Building AI agents with Structured Outputs, Function Calling, and MCP

This session covers building autonomous AI agents in Java using LangChain4j’s new agentic module, structured outputs via JSON schemas, function calling from AI models, and the MCP protocol for LLM communication. Practical demos use OpenAI’s Java SDK to showcase these capabilities.

Julien DuboisMicrosoft

talkDetail.whenAndWhere

Thursday, October 9, 13:50-14:40

Room 6

talks.description

AI agents are programs that can act autonomously: to do this, they must be able to communicate programmatically with an LLM and perform actions.

In this session, we will explore:

The new "agentic" module from LangChain4j: how to build AI agents in Java and orchestrate them with a nice API
Structured Outputs: how to require an LLM to respond following a JSON schema, allowing to map the result to Java objects
Function Calling: how to define and call Java functions from within an AI model
MCP: the new protocol that standardizes how LLMs communicate with different data sources and tools

We will use the code, demos, and documentation I created to implement these features in LangChain4j using OpenAI’s brand-new Java SDK.

agents

llm

protocol

java

talks.speakers

Julien Dubois

Microsoft

France

Julien Dubois manages the Java Developer Relations team at Microsoft.
He is known as the creator and lead developer of the JHipster project, and as a Java Champion. In the past 25 years, Julien mainly worked with the Java and Spring technologies, leading technical teams for many different customers across all industries. As he loves sharing his passion, Julien wrote a book on the Spring Framework, spoke at more than 200 international conferences, and created several popular Open Source projects.

talks.watchOnYoutube

comments.title

comments.speakerNotEnabledComments