GenAI & BeyondGenAI & Beyond
Keynote20min
BEGINNER

Agent Orchestration with LangChain4J

Discover how langchain4j-agentic empowers Java developers to build robust, controllable agent workflows using patterns like sequential, looping, and parallel execution. Learn about supervisor agents, human validation, workflow composition, and context management—plus see live demos of scalable agent systems for practical automation and control.

Lize Raes
Lize RaesOracle

talkDetail.whenAndWhere

talks.scheduleTBD
Room 8
talks.roomOccupancytalks.noOccupancyInfo
talks.description
The agents are coming for you, Java developers! With langchain4j-agentic, you can combine AI (and non-AI) agents into powerful but controlled workflows. We’ll explore the core patterns: sequential, looping, conditional, and parallel, plus the supervisor pattern where agents decide for themselves which tasks to run. You’ll also see human validation strategies that keep your agent army in check.
Compound agents can wrap entire workflows into a single building block, while AgenticScope gives you control over context and a clear view of the call chain.
Live on stage, we’ll demo playful agent systems that scale from small tasks to complex automation. You’ll leave with a sense of what’s possible today, how to keep it under control, and how Java developers can shape the next rise of the agents.
patterns
agents
automation
workflows
talks.speakers
Lize Raes

Lize Raes

Oracle

Switzerland

Lize Raes loves helping developers to bring AI into real-world applications. As Developer Advocate for Java + AI at Oracle and collaborator at LangChain4j, she’s invested into making cutting-edge tech accessible and useful for developers. Her path has taken her from cochlear implant research to advising the Belgian government during COVID-19, to bioinformatics for drug development. Lize likes her projects hands-on and slightly unconventional, especially when they help make the world a bit better. Outside of work, you’ll find her behind the piano or in her woodworking atelier.

talkDetail.rateThisTalk

talkDetail.poortalkDetail.excellent

talkDetail.ratingNotYetAvailable

talkDetail.ratingAvailableWhenStarted

talkDetail.signInRequired

talkDetail.signInToRateDescription