Uploaded April 2026 | Updated September 2026, 2 weeks ago
#VDZ26
Developing AI applications today goes beyond simple single-model interactions. We're seeing a shift towards agentic AI systems, where multiple specialized agents work together, each capable of independent reasoning. The real challenge for an AI architect lies in orchestrating these agents to collaborate effectively towards a common goal.
Given the diverse and complex tasks these systems handle, a "one-size-fits-all" approach to coordination just doesn't work. We'll explore the spectrum of agentic patterns, from reliable but rigid workflows to highly flexible, autonomous agent orchestration using LLMs, and everything in between.
Beyond just sequencing agents, effective communication is vital. Agents need a shared space to exchange results and enrich each other's contexts.
This talk will cover:
- The pros and cons of various agentic patterns.
- Practical demonstrations of how to combine these patterns using -LangChain4j and its Quarkus extension.
- How to leverage the provided infrastructure for agent collaboration.
- The flexibility to implement and seamlessly integrate your own custom agentic patterns.
#VDZ26
Developing AI applications today goes beyond simple single-model interactions. We're seeing a shift towards agentic AI systems, where multiple specialized agents work together, each capable of independent reasoning. The real challenge for an AI architect lies in orchestrating these agents to collaborate effectively towards a common goal.
Given the diverse and complex tasks these systems handle, a "one-size-fits-all" approach to coordination just doesn't work. We'll explore the spectrum of agentic patterns, from reliable but rigid workflows to highly flexible, autonomous agent orchestration using LLMs, and everything in between.
Beyond just sequencing agents, effective communication is vital. Agents need a shared space to exchange results and enrich each other's contexts.
This talk will cover:
- The pros and cons of various agentic patterns.
- Practical demonstrations of how to combine these patterns using -LangChain4j and its Quarkus extension.
- How to leverage the provided infrastructure for agent collaboration.
- The flexibility to implement and seamlessly integrate your own custom agentic patterns.
![[VDBUH2026] Victor Rentea - Kenote: AI Didn’t Replace You. It Promoted You!](https://i.ytimg.com/vi/5hVlf9_G71Q/mqdefault.jpg "[VDBUH2026] Victor Rentea - Kenote: AI Didn’t Replace You. It Promoted You!
We’ve always been rewarded for writing code, debugging systems, and mastering frameworks. But today, AI no longer just assists – it builds, analyzes, debugs, and reasons, so our role gets upgraded to shaping systems, taking decisions, and achieving outcomes. But as our attention moves away from code, how can we remain in control and keep the quality high? That’s the tension many senior engineers feel. This talk explores how AI agents can offload our chores, preserve our mental energy, and amplify our impact across the system—distilling lessons from early adopters of agentic engineering.
But this is not a talk about tools. It’s a talk about identity.
Because the real question today isn’t: “Will AI change my job?”
It’s: “Will I evolve fast enough to stay relevant?”")
