Workflow Templates

The Agent Decisioner is a dynamic, AI-powered routing system that automatically selects the most appropriate large language model (LLM) to respond to a user's query based on the query’s content and purpose. This workflow ensures dynamic, optimized AI responses by intelligently routing queries to the best-suited model. Advantages 🔁 Automatic Model Routing:** Automatically selects the best model for the job, improving efficiency and relevance of responses. 🎯 Optimized Use of Resources:** Avoids overuse of expensive models like GPT-4 by routing simpler queries to lightweight models. 📚 Model-Aware Reasoning:** Uses detailed metadata about model capabilities (e.g., reasoning, coding, web search) for intelligent selection. 📥 Modular and Extendable:** Easy to integrate with other tools or expand by adding more models or custom decision logic. 👨‍💻 Ideal for RAG and Multi-Agent Systems:** Can serve as the brain behind more complex agent frameworks or Retrieval-Augmented Generation pipelines. How It Works Chat Trigger: The workflow starts when a user sends a message, triggering the Routing Agent. Model Selection: The AI Agent analyzes the query and selects the best-suited model from the available options (e.g., Claude 3.7 Sonnet for coding, Perplexity/Sonar for web searches, GPT-4o Mini for reasoning). Structured Output: The agent returns a JSON response with the user’s prompt and the chosen model. Execution: The selected model processes the query and generates a response, ensuring optimal performance for the task. Set Up Steps Configure Nodes: Chat Trigger: Set up the webhook to receive user messages. Routing Agent (AI Agent): Define the system message with model strengths and JSON output rules. OpenRouter Chat Model: Connect to OpenRouter for model access. Structured Output Parser: Ensure it validates the JSON response format (prompt + model). Execution Agent (AI Agent1): Configure it to forward the prompt to the selected model. Connect Nodes: Link the Chat Trigger to the Routing Agent. Connect the OpenRouter Chat Model and Output Parser to the Routing Agent. Route the parsed JSON to the Execution Agent, which uses the chosen model via OpenRouter Chat Model1. Credentials: Ensure OpenRouter API credentials are correctly set for both chat model nodes. Test & Deploy: Activate the workflow and test with sample queries to verify model selection logic. Adjust the routing rules if needed for better accuracy. Need help customizing? Contact me for consulting and support or add me on Linkedin.

Who is this for? This workflow is ideal for sales teams, marketers, and virtual assistants who manage outbound campaigns and want to improve their cold outreach personalization. It helps automate the research and writing process for each lead, saving time while improving quality. What problem is this workflow solving? Cold outreach often lacks personalization because manually reviewing each lead's website takes time. This workflow eliminates that bottleneck by using AI to auto-generate personalized icebreakers, summaries, and outreach emails based on a lead’s website—without human research. What this workflow does This n8n workflow runs on a schedule and pulls leads from Airtable who don't yet have an "Ice breaker" field filled out. For each lead, it does the following: Trigger: Scheduled daily via the Run Daily to Process New Leads node. Search Airtable: Finds leads in Airtable where the Ice breaker field is empty using the Search Cold Leads Without Icebreaker node. Split in Batches: Iterates through each lead one by one using Loop Through Each Lead. Rate Limiting: Waits briefly before each request using Wait Before Making Request to avoid rate limits. Scrape Website: Sends each lead’s website to Dumpling AI's /scrape endpoint via the Scrape Lead Website with Dumpling AI HTTP request. Generate AI Copy: Sends the scraped content to GPT-4o using the Generate Icebreaker, Summary & Email (GPT-4o) node. It asks the LLM to create: A short personalized icebreaker A 2–3 line website summary A short email body for cold outreach Save Results: Updates the original Airtable record with the generated content using the Save AI Output Back to Airtable node. Sticky Note: Provides an overview of the workflow and usage instructions for future editors or collaborators. This loop continues for all leads found, updating Airtable with fresh AI-generated outreach content. Integration Requirements Airtable (Personal Access Token) Dumpling AI API Key (Header Auth) OpenAI (GPT-4o)

⚠️ Disclaimer This workflow uses a community node: npm install n8n-nodes-supadata Please make sure to install this before running the workflow. 🔎 Who is this for? This workflow is for anyone who wants quick summaries of YouTube videos, such as researchers, students, analysts, or busy professionals. Just send a video link via Telegram and receive a structured summary in seconds—no need to watch the entire video. 🧠 What problem is this workflow solving? Watching long videos to extract key information is time-consuming. This automation solves that by instantly: Fetching the full transcript of the video Summarizing the content with AI Sending a clean summary directly to Telegram for quick reading It’s a fast and reliable way to stay informed without the overwhelm. ⚙️ What this workflow does 💬 Telegram Trigger Start by sending a YouTube link to your Telegram bot. 🎙️ Get Transcript (Supadata) Uses Supadata API to retrieve the full video transcript. 🧠 Summarize with OpenAI GPT-4o Processes the transcript using a structured prompt to extract: Main theme of the video Target audience Key insights and tips Problems discussed and solutions mentioned Notable quotes or highlights 📨 Send to Telegram The final summary is formatted and sent back to your Telegram chat, ready for reading or saving. 🛠️ Requirements n8n instance (Cloud or self-hosted)** Supadata API Key OpenAI API Key Telegram Bot Token ✅ Output Example The Telegram summary includes: 🎯 Title and topic 💡 Key learnings 🛠️ Tips or insights 🚨 Issues raised and solutions 📝 Quotes or highlights Just send a link, and get the core message—fast. Perfect for learning on the go. 🧠📲 Made by: Khaisa Studio Tag: youtube, summarizer, telegram, openai Category: AI Automation, Video Tools Need a custom? contact me on LinkedIn or Web

Description This workflow creates an automated video content pipeline that generates creative TikTok-style videos using AI. It combines OpenAI's GPT-4o-mini for idea generation with Sisif.ai's text-to-video AI technology to produce engaging short-form content automatically. Perfect for: Content creators, social media managers, marketing teams, and anyone who wants to maintain a consistent flow of AI-generated video content without manual intervention. Prerequisites Sisif.ai Account**: Sign up at sisif.ai and get your API token from sisif.ai/api/ OpenAI Account**: Get your API key from OpenAI platform n8n Instance**: Self-hosted or cloud instance How it Works The workflow operates on a scheduled cycle, generating fresh video content every 6 hours: 🤖 AI Idea Generation: OpenAI's GPT-4o-mini acts as a creative video strategist, generating unique, trend-aware video concepts optimized for TikTok and social media 🎬 Video Creation: Sisif.ai transforms each creative prompt into a high-quality 5-second video in 360x640 resolution ⏱️ Smart Monitoring: The workflow intelligently monitors video generation progress, waiting for completion before proceeding 📊 Data Processing: Final video data is structured and prepared for further use or storage Key Features ⚡ Fully Automated Runs every 6 hours without manual intervention Generates 4 unique videos daily (28 videos per week) Self-monitoring with automatic retry logic 🎯 Optimized for Social Media TikTok-perfect 360x640 resolution 5-second duration for maximum engagement Trend-aware content generation Action-packed, visual storytelling 🔧 Smart Architecture Simple HTTP requests for reliable operation Bearer token authentication for secure API access Automatic status checking and waiting logic Error handling and retry mechanisms

Monitor & Archive Keyword Tweets to Airtable 📌 Overview Automatically searches Twitter for any keyword/topic (person, brand, hashtag), filters duplicates, and stores new tweets in Airtable with rich metadata - all on a daily schedule. 🛠️ Workflow Steps ⏰ Schedule Trigger Runs daily at 8 AM (customizable) 🐦 Twitter Search Fetches 100 latest tweets matching your keyword 📦 Reformat Data Structures: Text | Likes | ID | URL Author | Timestamp 🗂️ Fetch Airtable Records Retrieves existing tweet IDs 🔍 Deduplicate Compares IDs to exclude duplicates ➕ Append New Tweets Saves only fresh entries to Airtable 💡 Key Benefits 🤖 Automated Monitoring**: Near real-time tracking 🧹 Clean Data**: Zero duplicate entries 📁 Structured Archive**: Organized metadata for analysis ⚙️ Fully Customizable**: Adapt keywords/schedule/output 🧩 Perfect For Social media analysts tracking brand mentions Journalists monitoring public figures Researchers archiving topic conversations Marketing teams measuring campaign reach 🚀 Getting Started Import into n8n Connect Credentials: Twitter API keys Airtable base + table ID Configure: Search keyword (e.g., "Narendra Modi") Schedule timing Run & Forget: Initial run to backfill Daily auto-archiving ✅ Enhancement Ideas Add Filters: Exclude retweets Filter by language Geolocation targeting Notifications: Slack alerts for new tweets Email digests AI Extensions: Sentiment analysis Auto-categorization Trend reporting

This n8n template helps you automatically discover, analyze, and track trending topics and videos on YouTube using an AI-powered agent. Use cases are many: This workflow is perfect for YouTube creators needing fresh video ideas, digital marketers scouting new campaign topics, social media managers who want to catch trends early, and researchers who want to analyze what’s viral. How It Works The workflow starts whenever a chat message is received (e.g., a trend question, a topic prompt, or a request for insights). Incoming chat is routed to the AI Agent – Trend Explorer node: First, the agent triggers the Workflow – YouTube Search tool to gather the latest trending topics and keywords from YouTube. Next, the agent supplies this real-time YouTube data to the OpenAI Chat Model for deep analysis, trend interpretation, and unique insights. To provide context-aware answers and track ongoing interests, the agent also references a Simple Memory module, recalling past queries, and user instructions. Finally, the result is a fast, data-driven, and smart trend report delivered instantly to your chat. How To Set Up Download the workflow package (including 2 .json files) and import it into your n8n interface. Set up necessary access in the following components of the AI Agent - Trend Explorer node: OpenAI Chat Model: allows API connection for trend insights. Workflow – YouTube Search: searches for trending videos based on the query. Simple Memory (optional): enhances experience for ongoing sessions. Start by sending a chat message on n8n. Check the response from the AI agent in the same chat box. Ask follow-ups, explore deeper, or trigger new searches - all in one chat thread. Requirements n8n instance (self-hosted or cloud). Set up API access to OpenAI Chat Model for chat-based AI. How To Customize Connect to your favorite chat platforms**: Easily integrate with additional chat triggers such as Telegram, Slack, or your preferred messaging app. Choose your preferred AI model**: If you want a different viewpoint, simply swap OpenAI Chat Model for Google Gemini, Claude, or any compatible LLM model in your workflow. Upgrade memory for smarter conversations: For long-term recall or more advanced, context-aware chats, replace **Simple Memory with a vector database like Pinecone or Redis. Need Help? If you’d like this workflow customized to fit your tools and platforms availability, or if you’re looking to build a tailored AI Agent for your own business - please feel free to reach out to Agent Circle. We’re always here to support and help you to bring automation ideas to life. Join our community on different platforms for support, inspiration and tips from others. Website: https://www.agentcircle.ai/ Etsy: https://www.etsy.com/shop/AgentCircle Gumroad: http://agentcircle.gumroad.com/ Discord Global: https://discord.gg/d8SkCzKwnP FB Page Global: https://www.facebook.com/agentcircle/ FB Group Global: https://www.facebook.com/groups/aiagentcircle/ X: https://x.com/agent_circle YouTube: https://www.youtube.com/@agentcircle LinkedIn: https://www.linkedin.com/company/agentcircle

What it does This is a simplistic demo workflow showing how to extract a license plate number from an image of a car submitted via a form – or in more general terms showcasing how you can: use a form trigger to upload files and feed it into an LLM use a changeable LLM model for image-to-text analysis Set up steps Import the workflow Ensure you have registered and account, purchased some credits and created and API key for OpenRouter.ai Create/adapt the OpenRouter credential with your indivial API key for OpenRouter "Test workflow" and submit an image of a car with license plate to extract its number How to adapt By changing the "prompt" in th "Settings" node you can quickly adapt this exemplatory workflow to other image-to-text use cases, such as: summarization: "summarize what's seen in the image" location finding: "identify the location where the image was taken" text extraction: "extract all text from the image and return it as markdown" Thanks to using OpenRouter, you also can quickly experiment with finding good model choices by simply changing the "model" in the "Settings" node. The following models gave good results for this demo use-case: google/gemini-2.0-flash-001 meta-llama/llama-3.2-90b-vision-instruct openai/gpt-4o The llama-3.2-11b and even claude-3.5-sonnet didn't recognize all characters in all test images. Using a generic LLM-model offers a quick way of prototyping an image-to-text application. For specific use cases in serious and scalable production deployments, consider using an API based service specifically made to that purpose, such as: Google Cloud Vision API Microsoft Azure Computer Vision Azure AI Document Intelligence Amazon Textract

Let a user load multiple files with a Form node, and process the binary data. A very important workflow for many tools. This is a learning example of several core concepts that are hard to grasp in n8n: $binary data Loop and $runIndex Split Out The Save File deomonstrates how to access the binary data correctly, but could be swapped to POST the files to an AI, for example.

AI-Powered Workflow for Auto-Responding to Positive Cold Email Replies This workflow is designed for agencies, freelancers, and sales teams who want to turn positive cold email replies into booked meetings automatically—without hiring VAs or spending hours on manual responses. ❓ The Problem Most teams waste time replying manually or pay for virtual assistants, leading to delays and missed opportunities. This template eliminates that bottleneck. ✅ What the Workflow Does Detects positive replies from Instantly.ai campaigns Uses AI to analyze intent and craft natural, human-like responses Adds personalization to keep replies authentic Includes Calendly links, product docs, or FAQs based on the lead’s intent Sends responses instantly—so you never miss a hot lead again No robotic AI text. Just smooth, human-style emails that get booked calls faster. 👥 Who is This For? Agencies** running Instantly.ai or similar outbound tools Founders** handling their own cold email outreach Sales teams** looking to automate follow-up and booking Anyone who gets 5–20 positive replies a week and wants to 2x–4x conversions ✅ Requirements n8n** (Cloud or self-hosted) Instantly.ai account** with API access OpenAI API key** (stored securely in n8n credentials) (Optional) Calendly or booking link, Notion or Google Docs for resources ⚙️ How to Set Up Import the workflow into n8n Add your Instantly.ai API credentials and OpenAI key using n8n’s credential manager Customize the AI prompt for your tone, CTA, and offer Insert your Calendly or booking link in the response template Test with one positive reply to confirm filtering and response quality Activate the workflow to auto-reply in real time 🔧 How to Customize Adjust the filtering logic for different keywords or intent signals Add branching for multiple booking links (e.g., based on region or service type) Push responses to a CRM for tracking Include extra resources like case studies or pricing docs

Travel Agent that Auto Response on Mail In this guide, we’ll break down how to set up an AI-powered auto-reply system that works while you sleep. Ready to 10X your efficiency? Let’s dive in! What’s the Goal? AI-driven auto-responses for Email. Instant replies to FAQs, order confirmations, and support queries. 24/7 availability - no more “We’ll get back to you soon” delays. Seamless integration with existing business tools. By the end, you’ll have a self-running communication assistant that never takes a coffee break. Why Does It Matter? Why automate replies? Because time = money and manual typing is so 2010. Here’s why this workflow is a game changer: Zero Human Error: AI doesn’t get tired or make typos. Lightning-Fast Replies: Customers get instant answers, improving satisfaction. 24/7 Availability: No more “Out of Office” replies. Focus on High-Value Work: Free your team from mundane tasks. Think of it as hiring a super efficient virtual assistant - minus the salary. How It Works Here’s the step by step magic behind the automation Step 1: Trigger the Workflow Detect new messages from WhatsApp, Email, or Slack. Use n8n’s webhook or API integration to capture incoming queries. Step 2: Process the Message with AI Send the message to an AI model (like OpenAI GPT-4 or Gemini). Generate a context-aware, human-like response. Step 3: Send the Automated Reply Route the AI-generated response back to the original platform. Ensure personalization (e.g., “Hi [Name], thanks for reaching out!”). Step 4: Log & Optimize Store interactions in a database (Airtable, Google Sheets). Continuously improve AI responses based on past data. How to use the workflow? Importing a workflow in n8n is a straightforward process that allows you to use pre-built or shared workflows to save time. Below is a step-by-step guide to importing a workflow in n8n, based on the official documentation and community resources. Steps to Import a Workflow in n8n 1. Obtain the Workflow JSON Source the Workflow:** Workflows are typically shared as JSON files or code snippets. You might receive them from: The n8n community (e.g., n8n.io workflows page). A colleague or tutorial (e.g., a .json file or copied JSON code). Exported from another n8n instance (see export instructions below if needed). Format:** Ensure you have the workflow in JSON format, either as a file (e.g., workflow.json) or as text copied to your clipboard. 2. Access the n8n Workflow Editor Log in to n8n:** Open your n8n instance (via n8n Cloud or your self-hosted instance). Navigate to the Workflows tab in the n8n dashboard. Open a New Workflow:** Click Add Workflow to create a blank workflow, or open an existing workflow if you want to merge the imported workflow. 3. Import the Workflow Option 1: Import via JSON Code (Clipboard): In the n8n editor, click the three dots (⋯) in the top-right corner to open the menu. Select Import from Clipboard. Paste the JSON code of the workflow into the provided text box. Click Import to load the workflow into the editor. Option 2: Import via JSON File: In the n8n editor, click the three dots (⋯) in the top-right corner. Select Import from File. Choose the .json file from your computer. Click Open to import the workflow.

This workflow is designed for dynamic and intelligent conversational capabilities. It incorporates OpenAI's GPT-4o model for natural language understanding and generation. Additional tools include SerpAPI and Wikipedia for enriched, data-driven responses. The workflow is triggered manually, and utilizes a 'Window Buffer Memory' to maintain the context of the last 20 interactions for better conversational continuity. All these components are orchestrated through n8n nodes, ensuring seamless interconnectivity. To use this template, you need to be on n8n version 1.50.0 or later.

This workflow allows users to generate beautifully stylized 3D-rendered food emoji icons based on a simple text prompt. It combines user input, structured visual design generation, and image rendering using OpenAI’s GPT models. ✨ What It Does Collects user input via a form: e.g. "green apple" Generates a structured JSON specification describing the emoji’s form, lighting, texture, and color scheme Uses AI to render an image based on that spec—styled like a high-quality emoji icon with a transparent background 🧠 Use Case This template is ideal for: Designers or creators needing icon ideas or drafts for food items Developers building emoji packs or digital stickers Inspiration for AI-assisted product illustration or branding 💡 Why It's Useful Instead of prompting a model directly with vague terms, this flow creates a structured visual spec tailored to food items. The final emoji-style icon is polished, modern, and downloadable. ✅ Requirements To get started with this workflow, follow these steps: 🔑 Configure Credentials: Set up your API credentials for OpenAI and Google Drive 💳 Add OpoenAI Credit: Make sure to add credit to your OpenAI account, verify your organization (required for generating images) 📊 Connect Google Drive: Authenticate your Google Drive account ⚙️ (Optional) Customize Prompts: Adjust the prompts within the workflow to better suit your specific needs Note: Each image generation will cost you about $0.17