Will there be Q&A sessions during the workshop?

Yes. Each session will have dedicated Q&A time, and you can also ask questions in the chat during the workshop.

What platform will be used?

The workshop will be hosted live on Airmeet.

How can I ask questions during the workshop?

You can use the chat or Q&A features during the session. A moderator will help manage and relay questions to Susanne.

Will I get access to slides, code samples, and exercises after the event?

Yes. All participants will receive the presentation slides, code examples, and any relevant resources after the event.

Will there be recordings of the event?

Yes. Recordings will be made available to all attendees so you can review the material at your own pace.

What happens if I cannot attend live?

You will still receive access to the recordings and materials so you can catch up later.

Building Reliable AI Agents with Java and LangChain4J

ByPackt Publishing Limited

Part of the Deep Engineering collection

Online event

Saturday, June 13 • 10:30 AM - 1:30 PM EDT

Overview

Move beyond simple pipelines and build reliable, production-ready AI agents in Java with decision-making, evaluation, and observability.

Most teams are experimenting with AI agents, but very few know how to make them reliable. In this hands-on workshop, you’ll learn how to build production-ready AI agents in Java using LangChain4J - starting from a simple pipeline and evolving it into an agentic system with decision-making, guardrails, evaluation, and observability. By the end, you won’t just have an agent - you’ll understand how to control, measure, and debug it.

Why Attend?

This workshop demonstrates how Java can be used to build reliable, production-ready AI applications for enterprise environments.

• Not sure when or how to use AI agents?
Learn how to move from deterministic pipelines to agent-based systems and apply them effectively.

• Want to use AI in Java without switching ecosystems?
Work with LangChain4J to integrate AI into familiar, enterprise-grade Java environments.

• Struggling to move beyond experimentation?
Gain a structured approach to designing agents that are reliable and production-ready.

• Looking for hands-on, practical experience?
Follow guided labs to build, test, and improve a working AI agent step by step.

What Will I Be Able to Do After This Workshop?

By the end of this workshop, participants will:

Understand the difference between deterministic pipelines and agent-based systems

Build a basic agent using LangChain4J in Java

Integrate LLMs as decision-makers (e.g. routing or evaluation)

Implement evaluation strategies to measure agent quality

Apply observability techniques to debug and monitor agent behavior

Learn how to build AI systems that are safe and production-ready

Who Should Attend?

Java software engineers – Developers working in Java who want to go beyond basic LLM integrations and learn how to build reliable, production-ready AI agents. This workshop shows how to evolve from simple RAG pipelines to structured agent-based systems using LangChain4J.

AI engineers and early adopters – Engineers experimenting met LLMs or RAG who want to add decision-making, guardrails, evaluation, and observability in Java. Learn how to turn prototypes into systems that are measurable, debuggable, and ready for real-world use.

Solutions architects and technical leads – Architects and leads who need to understand how AI agents behave in practice. Gain a clear, hands-on view of how agents are built, tested, and monitored, so you can better guide teams moving from experimentation to production.

Pre-Requisites

Basic Java knowledge

Familiarity with Maven/Gradle

IntelliJ IDEA (recommended)

No prior AI/LLM experience required

Tools & Technologies

Java

LangChain4J

(Azure) OpenAI / local LLM (optional)

Micrometer / OpenTelemetry (for observability demo)

Workshop Highlights

Live instruction with expert Q&A

Hands-on labs and code walkthroughs

Code snippets, templates, and reusable examples

Downloadable reference materials

Certificate of Completion

Optional follow-up resources or Slack access

Limited Seats. High Impact.

This is a live, interactive workshop with limited seats to maintain quality and hands-on depth.

Lineup

Susanne Pieterse

Good to know

Highlights

3 hours
Online

Refund Policy

Refunds up to 5 days before event

Location

Online event

Agenda

10:30 AM - 10:50 AM

Module 1 – Introduction & Mental Model

Susanne Pieterse

This opening session sets the foundation by clarifying what AI agents actually are beyond the hype. Through slides and discussion, participants will explore the differences between deterministic systems and agent-based systems, along with common pitfalls such as hallucination and unpredictability. The key takeaway is understanding that agents are not magic, they are systems built around decision loops.

10:50 AM - 11:10 AM

Module 2 – From Pipeline to Agent

Susanne Pieterse

In this live coding session, participants will start with a simple, prebuilt RAG pipeline and progressively refactor it into an agentic system. The focus will be on breaking down the pipeline into modular tools and introducing an orchestration layer. During the guided lab, participants will identify pipeline steps, convert them into reusable tools, and understand how structured components enable more flexible systems.

11:20 AM - 11:40 AM

Module 3 – Adding AI as Decision Maker

Susanne Pieterse

This module introduces the role of LLMs as decision-makers rather than just generators. Through live coding and explanation, participants will implement routing logic where the AI determines which tool to use. The session also covers prompt design for controlled behavior and introduces the concept of guardrails. In the guided lab, participants will build and test a simple routing agent with different inputs, reinforcing the idea that AI enables decision-making capabilities.

Frequently asked questions

Organized by

Packt Publishing Limited

Report this event