Agents & Automations

I built a fully automated AI Social Media System that analyzes an article and creates: • Text posts for Twitter and Threads • Text and image posts for LinkedIn, Facebook, and Instagram • AI avatar video posts for TikTok This system uses AI to automate content creation and posting across platforms: 🔥 Monitors Google Sheets for new articles 🔥 Writes AI social media posts 🔥 Generates AI images 🔥 Generates AI avatar clone videos 🔥 Publishes to social media using API I included multiple different types of content generated (text, image, video), so that you can easily customize this AI system to fit your needs.

Each time you add a new product to your Shopify store, Make will seamlessly utilize Picsart to remove the background from the primary image, replacing it with a crisp white backdrop. Following this, the product listing is instantly updated with the enhanced image. This template was created by Picsart and not tested by Make. For any inquiries about the template, please reach out to the template creator: [email protected].

Easily transcribe audio files stored on Google Drive with OpenAI Whisper. Automate transcription, store on a Google Doc, and instantly email the doc for ease of communication. Please note that the Whisper API file limit is 25mb. We have used CloudConvert to convert these files to smaller mp3 files for Whisper to transcribe.

n8n Workflow: Automate SIEM Alert Enrichment with MITRE ATT&CK & Qdrant Who is this for? This workflow is ideal for: - Cybersecurity teams & SOC analysts who want to automate SIEM alert enrichment. - IT security professionals looking to integrate MITRE ATT&CK intelligence into their ticketing system. - Organizations using Zendesk for security incidents who need enhanced contextual threat data. - Anyone using n8n and Qdrant to build AI-powered security workflows. What problem does this workflow solve? Security teams receive large volumes of raw SIEM alerts that lack actionable context. Investigating every alert manually is time-consuming and can lead to delayed response times. This workflow solves this problem by: ✔ Automatically enriching SIEM alerts with MITRE ATT&CK TTPs. ✔ Tagging & classifying alerts based on known attack techniques. ✔ Providing remediation steps to guide the response team. ✔ Enhancing security tickets in Zendesk with relevant threat intelligence. What this workflow does 1️⃣ Ingests SIEM alerts (via chatbot or ticketing system like Zendesk). 2️⃣ Queries a Qdrant vector store containing MITRE ATT&CK techniques. 3️⃣ Extracts relevant TTPs (Tactics, Techniques, & Procedures) from the alert. 4️⃣ Generates remediation steps using AI-powered enrichment. 5️⃣ Updates Zendesk tickets with threat intelligence & recommended actions. 6️⃣ Provides structured alert data for further automation or reporting. Setup GuidePrerequisites - n8n instance (Cloud or Self-hosted). - Qdrant vector store with MITRE ATT&CK data embedded. - OpenAI API key (for AI-based threat processing). - Zendesk account (for ticket enrichment, if applicable). Clean Mitre Data Python Script - Cleaned Mitre Data - Full Mitre Data Steps to Set Up 1️⃣ Embed MITRE ATT&CK data into Qdrant. This workflow pulls MITRE ATT&CK data from Google Drive and loads it into Qdrant. The data is vectorized using OpenAI embeddings for fast retrieval. 2️⃣ Deploy the n8n Chatbot. The chatbot listens for SIEM alerts and sends them to the AI processing pipeline. Alerts are analyzed using an AI agent trained on MITRE ATT&CK. 3️⃣ Enrich Zendesk Tickets. The workflow extracts MITRE ATT&CK techniques from alerts. It updates Zendesk tickets with contextual threat intelligence. The remediation steps are included as internal notes for SOC teams. How to Customize This Workflow 🔧 Modify the chatbot trigger: Adapt the chatbot node to receive alerts from Slack, Microsoft Teams, or any other tool. 🔧 Change the SIEM input source: Connect your workflow to Splunk, Elastic SIEM, or Chronicle Security. 🔧 Customize remediation steps: Use a custom AI model to tailor remediation responses based on organization-specific security policies. 🔧 Extend ticketing integration: Modify the Zendesk node to also work with Jira, ServiceNow, or another ITSM platform. Why This Workflow is Powerful ✅ Saves time: Automates alert triage & classification. ✅ Improves security posture: Helps SOC teams act faster on threats. ✅ Leverages AI & vector search: Uses LLM-powered enrichment for real-time context. ✅ Works across platforms: Supports n8n Cloud, Self-hosted, and Qdrant. 🚀 Get Started Now! 📖 Watch the Setup Video 💬 Have Questions? Join the Discussion in the YouTube Comments!

Video Guide I prepared a detailed guide explaining how to build an AI-powered meeting assistant that provides real-time transcription and insights during virtual meetings. Who is this for? This workflow is ideal for business professionals, project managers, and team leaders who require effective transcription of meetings for improved documentation and note-taking. It's particularly beneficial for those who conduct frequent virtual meetings across various platforms like Zoom and Google Meet. What problem does this workflow solve? Transcribing meetings manually can be tedious and prone to error. This workflow automates the transcription process in real-time, ensuring that key discussions and decisions are accurately captured and easily accessible for later review, thus enhancing productivity and clarity in communications. What this workflow does The workflow employs an AI-powered assistant to join virtual meetings and capture discussions through real-time transcription. Key functionalities include: - Automatic joining of meetings on platforms like Zoom, Google Meet, and others with the ability to provide real-time transcription. - Integration with transcription APIs (e.g., AssemblyAI) to deliver seamless and accurate capture of dialogue. - Structuring and storing transcriptions efficiently in a database for easy retrieval and analysis. - Real-Time Transcription: The assistant captures audio during meetings and transcribes it in real-time, allowing participants to focus on discussions. - Keyword Recognition: Key phrases can trigger specific actions, such as noting important points or making prompts to the assistant. - Structured Data Management: The assistant maintains a database of transcriptions linked to meeting details for organized storage and quick access later. SetupPreparation 1. Create Recall.ai API key 2. Setup Supabase account and table - create table sql public.data ( id uuid not null default gen_random_uuid (), date_created timestamp with time zone not null default (now() at time zone 'utc'::text), input jsonb null, output jsonb null, constraint data_pkey primary key (id), ) tablespace pg_default; 3. Create OpenAI API key Development - Bot Creation: Use a node to create the bot that will join meetings. Provide the meeting URL and set transcription options within the API request. - Authentication: Configure authentication settings via a Bearer token for interacting with your transcription service. - Webhook Setup: Create a webhook to receive real-time transcription updates, ensuring timely data capture during meetings. - Join Meeting: Set the bot to join the specified meeting and actively listen to capture conversations. - Transcription Handling: Combine transcription fragments into cohesive sentences and manage dialog arrays for coherence. - Trigger Actions on Keywords: Set up keyword recognition that can initiate requests to the OpenAI API for additional interactions based on captured dialogue. - Output and Summary Generation: Produce insights and summary notes from the transcriptions that can be stored back into the database for future reference.

Voiceflow is a no-code platform that allows you to design, prototype, and deploy conversational assistants across multiple channels—such as chat, voice, and phone—with advanced logic and natural language understanding. It supports integration with APIs, webhooks, and even tools like Twilio for phone agents. It's perfect for building customer support agents, voice bots, or intelligent assistants. This workflow connects n8n and Voiceflow with tools like Google Calendar, Qdrant (vector database), OpenAI, and an order tracking API to power a smart, multi-channel conversational agent. There are 3 main webhook endpoints in n8n that Voiceflow interacts with: - n8n_order – receives user input related to order tracking, queries an API, and responds with tracking status. - n8n_appointment – processes appointment booking, reformats date input using OpenAI, and creates a Google Calendar event. - n8n_rag – handles general product/service questions using a RAG (Retrieval-Augmented Generation) system backed by: - Google Drive document ingestion, - Qdrant vector store for search, - and OpenAI models for context-based answers. Each webhook is connected to a corresponding "Capture" block inside Voiceflow, which sends data to n8n and waits for the response. How It Works This n8n workflow integrates Voiceflow for chatbot/voice interactions, Google Calendar for appointment scheduling, and RAG (Retrieval-Augmented Generation) for knowledge-based responses. Here’s the flow: Trigger: Three webhooks (n8n_order, n8n_appointment, n8n_rag) receive inputs from Voiceflow (chat, voice, or phone calls). Each webhook routes requests to specific functions: - Order Tracking: Fetches order status via an external API. - Appointment Scheduling: Uses OpenAI to parse dates, creates Google Calendar events, and confirms via WhatsApp. - RAG System: Queries a Qdrant vector store (populated with Google Drive documents) to answer customer questions using GPT-4. AI Processing: - OpenAI Chains: Convert natural language dates to Google Calendar formats and generate responses. - RAG Pipeline: Embeds documents (via OpenAI), stores them in Qdrant, and retrieves context-aware answers. - Voiceflow Integration: Routes responses back to Voiceflow for multi-channel delivery (chat, voice, or phone). Outputs: - Confirmation messages (e.g., "Event created successfully"). - Dynamic responses for orders, appointments, or product support. Setup StepsPrerequisites: - APIs: - Google Calendar & Drive OAuth credentials. - Qdrant vector database (hosted or cloud). - OpenAI API key (for GPT-4 and embeddings). Configuration: - Qdrant Setup: Run the "Create collection" and "Refresh collection" nodes to initialize the vector store. Populate it with documents using the Google Drive → Qdrant pipeline (embeddings generated via OpenAI). - Voiceflow Webhooks: Link Voiceflow’s "Captures" to n8n’s webhook URLs (n8n_order, n8n_appointment, n8n_rag). - Google Calendar: Authenticate the Google Calendar node and set event templates (e.g., summary, description). - RAG System: Configure the Qdrant vector store and OpenAI embeddings nodes. Adjust the Retrieve Agent’s system prompt for domain-specific queries (e.g., electronics store support). Optional: - Add Twilio for phone-agent capabilities. - Customize OpenAI prompts for tone/accuracy. PS: You can import a Twilio number to assign it to your agent for becoming a Phone Agent. Need help customizing? Contact me for consulting and support or add me on LinkedIn.

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. If you'd like to explore how tools like this personal assistant could be built and integrated into your teams and organization, get in touch with us at 1 Node.

Who is this for? This workflow template is perfect for content creators, researchers, students, or anyone who regularly works with audio files and needs to transcribe and summarize them for easy reference and organization. What problem does this workflow solve? Transcribing audio files and summarizing their content can be time-consuming and tedious when done manually. This workflow automates the process, saving users valuable time and effort while ensuring accurate transcriptions and concise summaries. What this workflow does This template automates the following steps: - Monitors a specified Google Drive folder for new audio files - Sends the audio file to OpenAI's Whisper API for transcription - Passes the transcribed text to GPT-4 for summarization - Creates a new page in Notion with the summary Setup To set up this workflow: - Connect your Google Drive, OpenAI, and Notion accounts to n8n - Configure the Google Drive node with the folder you want to monitor for new audio files - Set up the OpenAI node with your API key and desired parameters for Whisper and GPT-4 - Specify the Notion database where you want the summaries to be stored How to customize this workflow - Adjust the Google Drive folder being monitored - Modify the OpenAI node parameters to fine-tune the transcription and summarization process - Change the Notion database or page properties to match your preferred structure With this AI-powered workflow, you can effortlessly transcribe audio files, generate concise summaries, and store them in a structured manner within Notion. Streamline your audio content processing and organization with this automated template.

I am submitting this workflow for the Obsidian community to showcase the potential of integrating Obsidian with n8n. While straightforward, it serves as a compelling demonstration of the potential unlocked by integrating Obsidian with n8n. How it works This workflow lets you retrieve specific Airtable data you need in seconds, directly within your Obsidian note, using n8n. By highlighting a question in Obsidian and sending it to a webhook via the Post Webhook Plugin, you can fetch specific data from your Airtable base and instantly insert the response back into your note. The workflow leverages OpenAI’s GPT model to interpret your query, extract relevant data from Airtable, and format the result for seamless integration into your note. Set up steps 1. Install the Post Webhook Plugin: Add this plugin to your Obsidian vault from the plugin store or GitHub. 2. Set up the n8n Webhook: Copy the webhook URL generated in this workflow and insert it into the Post Webhook Plugin's settings in Obsidian. 3. Configure Airtable Access: Link your Airtable account and specify the desired base and table to pull data from. 4. Test the Workflow: Highlight a question in your Obsidian note, use the “Send Selection to Webhook” command, and verify that data is returned as expected.

The automated image analysis and response workflow using n8n is a sophisticated solution designed to streamline the process of analyzing images sent via Telegram and delivering insightful responses based on the analysis outcomes. This cutting-edge workflow employs a series of meticulously orchestrated nodes to ensure seamless automation and efficiency in image processing tasks. ### Use Cases: This advanced workflow caters to a myriad of scenarios where real-time image analysis and response mechanisms are paramount. The use cases include: - Providing immediate feedback on images shared within Telegram groups. - Enabling automated content moderation based on the analysis of image content. - Facilitating rapid categorization and tagging of images based on the results of the analysis. ### Detailed Workflow Setup: To effectively implement this workflow, users must adhere to a meticulous setup process, which includes: - Access to the versatile n8n platform, ensuring seamless workflow orchestration. - Integration of a Telegram account to facilitate image reception and communication. - Utilization of an OpenAI account for sophisticated image analysis capabilities. - Configuration of Telegram and OpenAI credentials within the n8n environment for seamless integration. - Proficiency in creating and interconnecting nodes within the n8n workflow for optimal functionality. ### Detailed Node Description: Get the Image (Telegram Trigger): - Actively triggers upon receipt of an image via Telegram, ensuring prompt processing. - Extracts essential information from the received image message to initiate further actions. Merge all fields To get data from trigger: - Seamlessly amalgamates all relevant data fields extracted from the trigger node for comprehensive data consolidation. Analyze Image (OpenAI): - Harnesses the powerful capabilities of OpenAI services to conduct in-depth analysis of the received image. - Processes the image data in base64 format to derive meaningful insights from the visual content. Aggregate all fields: - Compiles and consolidates all data items for subsequent processing and analysis, ensuring comprehensive data aggregation. Send Content for the Analyzed Image (Telegram): - Transmits the analyzed content back to the Telegram chat interface for seamless communication. - Delivers the analyzed information in textual format, enhancing user understanding and interaction. Switch Node: - The Switch node is pivotal for decision-making based on predefined conditions within the workflow. - It evaluates incoming data to determine the existence or absence of specific elements, such as images in this context. - Utilizes a set of rules to assess the presence of image data in the message payload and distinguishes between cases where images are detected and when they are not. - This crucial node plays a pivotal role in directing the flow of the workflow based on the outcomes of its evaluations. ### Conclusion: The automation of image analysis processes through this sophisticated workflow not only enhances operational efficiency but also revolutionizes communication dynamics within Telegram interactions. By incorporating this advanced workflow solution, users can optimize their image analysis workflows, bolster communication efficacy, and unlock new levels of automation in image processing tasks.

Tags: Supply Chain, Logistics, Control Tower Context Hey! I’m Samir, a Supply Chain Engineer and Data Scientist from Paris, and the founder of LogiGreen Consulting. We design tools to help companies improve their logistics processes using data analytics, AI, and automation—to reduce costs and minimize environmental impact. Let’s use N8N to build smarter and more sustainable supply chains! 📬 For business inquiries, you can add me on LinkedIn. Who is this template for? This workflow template is designed for logistics operations that need a monitoring solution for their distribution chains. Connected to your Transportation Management Systems, this AI agent can answer any question about the shipments handled by your distribution teams. How does it work? The workflow is connected to a Google BigQuery table that stores outbound order data (customer deliveries). Here’s what the AI agent does: 🤔 Receives a user question via chat. 🧠 Understands the request and generates the correct SQL query. ✅ Executes the SQL query using a BigQuery node. 💬 Responds to the user in plain English. Thanks to the chat memory, users can ask follow-up questions to dive deeper into the data. What do I need to get started? This workflow requires no advanced programming skills. You’ll need: - A Google BigQuery account with an SQL table storing transactional records. - An OpenAI API key (GPT-4o) for the chat model. Next Steps Follow the sticky notes in the workflow to configure each node and start using AI to support your supply chain operations. 🎥 Watch My Tutorial 🚀 Curious how N8N can transform your logistics operations? Notes The chat trigger can easily be replaced with Teams, Telegram, or Slack for a better user experience. You can also connect this to a customer chat window using a webhook. This workflow was built using N8N version 1.82.1. Submitted: March 24, 2025

The workflow automates the process of creating a summarized and enriched podcast digest, which is then sent via email. Note that to use this template, you need to be on n8n version 1.19.4 or later.

n8n Template: Store Chat Data in Supabase PostgreSQL for WhatsApp/Slack Integration This n8n template captures chat data (like user ID, name, or address) and saves it to a Supabase PostgreSQL database. It’s built for testing now but designed to work with WhatsApp, Slack, or similar platforms later, where chat inputs aren’t predefined. Step 1: Configure Firewall Rules in Your VPC Network To let your n8n instance talk to Supabase, add a firewall rule in your VPC network settings (e.g., Google Cloud, AWS, etc.). 1. Go to VPC Network settings. 2. Add a new firewall rule: - Name: allow-postgres-outbound - Direction: Egress (outbound traffic) - Destination Filter: IPv4 ranges - Destination IPv4 Ranges: 0.0.0.0/0 (allows all; restrict to Supabase IPs for security) - Source Filter: - Pick IPv4 ranges and add the n8n VM’s IP range, or - Pick None if any VM can connect - Protocols and Ports: - Protocol: TCP - Port: 5432 (default PostgreSQL port) 3. Save the rule. Step 2: Get the Supabase Connection String Log into your Supabase Dashboard. 1. Go to your project, click the Connect button in the header. 2. Copy the PostgreSQL connection string: - postgresql://postgres.fheraruzdahjd:[YOUR-PASSWORD]@aws-0-eu-central-1.pooler.supabase.com:6543/postgres 3. Replace [YOUR-PASSWORD] with your Supabase account password (no brackets) and replace the string before that with your actual unique identifier. 4. Note the port (6543 or 5432)—use what’s in the string. Step 3: Set Up the n8n Workflow This workflow takes chat data, maps it to variables, and stores it in Supabase. It’s built to handle messy chat inputs from platforms like WhatsApp or Slack in production. Workflow Steps: - Trigger Node: "When clicking 'Test workflow'" (manual trigger). For now, it’s manual. In production, this will be a WhatsApp or Slack message trigger, which won’t have a fixed input format. - Set Node: "Set sample input variables (manual)". This node sets variables like id, name, and address to mimic chat data. Why? Chat platforms send unstructured data (e.g., a message with a user’s name or address). We map it to variables so we can store it properly. The id will be something unique like a phone number, account ID, or account number. - Sample Agent Node: Uses a model (e.g., GeminiFlash2.0 but doesn't matter). This is a placeholder to process data (e.g., clean or validate it) before saving. You can skip or customize it. - Supabase PostgreSQL Node: "Supabase PostgreSQL Database". Connects to Supabase using the connection string from Step 2. Saves the variables (id, name, address) to a table. Why store extra fields? The id (like a phone number or account ID) is the key. Extra fields like name or address let us keep all user info in one place for later use (e.g., analytics or replies). - Output Node: "Update additional values e.g., name, address". Confirms the data is saved. In production, this could send a reply to the chat platform. Why This Design? - Handles Unstructured Chat Data: WhatsApp or Slack messages don’t have a fixed format. The "Set" node lets us map any incoming data (e.g., id, name) to our database fields. - Scales for Production: Using id as a key (phone number, account ID, etc.) with extra fields like name makes this workflow flexible for many use cases, like user profiles or support logs. - Future-Ready: It’s built to swap the manual trigger for a real chat platform trigger without breaking. Step 4: Configure the Supabase PostgreSQL Node In the n8n workflow, set up the Supabase PostgreSQL node: - Host: aws-0-eu-central-1.pooler.supabase.com (from the connection string) - Port: 6543 (or what’s in the connection string) - Database: postgres - User: postgres.fhspudlibstmpgwqmumo (from the connection string) - Password: Your Supabase password - SSL: Enable (Supabase usually requires it) Set the node to Insert or Update: - Map id to a unique column in your Supabase table (e.g., phone number, account ID). - Map fields like name, address to their columns. Test the workflow to confirm data saves correctly. Security Tips - Limit Firewall Rules: Don’t use 0.0.0.0/0. Find Supabase’s IP ranges in their docs and use those. - Hide Passwords: Store your Supabase password in n8n’s environment variables. - Use SSL: Enable SSL in the n8n node for secure data transfer.

This workflow is a template example for making Discord GPT-powered bots. Incoming user requests are analysed and categorised via the OpenAI node with the help of a hand-crafted prompt. The response message is then routed to a different Discord channel.

Who is this for? This workflow template is designed for AI enthusiasts, developers, and privacy-conscious users who want to leverage the power of local large language models (LLMs) without sending data to external services. It's particularly valuable for those running Ollama locally who want intelligent routing between different specialized models. What problem is this workflow solving? When working with multiple local LLMs, each with different strengths and capabilities, it can be challenging to manually select the right model for each specific task. This workflow automatically analyzes user prompts and routes them to the most appropriate specialized Ollama model, ensuring optimal performance without requiring technical knowledge from the end user. What this workflow does This intelligent router: - Analyzes incoming user prompts to determine the nature of the request - Automatically selects the optimal Ollama model from your local collection based on task requirements - Routes requests between specialized models for different tasks: - Text-only models (qwq, llama3.2, phi4) for various reasoning and conversation tasks - Code-specific models (qwen2.5-coder) for programming assistance - Vision-capable models (granite3.2-vision, llama3.2-vision) for image analysis - Maintains conversation memory for consistent interactions - Processes everything locally for complete privacy and data security How to customize this workflow to your needs - Add or remove models from the router's decision framework based on your specific Ollama collection - Adjust the system prompts in the LLM Router to prioritize different model selection criteria - Modify the decision tree logic to better suit your specific use cases - Add additional preprocessing steps for specialized inputs This workflow demonstrates how n8n can be used to create sophisticated AI orchestration systems that respect user privacy by keeping everything local while still providing intelligent model selection capabilities.

Analyze your Mailchimp campaign performance using OpenAI, and effortlessly save crucial insights on Google Sheets with accompanying improvement suggestions.

How it works: This project creates a personal AI assistant named Angie that operates through Telegram. Angie can summarize daily emails, look up calendar entries, remind users of upcoming tasks, and retrieve contact information. The assistant can interact with users via both voice and text inputs. --- Step-by-step:Telegram Trigger: The workflow starts with a Telegram trigger that listens for incoming message events. The system determines if the incoming message is voice or text. If voice, the voice file is retrieved and transcribed to text using OpenAI's API Speech to Text. AI Assistant: The telegram request is passed to the AI assistant (Angie). Tools Integration: The AI assistant is equipped with several tools: - Get Email: Uses Gmail API to fetch recent emails, filtering by date. - Get Calendar: Retrieves calendar entries for specified dates. - Get Tasks: Connects to a Baserow (open-source Airtable alternative) database to fetch to-do list items. - Get Contacts: Also uses Baserow to retrieve contact information. Response Generation: The AI formulates a response based on the gathered information and sends it back to the user on Telegram.

This n8n workflow template allows you to write WordPress posts by just providing a few keywords. It uses AI technology to write the text and to create the post's featured image. The text includes an introduction, chapters, and conclusions. Each chapter is written independently, allowing you to create very long articles. I suggest reviewing the created posts before publishing them on your WordPress website. The article generation might take some minutes as each chapter is created independently. Features - Easy to use: Easy web interface to start the generation of the WordPress post - AI-powered: Text and image generation is done by artificial intelligence - Long-text ready: Possibility to create very long articles - Configurable: Possibility to provide as many keywords as you want, to choose the number of chapters, and the length of the article - Plugs into your WordPress: Easily integrates with your WordPress website - Tweak it as you want: Fine-tune the Open AI prompts and the workflow as you want Workflow Steps 1. User form: An n8n form is used to trigger the post creation 2. Settings: This node is used to set your WordPress URL (which is used later in the workflow) 3. Article structure: First AI action that writes the introduction, the conclusions, and the chapter structure. 4. Data check: Check that the data provided by the AI is valid 5. Chapters split/Chapters text: Splits the data for each chapter into a separate item and generates each chapter's text with AI 6. Content preparation: Prepares the text for posting, merging the introduction, the chapters, and the conclusions. Adds some basic HTML formatting 7. Draft on WordPress: Creates the draft post on WordPress 8. Featured image: Creates a featured image and adds it to the post on WordPress 9. User feedback: Sends feedback to the user on the n8n form Getting Started To deploy and use this template: 1. Import the workflow into your n8n workspace. 2. Set your WordPress URL in the wordpress_url field in the "Settings" node. Include the slash (/) at the end of the URL. 3. Set up your Open AI n8n credentials by following the appropriate guide. The Open AI credentials are used by the Open AI nodes ("Create post title and structure", "Create chapters text", and "Generate featured image"). 4. Set up your WordPress n8n credentials by following the appropriate guide. The WordPress credentials are used by the WordPress and HTTP Request nodes ("Post on WordPress", "Upload media", and "Set image ID for the post"). Pay attention that the "Password" in the WordPress credentials is not the user's password but the Application Password. How to use the workflow to create a WordPress post 1. Activate the workflow. 2. Open the "Form" node and copy the "Production URL". This is the public URL of the form to AI-write the post. 3. Open the URL in a browser and fill in the form. 4. Wait a few minutes till you get the feedback in the form that the post was created. 5. Go to WordPress and check the newly created draft post. Review and publish your post!

Every time a new Dialogflow fulfillment webhook is triggered, Make will automatically filter the scenario based on a condition. Then, a specific fulfillment response is sent depending on each route.

This n8n workflow automates the process of saving web articles or links shared in a chat conversation directly into a Notion database, using Google's Gemini AI and Browserless for web scraping. Who is this AI automation template for? It's useful for anyone wanting to reduce manual copy-pasting and organize web findings seamlessly within Notion. A smarter web clipping tool! What this AI automation workflow does: Starts when a message is received. Uses a Google Gemini AI Agent node to understand the context and manage the subsequent steps. It identifies if a message contains a request to save an article/link. If a URL is detected, it utilizes a tool configured with the Browserless API (via the HTTP Request node) to scrape the content of the web page. Creates a new page in a specified Notion database, populating it with the summary scraped content, in a specific format, never leaving out any important details. It also saves the original URL, smart tags, publication date, and other metadata extracted by the AI. Posts a confirmation message (e.g., to a Discord channel) indicating whether the article was saved successfully or if an error occurred. Setup: - Import Workflow: Import this template into your n8n instance. - Configure Credentials & Notion Database: - Notion Database: Create or designate a Notion database (like the example "Knowledge Database") where articles will be saved. Ensure this database has the following properties (fields): - Name (Type: Text) - This will store the article title. - URL (Type: URL) - This will store the original article link. - Description (Type: Text) - This can store the AI-generated summary. - Tags (Type: Multi-select) - Optional, for categorization. - Publication Date (Type: Date) - *Optional, store the date the article was published. Ensure the n8n integration has access to this specific database. If you require a different format for the Notion Database, note that you will have to update the Notion tool configuration in this n8n workflow accordingly. - Notion Credential: Obtain your Notion API key and add it as a Notion credential in n8n. Select this credential in the save_to_notion tool node. - Configure save_to_notion Tool: In the save_to_notion tool node within the workflow, set the 'Database ID' field to the ID of the Notion database you prepared above. Map the workflow data (URL, AI summary, etc.) to the corresponding database properties (URL, Description, etc.). In the blocks section of the notion tool, you can define a custom format for the research page, allowing the AI to fill in the exact details you want extracted from any web page! - Google Gemini AI: Obtain your API key from Google AI Studio or Google Cloud Console (if using Vertex AI) and add it as a credential. Select this credential in the "Tools Agent" node. - Discord (or other notification service): If using Discord notifications, create a Webhook URL (instructions) or set up a Bot Token. Add the credential in n8n and select it in the discord_notification tool node. Configure the target Channel ID. - Browserless/HTTP Request: - Cloud: Obtain your API key from Browserless and configure the website_scraper HTTP Request tool node with the correct API endpoint and authentication header. - Self-Hosted: Ensure your Browserless Docker container is running and accessible by n8n. Configure the website_scraper HTTP Request tool node with your self-hosted Browserless instance URL. - Activate Workflow: Save, test, and activate the workflow. How to customize this workflow to your needs: - Change AI Model: Experiment with different AI models supported by n8n (like OpenAI GPT models or Anthropic Claude) in the Agent node if Gemini 2.5 Pro doesn't fit your needs or budget, keeping in mind potential differences in context window size and processing capabilities for large content. - Modify Notion Saving: Adjust the save_to_notion tool node to map different data fields (e.g., change the summary style by modifying the AI prompt, add specific tags, or alter the page content structure) to your Notion database properties. - Adjust Scraping: Modify the prompt/instructions for the website_scraper tool or change the parameters sent to the Browserless API if you need different data extracted from the web pages. You could also swap Browserless for another scraping service/API accessible via the HTTP Request node.

Fully automated AI Agent system that creates carousels and slideshows for social media, 100% automated, running on autopilot every day or every hour! You can post to multiple Instagram accounts, multiple TikTok accounts, multiple Pinterest accounts, etc. It even posts long-form threads for Twitter, Bluesky, and Threads, with 1 image per post, so everything is neatly formatted. And, you can easily customize the images and quotes to fit your brand, niche, or business. n8n - workflow automation that runs daily AI agent - use ChatGPT to brainstorm quotes and image prompts Blotato - generate slideshow/carousel and publish to 8 social platforms