World Congress 2025 Aug 20, 2025 Session details

Agentic AI Systems for Critical Workloads

Mario Fusco

Move your generative AI prototypes from experimental notebooks into enterprise-grade Java. Discover how to build, orchestrate, and test autonomous agent workloads using LangChain4j and Quarkus.

Pause
Mute Enter Fullscreen
#1 about 2 min

Choosing Java over Python for enterprise AI integration

Java provides transaction management, observability, and security capabilities necessary for enterprise-grade generative deployments.

#2 about 2 min

Core components of autonomous agentic AI systems

Agentic systems combine a foundational model with tools, memory access, and orchestration to perform tasks with minimal human intervention.

#3 about 2 min

Workflow patterns versus independent agent architectures

Developers can orchestrate tasks using programmatically defined workflows or rely on independent agents that coordinate themselves.

#4 about 3 min

Navigating model selection and hallucination challenges locally

Local model deployment requires significant trial and error for prompt engineering and managing occurrences like tool hallucination.

#5 about 3 min

Implementing sequential and parallel agent workflow pipelines

Chaining agents sequentially allows progressive task refinement, while parallel execution effectively splits independent domains before combining results.

#6 about 3 min

Utilizing the mixture of experts routing pattern

A central router agent evaluates input contexts to accurately delegate complex requests to specialized domain experts.

#7 about 6 min

Testing strategies for non-deterministic AI system outputs

Validating probabilistic responses involves building classification functions using evaluation strategies like cosine distance or LLM-as-a-judge approaches.

#8 about 6 min

Transitioning to autonomous multi-agent task execution

Replacing programmatic routers with pure agentic capabilities offers greater dynamic flexibility at the expense of predictable debugging.

#9 about 5 min

Optimizing tool invocation and external API retrieval

Agents autonomously integrate external web services and internet searches to answer complex queries lacking initial context.

#10 about 2 min

Future API protocols and programmatic system structures

Upcoming integration frameworks like Google's A2A protocol will enable comprehensive logical looping and sequence building for agent orchestration.

Matching moments

2:54 min

Utilizing Java frameworks to interface with AI models

Mary Grygleski Mary Grygleski · LIVE

1:32 min

Building autonomous functions with conversational agent frameworks

Modood Alvi · World Congress 2025

3:36 min

Overview of generative AI and the presentation agenda

juarezjunior juarezjunior · World Congress 2024

2:02 min

Shifting focus from isolated models to enterprise AI systems

Mohak Chadha Mohak Chadha · World Congress 2026 Europe

2:49 min

Balancing AI-assisted workflows with fully autonomous system agents

Avani Prabhakar Avani Prabhakar +3 · World Congress 2026 Europe

2:56 min

Integrating local AI models into Java Quarkus applications

Cedric Clyburn Cedric Clyburn · World Congress 2024

Upcoming sessions on this topic

Open session

World Congress 2026 North America

September 24, 2026 · 17:30–18:00

Stage 6

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

September 25, 2026 · 14:50–15:20

Stage 6

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

September 25, 2026 · 15:45–15:55

Outdoor Stage

Closing the Visibility Gap: Lessons from Safety Critical Agentic Systems

Vivek Pandit

Frontier AI Lead at Turing

Vivek Pandit
Open session

World Congress 2026 North America

September 23, 2026 · 13:15–15:15

Stage 9

DeepAgents: Build Multi-Agent AI Systems That Actually Work

Anagha Rumade, Anjana Umapathy, Apoorva Jaiswal

Anagha Rumade
Anjana Umapathy
Apoorva Jaiswal
Open session

World Congress 2026 North America

September 25, 2026 · 11:40–12:10

Stage 2

Reinventing Testing Practices in the AI Era

Eric Deandrea

Java Champion & Senior Principal Software Engineer, IBM

Eric Deandrea
Open session

World Congress 2026 North America

September 24, 2026 · 11:40–12:10

Stage 4

Taming Rogue Agents: Observability-Driven Evaluation for Production Reliability

Anagha Rumade, Anjana Umapathy, Apoorva Jaiswal

Anagha Rumade
Anjana Umapathy
Apoorva Jaiswal