AI Integration: Building AI-Powered Java Apps (Day 2)

Introduction
The second day shifts to deeper technical integration. Participants work hands-on with local model deployment, RAG systems, tool calling, the Model Context Protocol (MCP), multi-agent workflows, and evaluation and observability techniques for AI-enhanced Java applications.

Detailed description

Day 2 dives into the technical side of integrating AI into Java applications. Where Day 1 focuses on building an effective personal workflow, Day 2 is about embedding AI capabilities directly into the software you build.

Participants work hands-on with local language model deployment using Ollama and vLLM, giving them control over model selection, cost, and data privacy. From there, we build RAG (Retrieval-Augmented Generation) systems in Java using LangChain4j and vector databases, enabling AI to work with your organisation’s own data and documents.

We then cover tool calling to connect AI systems to real-world services, and the Model Context Protocol (MCP) — the emerging standard for integrating AI agents with external tools and data sources using Spring AI and LangChain4j.

The day closes with multi-agent orchestration patterns and practical guidance on evaluation and observability, so you can measure and maintain the quality of AI-enhanced systems in production.

Prerequisites

Solid Java development experience and familiarity with REST APIs and modern frameworks. Experience with GitHub and modern IDEs is required. Day 1 of this training or equivalent experience with AI-powered development workflows is recommended.

Participants are expected to have access to the following tools for the hands-on portions of the day:

• IntelliJ with AI agent subscription
• OpenAI account
• Anthropic account
• Google Gemini account
• GitHub Copilot

Target audience
Designed for Java developers, architects, and tech leads who want to integrate AI capabilities directly into their applications. This day is particularly suited for those planning AI features in their products or building systems that leverage language models, RAG, or multi-agent workflows.

Learning goals

After completing this training, participants will be able to:

• Deploy and query local language models using Ollama and vLLM
• Build RAG systems in Java using LangChain4j and vector databases
• Implement tool calling and connect AI systems to real-world data and services
• Build and consume MCP servers with Spring AI and LangChain4j
• Design and orchestrate multi-agent workflows using sequential, parallel, loop, and conditional patterns
• Evaluate and observe AI system behaviour in production using OpenTelemetry and LLM engineering platforms

Topics covered

• Local model deployment with Ollama and vLLM
• Building RAG systems in Java
• Tool calling and connecting AI to real-world systems
• Model Context Protocol (MCP) with Spring AI and LangChain4j
• Multi-agent workflows and orchestration patterns
• Evaluation and observability with OpenTelemetry

Training outline

• Local model deployment with Ollama and vLLM (2 hours)
• Building RAG systems with Java and LangChain4j (2 hours)
• Tool calling: connecting AI to real-world systems (2 hours)
• Model Context Protocol (MCP) with Spring AI and LangChain4j (2 hours)
• Multi-agent workflows: sequential, parallel, loop, and conditional patterns (2 hours)
• Evaluation and observability with OpenTelemetry and LLM engineering platforms (1-2 hours)

Course format
This is an in-person classroom training that can be delivered at an OpenValue office or as an in-company training. This is Day 2 of the AI Integration for Java Developers training and can be followed as a standalone or combined with Day 1 for the full two-day package.

Certification
Participants receive a certificate of completion upon finishing the training.

Next steps
For more information about expanding your knowledge past this course, check out our entire training portfolio at www.openvalue.training or in your learning management system. Contact us at training@openvalue.nl for personal learning advice or customized on-demand training and just contact your OpenValue trainer during the training course.

Provided training material
Learning material with slides and exercises will be available for the participants.

About the trainers
Tom Wigleven is Principal Engineer at OpenValue. Mauro Palsgraaf is Senior Software Developer at OpenValue.

Note: This training can be given in Dutch or English at one of the OpenValue offices (Utrecht, Amsterdam, Rotterdam, Arnhem, Munich, Dusseldorf, Vienna, Zurich) or at your own location. Please contact us to discuss possibilities for a remote training and for training in German.