Anton is a Developer Advocate at JetBrains, working with Kotlin, IntelliJ IDEA, and AI-driven developer tools. With a background in server-side development, he has spent over a decade building software for developers. A Java Champion since 2014, Anton speaks at conferences, shares insights on the Kotlin YouTube channel, and enjoys exploring new ideas in programming languages, AI-powered tooling, and developer workflows. He’s always experimenting with new tech, looking for ways to make coding more efficient and enjoyable.
AI agents don’t have to be black boxes—or written in Python. In this session, we’ll build one from scratch in Kotlin using Koog, a lightweight framework for constructing tool-using LLM agents.
We’ll start by breaking down the fundamentals:
• How an agent communicates with a language model
• How tools are registered and invoked
• How to build robust interaction loops for both local LLMs and remote APIs like OpenAI or Google
From there, we’ll layer in Model Control Protocol (MCP) integrations and show how Koog’s DSL lets us define agent workflows as readable, reproducible graphs.
The session concludes with a live implementation of a coding agent—capable of generating and testing small programs—by wiring together tools such as test runners, linters, and file systems.
Searching for speaker images...