SecurityHands-on Lab120min
Building secure AI agents with Quarkus LangChain4j
This hands-on workshop teaches participants to build and secure AI agents using Quarkus LangChain4j. Attendees will set up projects, implement security against prompt injection, configure authentication, and add monitoring. Suitable for all experience levels, the session includes practical exercises for integrating and safeguarding AI agents in enterprise applications.
Willem Jan GlerumLunatech
Radek KargulLunatech
talkDetail.whenAndWhere
Monday, October 6, 16:50-18:50
BOF 1
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.
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.
Willem Jan Glerum
Willem Jan is a Principal Software Engineer at Lunatech who loves building cloud software and contributing to open source. He's all about writing quality code and finding ways to automate anything. Willem Jan has been working with Quarkus since the beginning and enjoys making sure his applications are both simple and secure. On weekends, you won't find him behind a keyboard - he's either out enjoying nature or volunteering with his local scout group.
Radek Kargul
Radek has a background in Software Engineering, ML, and AI from his undergraduate and postgraduate studies (including hands-on experience) at TU Delft. He recently graduated with his Master’s Thesis in Explainable AI (XAI) for large language models (LLMs). He sees great potential in integrating and understanding how ML/AI can be integrated into software.
comments.speakerNotEnabledComments