Mario Fusco

Agentic AI Systems for Critical Workloads

Traditional unit tests are useless against agentic AI. Learn to build and test reliable systems for critical Java workloads using a new probabilistic framework.

Agentic AI Systems for Critical Workloads
#1about 2 minutes

Why Java is a strong choice for enterprise AI applications

LangChain4j brings AI capabilities to Java, which is ideal for building enterprise-grade systems that require transactions, observability, and security.

#2about 3 minutes

Understanding the core components of agentic AI systems

Agentic AI systems consist of a core LLM, tools, memory, and orchestration, with the key distinction being between programmatic workflows and autonomous agents.

#3about 3 minutes

Practical challenges when building with local LLMs

Developing with local LLMs involves significant trial and error in model selection and prompt engineering, and requires handling issues like tool hallucination.

#4about 5 minutes

Building predictable AI systems with the workflow pattern

The workflow pattern uses programmatic code to orchestrate specialized agents in sequences, parallel tasks, or a mixture of experts for predictable outcomes.

#5about 6 minutes

Strategies for testing non-deterministic AI applications

Testing LLM-based systems requires new approaches like using sample-based evaluation, custom scoring functions, and strategies such as cosine distance or LLM-as-a-judge.

#6about 7 minutes

Comparing the workflow pattern to the agent pattern

While workflows offer predictability and easier debugging, the agent pattern provides greater flexibility by allowing agents to autonomously decide which tools to use.

#7about 3 minutes

Creating advanced agents that use external tools

Agents can autonomously combine LLM capabilities with external tools like web services or search engines to accomplish complex, multi-step tasks.

#8about 2 minutes

The future of agent orchestration in LangChain4j

Upcoming features include integration with the AITO protocol and a new programmatic API for composing complex agent interactions like sequences and loops.

Related jobs
Jobs that call for the skills explored in this talk.

Featured Partners

Related Videos

Create AI-Infused Java Apps with LangChain4j29:18

Create AI-Infused Java Apps with LangChain4j

Daniel Oh, Kevin Dubois

AI Agents Graph: Your following tool in your Java AI journey30:38

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

Alex Soto

Beyond Chatbots: How to build Agentic AI systems24:22

Beyond Chatbots: How to build Agentic AI systems

Philipp Schmid

On a Secret Mission: Developing AI Agents29:03

On a Secret Mission: Developing AI Agents

Jörg Neumann

Infusing Generative AI in your Java Apps with LangChain4j32:02

Infusing Generative AI in your Java Apps with LangChain4j

Kevin Dubois

Supercharge Agentic AI Apps: A DevEx-Driven Approach to Cloud-Native Scaffolding31:02

Supercharge Agentic AI Apps: A DevEx-Driven Approach to Cloud-Native Scaffolding

Daniel Oh

Agents for the Sake of Happiness39:11

Agents for the Sake of Happiness

Thomas Dohmke

Agentic AI - From Theory to Practice: Developing Multi-Agent AI Systems on Azure26:35

Agentic AI - From Theory to Practice: Developing Multi-Agent AI Systems on Azure

Ricardo

From learning to earning

Jobs that call for the skills explored in this talk.