Building secure AI agents with Quarkus LangChain4j

In this hands-on workshop, participants will learn how to create and secure AI agents leveraging Quarkus LangChain4j. As AI agents are used more and more within enterprise applications, securing them has become a critical concern. You for example don't want your agent to drop your database, execute privileged actions or leak your sensitive customer data by accident. Workshop participants will: • Set up a Quarkus project with LangChain4j extension

• Build a basic AI agent that can interact with business applications

• Implement security measures to prevent prompt injection attacks

• Configure authentication and authorization for AI agent actions

• Structure the application for maintainability and security

• Add appropriate monitoring and audit logging

Each participant should bring their own laptop with JDK 21, Maven, Ollama and Podman Desktop installed. The workshop will include step-by-step instructions, code examples, and exercises to reinforce learning. This workshop is suitable for developers new to AI and more experienced engineers who want to learn how to include and secure AI agents in their projects. Some basic knowledge of Java and Quarkus is helpful but not required.