Building AI Agents with Koog and Kotlin
AI systems are rapidly evolving from simple chat interfaces to autonomous agents capable of reasoning, planning, memory handling, and interacting with external systems.
In this hands-on workshop, participants will learn how to build AI agents using Koog and Kotlin, moving beyond simple prompt engineering towards reliable, structured, and event-driven AI workflows.
Participants will implement agents that use tools, structured outputs, memory, and event-driven integrations while exploring how modern software architecture principles remain essential in AI-enabled systems.
The workshop also demonstrates how AI agents can interact with event-driven and event-sourced systems to derive insights, process business events, and build contextual understanding over time.
Most AI tutorials focus primarily on prompts and isolated demos. Real-world AI systems, however, require structured workflows, memory management, reliable integrations, and maintainable architectures.
This workshop introduces participants to agentic systems using Koog and Kotlin.
Participants will:
- Learn the fundamentals of AI agents and agentic workflows
- Understand the difference between stateless and stateful AI systems
- Build AI agents using Koog and Kotlin
- Implement tool calling and structured outputs
- Explore memory and contextual reasoning
- Integrate AI agents with external systems and APIs
- Explore how event streams can serve as long-term memory and context
- Build small autonomous workflows around realistic business domains
- Discuss reliability, observability, and architectural trade-offs in AI systems
- Understand the role of semantic domain events in AI reasoning
Participants will leave with a practical understanding of how modern AI agents can be integrated into real software systems using robust architectural principles.
Prerequisites
Participants should have:
- Basic Kotlin or Java development experience
- Basic understanding of APIs and backend systems
- Curiosity about AI systems and autonomous agents
- Prior experience with LLMs or AI frameworks is not required.
Oliver Zihler is a dedicated Software Crafter specialising in Domain-Driven Design, Event Sourcing, collaborative modelling, and effective software development. His current focus lies in leveraging software architecture and business semantics to improve AI reasoning and AI-assisted development. Oliver actively organises Tech Excellence meetups and conferences, fostering community learning and innovation. At Codeartify, he serves as a technical trainer, software engineer, and architect, guiding teams to deliver robust software solutions.
Alina Liburkina is Software Craftress and CEO of Codeartify GmbH. She is a technical trainer, software engineer and architect, and (IT) event organizer passionate about DDD, Refactoring, Hexagonal and Clean Architecture. She is a co-organizer of an international conference and meetups TechExcellence. Moreover, she promotes and introduces XP techniques in the teams she works with. She loves to gather and share her knowledge with others through pair or mob programming, presentations or hands-on workshops.