Sebastian and Márton talk to Vadim Briliantov, the Technical Lead for Koog: an agentic framework built by JetBrains. We learn about what AI agents are, and why building them in Kotlin with Koog is a great choice. We also discuss all the different ways AI agents can connect to other systems and your existing code, and look at advanced features for agents like custom strategies, model switching, and history compression.

Resources:

• JetBrains/koog on GitHub
• Koog Documentation

Hosts:

• Sebastian Aigner – Website | Bluesky
• Márton Braun – Website | Bluesky

Guest:

• Vadim Briliantov – LinkedIn | Medium | GitHub | Bluesky | Twitter/X

Timeline:
(0:00) Intro
(1:11) Vadim’s history at JetBrains
(4:21) What’s an AI Agent?
(5:47) Koog!
(7:12) Applications for agents
(12:43) Koog’s building blocks
(15:05) Strategies, feedback loops
(23:55) The Kotlin DSL
(26:12) Persistent state
(29:48) Subgraphs
(32:33) Tools
(39:52) MCP support (and A2A)
(44:01) Entry point and type safety
(49:39) Spring and Ktor support
(51:27) LLM Providers
(53:30) Model switching
(56:02) History and memory
(59:22) Enterprise-ready
(1:02:12) History compression
(1:11:47) Markdown?!
(1:14:37) What’s next?
(1:18:22) Going open-source
(1:20:32) Conclusion

Sebastian and Márton chat with Marcin Moskała about coroutines.

Resources:

• Coroutines Mastery course
• Coroutines | Kotlin Documentation
• kotlinx.coroutines
• Taming Asynchronous Beasts | Marcin Moskała
• Coroutine Debugging in IntelliJ IDEA | Alexey Merkulov
• Lifecycles, Coroutines and Scopes | Alejandro Serrano Mena
• Collect Like a Pro | Manuel Vivo
• Untangling Coroutine Testing | Márton Braun
• JetBrains/lincheck – Concurrent testing framework
• #talking-kotlin on Kotlin Slack

Hosts:

• Sebastian Aigner – Website | Bluesky
• Márton Braun – Website | Bluesky

Guest:

• Marcin Moskała – kt.academy

Timeline:
(0:00) Introduction
(1:18) Branding discussion
(3:23) Handling preconceptions
(4:54) What are coroutines?
(7:17) Lightweight threads?
(11:07) Where coroutines live
(13:27) Sequence Builder Example
(17:37) The design of coroutines
(20:52) What Makes Coroutines special vs other languages?
(26:56) Coroutines vs Loom
(34:55) Easy to start, hard to master
(41:07) Common mistakes
(49:33) Flows
(58:52) Thinking about Flows
(1:02:41) Derailing the conversation
(1:03:55) Flows for single values
(1:12:27) Structured concurrency
(1:18:53) The 4 advantages
(1:24:40) Seb tries web dev / The web is broken?!
(1:31:15) collectAsStateWithLifecycle
(1:32:00) Gardening break
(1:36:23) Scopes and contexts
(1:43:22) Testing coroutines
(1:50:29) Lincheck
(1:51:32) Turbine
(1:55:05) Coroutines Mastery course
(2:01:43) Wrap-up

Sebastian and Alex chat about the kotlinx.rpc project, in a special episode recorded in the Munich JetBrains office. They explore all the different components of the library, how you can use it to define RPC services and clients, integrate with Ktor and existing gRPC definitions, and more. While the library is still experimental, it’s already feature-packed, and it has ambitious plans for the future!

• kotlinx-rpc on GitHub
• #kotlinx-rpc on Slack
• kotlinx.serialization on GitHub
• gRPC

• 
  

Host: Sebastian Aigner

• Website
• Bluesky

Guest: Alex Sysoev

• LinkedIn

• GitHub