Quarkus at Jfokus 2026

[insectengine]

Event Description: Jfokus is all about developers! Java SE & Java EE, Frontend & Web, GenAI and AI, Continuous Delivery & DevOps, Cloud & Big Data, Future & Trends, Alt.JVM Languages, Agile development. And Norse gods...

Date: February 2-4, 2026
Location: Stockholm, Sweden
Event Type: In Person

https://www.jfokus.se/

Sessions

Session: Did you really get better?
Speaker(s): Eric Deandrea
Date/Time: Monday, February 2nd at 11:00 - 12:30 in Room C3
Abstract: Testing is hard, which is why developers tend to avoid it. Testing non-deterministic things is even harder, which is unfortunate, since we're all writing AI-infused applications, and AI models are notoriously non-deterministic. What happens when the applications start using advanced features, such as RAG, tools, and agents? How do you test these applications? There must be some tools, technologies, and practices out there that can help, while not costing your organization lots of money! Join Java Champions Oleg & Eric in this session as they revisit a topic they debuted at JFokus last year. The AI landscape changes at a breathtaking pace, so what new capabilities and strategies have come along in the last year? Hopefully by the end of the presentation you will be able to answer the question "If I change my model/prompt/application, did I get better or worse"?

Session: From LLM orchestration to autonomous agents: Agentic AI patterns with LangChain4j
Speaker(s): Mario Fusco & Kevin Dubois
Date/Time: Monday, February 2nd at 13:20 - 17:00 in Room 23
Abstract: The late few months have seen the rapid evolution of LLMs from passive completion engines, only good for generic chatbots, to components of a more complex, programmatically defined, workflow and finally into active and autonomous elements capable of reasoning, planning, and taking actions. But moving from basic prompt engineering to truly autonomous systems requires a new class of design patterns and possibly a framework allowing to implement those patterns and put them at work in a convenient and effortless way. In this deep dive, we will explore the architecture and implementation of agentic AI using LangChain4j, a Java-native framework for building LLM-powered applications. You’ll learn how to move beyond the plain usage of a standalone LLM to design intelligent, modular agents capable of dynamic decision-making, memory retention, tool usage, RAG, MCP and A2A integration and multi-step goal execution. After having covered the core concepts of agentic AI, we will guide you in incrementally building and testing an agentic system from scratch using LangChain4j and Quarkus, backed by real-world examples and live coding. Whether you're exploring agentic AI for task automation, intelligent assistants, or decision-support systems, this session will give you the practical tools and architectural understanding to build robust and maintainable autonomous agents in Java.

Session: How Java, standards, and community helped education equality
Speaker(s): Richard Fichtner
Date/Time: Tuesday, February 3rd at 11:00 - 11:50 in Room C1
Abstract: How do you develop a highly scalable and secure platform for over 180,000 elementary school children with a small team – and under the strictest data protection requirements? The answer: with modern Java technology, a strong open source ecosystem, and a community that sticks together. In this case study, Stefan Böhringer (University of Regensburg) and Richard Fichtner (XDEV Software GmbH) provide insights into the BYLES project, Germany's largest digital reading screening program. They show how Quarkus, Jakarta EE, and Keycloak were used to create a robust, maintainable solution – without any reactive overhead, but with pragmatic, understandable Java code. What you will take away from the talk: How to set up projects with modern Java securely and scalably – even with a small team. How Java projects can grow through strong communities (JUGs!) and buddy approaches. Why standards often scale better than “hype.” How pragmatic technology decisions solve real problems. A talk for everyone who has to master real projects – not just on a greenfield site, but in real life.

Session: Introduction to Verifiable Credentials
Speaker(s): Sergey Beryozkin
Date/Time: Tuesday, February 3rd at 11:00 - 11:50 in Room C3
Abstract: Verifiable Credentials is the next big thing in the digital identity security that will allow users to provide cryptographically protected, verifiable documents containing such data as driving licenses, certificates, degrees and medical reports to services that require them, restricting when necessary how much information can be provided. In this session, Sergey Beryozkin will provide an overview of the Verifiable Credentials standardization process, explain how Verifiable Credentials are issued, presented and verified, and demonstrate how a Quarkus application can login users using an authorization code flow with an OpenId Connect provider such as Keycloak and get access to the verifiable credential.

Session: Agentic AI Patterns
Speaker(s): Mario Fusco & Kevin Dubois
Date/Time: Tuesday, February 3rd at 16:00 - 16:50 in Room A4
Abstract: There is no universally agreed definition of what an AI agent is. In practice though, several patterns are emerging. These patterns demonstrate the coordination and integration of multiple AI services to build sophisticated Agentic AI systems capable of handling intricate tasks. These Agentic Systems architectures can be grouped in 2 main categories: workflows, where LLMs and tools are orchestrated through predefined code paths, and agents, where LLMs dynamically direct their own processes and tool usage, maintaining control over how they execute tasks. Testing these Agentic Systems architectures is a big challenge for the adoption in mission critical scenarios. This is mainly due to their not completely deterministic nature. The goal of this talk is to give a theoretical overview of Agentic AI in general and these patterns in particular. We will discuss their differences and range of applicability and show with practical examples how they can be easily implemented and tested. We’ll use Quarkus and its LangChain4j extension, but the concepts are universal.

Session: Healthy Geeks, Better Code: Lessons from Fitness and AI
Speaker(s): Markus Eisele & Sergey Beryozkin
Date/Time: Tuesday, February 3rd at 16:00 - 16:50 in Room C1
Abstract: Being a software geek often means working long hours, late nights, and weekends. The result is tiredness, stress, and low energy that makes it harder to enjoy building software. But staying fit can help you feel better, think clearer, and even be more effective at your job.

In this talk, Marc Nuri, Markus Eisele and Sergey Beryozkin will share their own fitness stories and how they found balance between coding and staying healthy. You will see how small steps in fitness can improve both your health and your productivity. We will also show a live demo of the Quarkus LangChain4j Fitness Adviser, an AI service that uses Strava activity data together with Google Gemini to give fitness advice. It is a fun example of how modern AI tools can be used in a positive and practical way.