Agentic Engineering & ToolingHands-on Lab120min
Building Production-Ready Agentic Systems with LangChain4j and Quarkus
Hands-on lab building a production-ready agentic AI app with LangChain4j and Quarkus. Learn to integrate tools via MCP/A2A, add reusable skills, guardrails, resilience, and testing. Gain practical patterns for reliable, observable, secure, and testable agent workflows, leaving with a working enterprise-grade application.
talk.summaryAiDisclaimer
Mario FuscoIBM
Georgios AndrianakisIBM
Kevin DuboisIBM
Agentic AI demos are easy. Building agentic systems that are reliable, observable, secure, testable, and ready for production is where the real challenge begins.
In this hands-on lab, you'll build an enterprise-grade agentic AI application from the ground up using LangChain4j and its Quarkus extension. Along the way, you'll learn how to connect remote tools and agents through emerging interoperability standards such as MCP and A2A. You'll also explore how to encapsulate business capabilities as reusable skills, enforce governance through guardrails, and implement resilience patterns such as fault tolerance, retries, and persistence to ensure reliable execution of long-running agent workflows.
Finally, we'll cover one of the most overlooked aspects of agentic development: testing. You'll learn practical techniques for validating agent behavior, mocking tools and models, and building automated tests that provide confidence before deployment.
By the end of the lab, you'll leave with a complete, working agentic application and a set of proven patterns for building AI systems that can move beyond prototypes and into production. Note that this lab will be based on the last part of a 3-sections workshop, but if you lack any prior knowledge you will be also allowed to work on the former 2 parts and proceed at your own pace.
In this hands-on lab, you'll build an enterprise-grade agentic AI application from the ground up using LangChain4j and its Quarkus extension. Along the way, you'll learn how to connect remote tools and agents through emerging interoperability standards such as MCP and A2A. You'll also explore how to encapsulate business capabilities as reusable skills, enforce governance through guardrails, and implement resilience patterns such as fault tolerance, retries, and persistence to ensure reliable execution of long-running agent workflows.
Finally, we'll cover one of the most overlooked aspects of agentic development: testing. You'll learn practical techniques for validating agent behavior, mocking tools and models, and building automated tests that provide confidence before deployment.
By the end of the lab, you'll leave with a complete, working agentic application and a set of proven patterns for building AI systems that can move beyond prototypes and into production. Note that this lab will be based on the last part of a 3-sections workshop, but if you lack any prior knowledge you will be also allowed to work on the former 2 parts and proceed at your own pace.
Mario Fusco
Mario is a senior principal software engineer at IBM working as Drools project lead. Among his interests there are also high performance systems and generative AI, being an active contributor of widely adopted projects like Quarkus and LangChain4j. He is also a Java Champion, the JUG Milano coordinator, a frequent speaker and the co-author of "Modern Java in Action" published by Manning.
Georgios Andrianakis
Georgios works for IBM as a Senior Principal Software Engineer and is currently one of the most active contributors to Quarkus, where he works in all sorts of areas, including but not limited to LangChain4j, RESTEasy Reactive, Spring compatibility, Kubernetes support, testing, Kotlin, and more.
He is also an enthusiastic promoter of Quarkus who never misses a chance to spread the Quarkus love!
He is also an enthusiastic promoter of Quarkus who never misses a chance to spread the Quarkus love!
Kevin Dubois
Kevin Dubois is a software architect and platform engineer with a career spanning over 20 years. He is often featured as a keynote speaker at conferences around the world where he shares his experience and knowledge about cloud native & AI software development, developer experience, open source and Java. Kevin is also an author and Java Champion. He currently works as a Senior Principal Developer Advocate at IBM, and is Technical Lead for the CNCF Developer Experience Technical Advisory Group as well as an ambassador for the Agentic AI Foundation.