Your First AI Agent in Kotlin | Tutorial

📢 UPDATE: Koog is now available for Java! You can now build enterprise AI agents using our new, idiomatic Java builder API. ☕️ Java Developers: While this specific video is coded in Kotlin, Koog for Java shares the exact same features, concepts, and naming conventions. The architecture you learn here applies directly to your Java codebase! 📎 Read the Java launch post: https://blog.jetbrains.com/ai/2026/03... Learn how to build your first AI agent in Kotlin using Koog, JetBrains’ framework for working with LLMs. 🚀 We’ll start from scratch—setting up dependencies, creating an LLM client, and sending prompts to models.You’ll see how to handle responses, translate text, and even connect your agent to the real world by calling tools. Step by step, we’ll implement a money transfer example, showing how to define tools, register them, and let the agent use them dynamically. You’ll also learn how Koog simplifies working with multiple models, handles conversation history, and manages tool calls automatically. By the end, you’ll understand what makes an AI agent tick: an LLM acting as the “brain” plus tools it can call in a loop. This demo is just the beginning—Koog gives you the flexibility to scale from prototypes to production-ready AI agents. 🔗 Useful resources: 📦 Koog repository: https://github.com/JetBrains/koog 📚 Koog documentation: https://docs.koog.ai/ 💻 Project accompanying this video (contains code samples): https://github.com/svtk/koog-tutorials 📝 Tutorial accompanying this video: https://github.com/svtk/koog-tutorial... #kotlin #ai #koog