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.

#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.