WeAreDevelopers Logo WeAreDevelopers
Sign in
For You LIVE
World Congress 2025 • Aug 20, 2025 • Session details

AI Agents Graph: Your following tool in your Java AI journey

Alex Soto

Bloated prompts kill enterprise AI latency and ruin reliability. Discover how to build resilient, stateful multi-agent workflows in Java using LangGraph4j's graph-based execution.

Pause
Mute Enter Fullscreen
#1 about 2 min

Introduction to AI agents and enterprise complexity

Simple agents lack the capabilities needed to handle complex enterprise requirements.

#2 about 2 min

Choosing Java over Python for enterprise AI ecosystems

Java offers better energy efficiency, stable dependency management, and robust enterprise integrations compared to Python.

#3 about 3 min

Building AI interactions in Java with LangChain4j

LangChain4j simplifies connecting to large language models, applying prompt templates, and managing context memory.

#4 about 2 min

Enabling function calling and tooling for models

Tooling mechanisms allow language models to dynamically execute tasks like checking weather or sending emails.

#5 about 3 min

Demonstrating a naive theme park chatbot application

A basic AI application demonstrates using provided documentation and location context to answer specific user queries.

#6 about 4 min

Scaling challenges in basic context injection workflows

Overloading a single model with excessive context or relying on basic routing structures increases costs and limits maintainability.

#7 about 2 min

Managing complex workflows with LangGraph4j orchestration

Orchestrating multiple models and persistent checkpoints facilitates complex event-driven capabilities and human-in-the-loop interactions.

#8 about 3 min

Understanding graphs with nodes, edges, and state

Graph-based architectures represent execution steps as distinct nodes connected by conditional edges and sharing a global map holding iteration state.

#9 about 8 min

Executing stateful logic and pausing for human input

Defining checkpoints allows developers to pause node execution until a user manually injects necessary context into the shared state.

#10 about 7 min

Categorizing and processing emails using an AI graph

Specialized models collaborate across multiple conditional nodes to categorize emails, generate reliable replies, or perform web searches.

Matching moments

3:25 min

Constructing scalable AI solutions using LangChain and LangGraph

Julián Duque Julián Duque · WWC 2025

2:54 min

Utilizing Java frameworks to interface with AI models

Mary Grygleski Mary Grygleski · LIVE

3:36 min

Overview of generative AI and the presentation agenda

juarezjunior juarezjunior · WWC 2024

2:57 min

Comparing popular Java frameworks for AI integration

Timo Salm Timo Salm · WWC 2025

2:36 min

Exploring the core architecture and components of AI agents

Jörg Neumann Jörg Neumann · WWC 2025

2:02 min

Shifting focus from isolated models to enterprise AI systems

Mohak Chadha Mohak Chadha · WWC Europe 2026

More from World Congress 2025

GenAI Security: Navigating the Unseen Iceberg thumbnail
24:33
10 months ago

GenAI Security: Navigating the Unseen Iceberg

Maish Saidel-Keesing

Behind the Code: How Women Are Powering the Future of AI thumbnail
30:28
12 months ago

Behind the Code: How Women Are Powering the Future of AI

Alexandra Wudel, Laura Moritz, Madalina Florean

The AI Hype Filter: What’s Real, What’s Investable, What’s Noise? thumbnail
28:12
12 months ago

The AI Hype Filter: What’s Real, What’s Investable, What’s Noise?

Justus Lumpe, Konstantin Vinogradov, Nils Eiteneyer, Stephan Wirris

AI in Leadership: How Technology is Reshaping Executive Roles thumbnail
28:19
12 months ago

AI in Leadership: How Technology is Reshaping Executive Roles

Bernd Datler, Jasmin Kaiser, Jeff Hausmann, Sonja Alvarez

The AI-Ready Stack: Rethinking the Engineering Org of the Future thumbnail
28:09
12 months ago

The AI-Ready Stack: Rethinking the Engineering Org of the Future

Alex Laubscher, Jan Oberhauser, Keno Dreßel, Mirko Novakovic

AI Sovereignty: What Does It Take? thumbnail
29:13
12 months ago

AI Sovereignty: What Does It Take?

Boris Hecker, Clemens Wasner, Robin Hermann, Sonja Alvarez

Upcoming sessions on this topic

Open session

World Congress 2026 North America

DeepAgents: Build Multi-Agent AI Systems That Actually Work

Anjana Umapathy, Apoorva Jaiswal, Anagha Rumade

Anjana Umapathy
Apoorva Jaiswal
Anagha Rumade
Open session

World Congress 2026 North America

AI Agents are Only as Smart as their Context: Building a Real-Time Context Engine at Intuit

Bharat Patel

Lead Software Engineer at Intuit

Bharat Patel
Open session

World Congress 2026 North America

Look What Java Can Do Now: Live-Coding a GenAI MCP Server with the JAQ Stack

Suren Konathala

Senior Engineering Leader, Marketing & AdTech, AI GTM & Digital Experience Platforms, Java x AI

Suren Konathala
Open session

World Congress 2026 North America

No Single Model to Rule Them All: Building Resilient AI Agents Across Open & Closed LLMs

Emmanuel Acheampong

Senior Manager Developer Relations at Crusoe AI

Emmanuel Acheampong
Open session

World Congress 2026 North America

Closing the Visibility Gap: Lessons from Safety Critical Agentic Systems

Vivek Pandit

Principal Engineer at Cadence

Vivek Pandit
Open session

World Congress 2026 North America

When Agents Became Users: Rearchitecting Identity and Permissions for AI at Scale

Dor Cohen, Yoav Gal

Dor Cohen
Yoav Gal

Related videos

Building AI Applications with LangChain and Node.js thumbnail
26:42
WWC 2025 • 12 months ago

Building AI Applications with LangChain and Node.js

Julián Duque

Agentic AI Systems for Critical Workloads thumbnail
30:01
WWC 2025 • 12 months ago

Agentic AI Systems for Critical Workloads

Mario Fusco

Java Meets AI: Empowering Spring Developers to Build Intelligent Apps thumbnail
31:53
WWC 2025 • 12 months ago

Java Meets AI: Empowering Spring Developers to Build Intelligent Apps

Timo Salm

Building the Future of Java: AI Agents, MCP, and Next-Gen App Development thumbnail
31:58
WWC Europe 2026 • about 1 month ago

Building the Future of Java: AI Agents, MCP, and Next-Gen App Development

Daniel Oh

Building a Multi-Agent Orchestration Engine That Actually Follows the Rules thumbnail
29:01
WWC Europe 2026 • about 1 month ago

Building a Multi-Agent Orchestration Engine That Actually Follows the Rules

Hussein Jundi, Torsten Stiller

Beyond Chatbots: How to build Agentic AI systems thumbnail
24:22
WWC 2025 • 12 months ago

Beyond Chatbots: How to build Agentic AI systems

Philipp Schmid

Related articles

From learning to earning

Jobs that call for the skills explored in this talk.