creates a 3D model. File Storage: The resulting 3D model is stored in cloud storage (e.g., S3, Google Drive, or a local server). Response to User: A download link for the 3D model is returned to the user via the same communication channel (HTTP response, email, or chat). Advantages Automation**: Eliminates the need for manual 3D modeling, saving time for artists, developers, and designers. AI-Powered**: Leverages AI to generate realistic and usable 3D models from simple 2D inputs. Scalability**: Can be triggered automatically and scaled up to handle many requests via n8n's automation. Integration-Friendly**: Easily extendable with other services like Discord, Telegram, or marketplaces for 3D assets. No-Code Configuration**: Built with n8n’s visual interface, making it editable without programming knowledge. How It Works Trigger: The workflow can be started manually ("When clicking ‘Test workflow’") or automatically at scheduled intervals ("Schedule Trigger"). Data Retrieval: The "Get new image" node fetches data from a Google Sheet, including the model image, product image, and product ID. 3D Image Creation: The "Create 3D Image" node sends the image data to the Fal.run API (Trellis) to generate a 3D model. Status Check: The workflow periodically checks the request status ("Get status" and "Wait 60 sec.") until the job is marked as "COMPLETED." Result Processing: Once completed, the 3D model URL is retrieved ("Get Url 3D image"), the file is downloaded ("Get File 3D image"), and uploaded to Google Drive ("Upload 3D Image"). Sheet Update: The final 3D model URL is written back to the Google Sheet ("Update result"). Set Up Steps Prepare Google Sheet: Create a Google Sheet with columns: IMAGE MODEL and 3D RESULT (empty). Example sheet: Google Sheet Template. Obtain Fal.run API Key: Sign up at Fal.ai and get an API key. Configure the Authorization header in the "Create 3D Image" node with Key YOURAPIKEY. Configure Workflow Execution: Run manually via the Test workflow button. For automation, set up the Schedule Trigger node (e.g., every 5 minutes). Verify Credentials: Ensure Google Sheets, Google Drive, and Fal.run API credentials are correctly set in n8n. Once configured, the workflow processes new entries in the Google Sheet, generates 3D models, and updates the results automatically. Need help customizing? Contact me for consulting and support or add me on Linkedin.

🧾 Personal Invoice Processor This N8N workflow automates the extraction and organization of personal invoices in Colombia received via Gmail. It includes the following key steps: 🔁 Flow Summary Email Trigger Polls Gmail every 30 minutes for emails with .zip attachments (assumed to contain invoices). Expects ZIP file following DIAN standards. ZIP File Handling Extracts all files. Filters only PDF and XML files for processing. Data Extraction & Processing Uses LangChain Agent + OpenAI (GPT-4o-mini) to extract: Tipo de documento (Factura / Nota Crédito) Número de factura Fecha de emisión (YYYY-MM-DD) NIT emisor y receptor (sin dígito de verificación) Razón social del emisor Subtotal, IVA, Total CUFE Resumen de compra (max 20 words, formatted sentence) Validation Ensures Total = Subtotal + IVA using a calculator node. Storage Uploads the original PDF to Google Drive. Renames the file to: YYYY-MM-DD-NUMERO_FACTURA.pdf. Inserts or updates invoice details in Google Sheets using a unique Key (NIT_Emisor + Numero_Factura) to prevent duplication. > ⚙️ Designed for personal use with minimal latency tolerance and high automation reliability.

Telegram Rich Output Helper Workflow Who is this for? Builders of Telegram chat‑bots, AI assistants, or notification services who already run n8n and need to convert long, mixed‑media answers from an LLM (or any upstream source) into Telegram‑friendly messages. Prerequisites A Telegram bot created with @BotFather. The bot’s HTTP API token saved as a Telegram API credential in n8n. n8n ≥ 1.0 with the built‑in Telegram node still installed. A parent workflow that calls this one via Execute Workflow and passes: chatId — the destination chat ID (integer). output — a string that can contain plain text and HTTP links to images, audio, or video. What the workflow does Extract Links – A JavaScript Code node scans output, deduplicates URLs, and classifies each by file extension. Link Path If no media links exist, the text path is used. Otherwise, each link is routed through a Switch node that triggers the correct Telegram call (sendPhoto, sendAudio, sendVideo) so users get inline previews or players. Text Path An IF node checks whether the remaining text exceeds Telegram’s 1 000‑character limit. When it does, a Code node slices the text at line boundaries; SplitInBatches then sends the chunks sequentially so nothing is lost. All branches converge, keeping the whole exchange inside one execution. Customisation tips Adjust the character limit** – edit the first expression in “If text too long”. Filter/enrich links** – extend the regex or add MIME checks before dispatch. Captions & keyboards** – populate additionalFields in the three “Send back” nodes. Throughput vs. order* – tweak the batch size in both *SplitInBatches** nodes. With this template in place, your users receive the complete message, playable media, and zero manual formatting – all within Telegram’s API limits.

This n8n workflow enables you to export data from Zammad, including Users, Roles, Groups, and Organizations, into individual Excel files. It simplifies data handling and reporting by creating structured outputs for further processing or sharing. Features Export Users with associated details such as email, firstname, lastname, role_ids, and group_ids. Export Roles and Organizations with their respective identifiers and names. Convert all data into separate Excel files for easy access and use. Usage Import this workflow into your n8n instance. Configure the required Zammad API credentials (zammad_base_url and zammad_api_key) in the Basic Variables node. Run the workflow to generate Excel files containing Zammad data. Issues and Suggestions If you encounter any issues or have suggestions for improvement, please report them on the GitHub repository. We appreciate your feedback to help enhance this workflow!

What problem is this workflow solving? This workflow is aimed for email marketing enthusiasts looking for an easy way to either extract the domain from an email ad also check if the syntax is correct without having to use the code node. How this works For this to work, replace the debugger node with your actual data source. Map your data at match the above layout Run your workflow and check for all the emails that are either valid or not Once done, you will have a list of all your emails, domains, and whether they are valid or not.

This workflow allows you to receive a Mattermost message when meeting notes get added to the Notion. Prerequisites Create a table in Notion similar to this: Meeting Notes Follow the steps mentioned in the documentation, to create credentials for the Notion Trigger node. Create create credentials for Mattermost. Notion Trigger: The Notion Trigger node will trigger the workflow when new data gets added to Notion. IF node: This node will check if the notes belong to the team Marketing. If the team is Marketing the node will true, otherwise false. Mattermost node: This node will send a message about the new data in the channel 'Marketing' in Mattermost. If you have a different channel, use that instead. You can even replace the Mattermost node with nodes of other messaging platforms, like Slack, Telegram, Discord, etc. NoOp node: Adding this node here is optional, as the absence of this node won't make a difference to the functioning of the workflow.

LLM/RAG Kaggle Development Assistant An on-premises, domain-specific AI assistant for Kaggle (tested on binary disaster-tweet classification), combining LLM, an n8n workflow engine, and Qdrant-backed Retrieval-Augmented Generation (RAG). Deploy via containerized starter kit. Needs high end GPU support or patience. Initial chat should contain guidelines on what to to produce and the challenge guidelines. Features Coding Assistance** • "Real"-time Python code recommendations, debugging help, and data-science best practices • Multi-turn conversational context Workflow Automation** • n8n orchestration for LLM calls, document ingestion, and external API integrations Retrieval-Augmented Generation (RAG)** • Qdrant vector-database for competition-specific document lookup • On-demand retrieval of Kaggle competition guidelines, tutorials, and notebooks after convertion to HTML and ingestion into RAG entirly On-Premises for Privacy** • Locally hosted LLM (via Ollama) – no external code or data transfer ALIENTELLIGENCE/contentsummarizer:latest for summarizing qwen3:8b for chat and coding mxbai-embed-large:latest for embedding • GPU acceleration required Based on: https://n8n.io/workflows/2339 breakdown documents into study notes using templating mistralai and qdrant/

This workflow will take all emails you put into a certain folder, upload any attachements to Nextcloud, and mark the emails as read (configurable). Attachements will be saved with automatically generated filenames: 2021-01-01_From-Sender-Name_Filename-of-attachement.pdf Instructions: Allow lodash to be used in n8n (or rewrite the code...) NODE_FUNCTION_ALLOW_EXTERNAL=lodash (environment variable) Import workflow Set credentials for Email & Nextcloud nodes Configure to use correct folder / custom filters Activate Custom filter examples: Only unread emails: Custom Email Config = ["UNSEEN"] Filter emails by 'to' address: Custom Email Config = [["TO", "example+invoices@posteo.de"]]

What This Workflow Does This workflow automates the candidate nurturing process, solving the common problem of candidates losing interest or "ghosting" after an application. It keeps them engaged and informed by sending a personalized, multi-channel (WhatsApp & Gmail) sequence of follow-up messages over their first week. The automation triggers when a new candidate is added to your ATS (e.g., via a Recrutei webhook). It then uses AI to generate a custom 3-part message (for Day 1, Day 3, and Day 7) tailored to the candidate's age and the specific job they applied for, ensuring a professional and empathetic experience that strengthens your employer brand. How it Works Trigger: A Webhook node captures the new candidate data from your Applicant Tracking System (ATS) or form. Data Preparation: Two Code nodes clean the incoming data. The first (Separating information) extracts key fields and formats the phone number. The second (Extract age) calculates the candidate's age from their birthday to be used by the AI. AI Content Generation: The workflow sends the candidate's details (name, age, job title) to an AI model (AI Recruitment Assistant). The AI has a detailed system prompt to generate three distinct messages for Day 1 (Thank You), Day 3 (Friendly Reminder), and Day 7 (Final Reinforcement), adapting its tone based on the candidate's age. Split Messages: A Code node (Separating messages per days) receives the single text block from the AI and splits it into three separate variables (day1, day3, day7). Day 1 Send: The workflow immediately sends the day1 message via both Gmail and WhatsApp (configured for Evolution API). Day 3 Send: A "Wait" node pauses the workflow for 2 days, after which it sends the day3 message. Day 7 Send: Another "Wait" node pauses for 4 more days, then sends the final day7 message, completing the 7-day nurturing sequence. Setup Instructions This workflow is plug-and-play once you configure the following 5 steps: Webhook Node: Copy the Test URL from the Webhook node and configure it in your ATS (e.g., Recrutei) or form builder to trigger whenever a new candidate is added. Run one test submission to make the data structure visible to n8n. AI Credentials: In the AI Recruitment Assistant node, select or create your OpenAI API credential. MCP Credential (Optional): If you use a Recrutei MCP, paste your endpoint URL into the MCP Recrutei node. Gmail Credentials: In all three Message Gmail nodes (Day 1, 3, 7), select or create your Gmail (OAuth2) credential. Optional: In the same nodes, go to Options and change the Sender Name from your_company to your actual company name. WhatsApp (Evolution API): This template is pre-configured for the Evolution API. In all three Message WhatsApp nodes (Day 1, 3, 7), you must: URL: Replace {server-url} and {instance} with your Evolution API details. Headers: In the "Header Parameters" section, replace your_api_key with your actual Evolution API key.