Talking Kotlin Building AI Agents With Koog
5 snips
Nov 17, 2025 Vadim Briliantov, Technical Lead for Koog at JetBrains, shares insights on building AI agents in Kotlin. He defines AI agents as dynamic problem solvers that interact with environments using Koog, an open-source framework. The discussion highlights Koog's applications, including backend automations and on-device agents, while exploring features like multi-phase coding strategies and custom tool management. Vadim also delves into history compression techniques, type safety, and the roadmap for future development, emphasizing Koog's enterprise readiness and exciting open-source potential.
AI Snips
Chapters
Transcript
Episode notes
Vadim's Path From Intern To Koog Lead
- Vadim described his eight-year JetBrains journey from intern to Tech Lead of the AI agents platform.
- He explained how internal agent work evolved into open-sourcing Koog for the wider Kotlin community.
Koog Is A Kotlin Framework For Agents
- Koog is an open-source Kotlin framework for building general-purpose AI agents across Android, backend, and JVM ecosystems.
- It targets enterprise-ready agentic systems, not only coding assistants, enabling on-device and server-scale deployments.
Agents Are Built From Three Layers
- Koog splits agents into environment (tools), model connection, and a middle 'agent strategy' layer expressed as graphs.
- Strategies define high-level algorithms as nodes and edges so agents follow structured multi-step flows.