AI

Enterprise AI on the JVM

Despite what you may have heard, the JVM is where you want to build if you are serious about Enterprise AI. We will teach you to embrace software engineering discipline to build safe AI in Kotlin and Java that generates value for your organization.

Description

Every organization wants to make AI work, but FOMO is not a strategy. Study after study shows even the biggest companies struggle with it. The reasons pile up: no clear business objectives, no data strategy, and no appreciation that context and structure are essential to enterprise AI at scale.

Python is great for computation and experimentation, which makes it a fine fit for machine learning, but it falls short on context and structure. JVM languages excel there: Java, which has dominated the enterprise for decades, and more recently Kotlin. Enterprise AI on the JVM teaches you to build robust, production-grade AI at scale on a proven, reliable platform.

What makes this course different

This is one of the first courses of its kind, because Python enjoyed a first-mover advantage in the shift from machine learning to AI. Only recently have businesses started to hit the limits of Python at enterprise scale, the same limits that held it back for decades while Java, C#, and more recently TypeScript dominated. Enterprises have invested billions in JVM applications, and the JVM now offers powerful options for enterprise AI that build on those investments.

Enterprise AI on the JVM opens with the concepts of AI, the software engineering principles we have honed for decades that production AI depends on, and the strengths the JVM brings over Python for the enterprise. You then learn four frameworks that bring these ideas together:

  • Spring AI
  • LangChain4j
  • Embabel
  • Koog
Each framework works at a different level of abstraction with its own design philosophy, so you learn what they share and how to choose the right one for what you are building. The course closes with a short discussion of agent architecture patterns.

When you finish, you will be an expert at building AI systems in production at scale, and your skills will carry across stacks. You will build better-architected AI in TypeScript, C#, and even Python when you have to.

Collaborating software engineers
What You'll Learn

Course Syllabus

About 21 hours total across seven lessons of 1 to 4 hours each. Spread them across a week or combine them into multi-lesson blocks.

1

Lesson 1: Principles of AI

4 hours

Master the vocabulary of AI, from tokens and prompts to RAG, agents, tools, MCP, and evals.

  • Large Language Models
  • Tokens: The Currency of AI
  • Prompts and Prompt Templates
  • Reasoning, Inference, and Thinking
  • Reinforcement Learning
  • Context Engineering
  • Embeddings
  • Retrieval Augmented Generation (RAG)
  • Agents
  • Tools
  • Model Context Protocol (MCP)
  • Guardrails
  • Caching
  • Evals
2

Lesson 2: AI in the Enterprise

3 hours

See why the JVM beats Python for enterprise AI through type safety, structure, and engineering discipline.

  • The Problem with Python
  • The Dominance of Java and Power of Kotlin
  • Type Safety
  • Domain-Driven Design
  • Loose Coupling
  • Patterns in the Enterprise
  • Security and Validation
  • Observability
  • Testability
  • AI Only When Necessary
3

Lesson 3: Spring AI

4 hours

Build, test, and deploy production AI with Spring AI, from chat clients to tools and guardrails.

  • A Simple Chat Client
  • Advisors
  • Structured Output Converters
  • Multimodality
  • Memory
  • RAG
  • Tool Calls
  • MCP
  • Evals
  • Guardrails
  • Observability
  • Developing with Docker Compose
  • Testing
  • Deployment
4

Lesson 4: Langchain4j

3 hours

Build the same production AI with LangChain4j and its AI Services abstraction.

  • A Simple Chat Client
  • AI Services
  • Multimodality
  • Memory
  • RAG
  • Tool Calls
  • MCP
  • Evals
  • Guardrails
  • Observability
  • Testing
  • Deployment
5

Lesson 5: Building Agents with Embabel

3 hours

Build planning agents with Embabel and its goal-oriented action planning.

  • Where Embabel Excels
  • Embabel Concepts
  • Goal-Oriented Action Planing: Embabel's Killer Feature
  • Your First Agent
  • Agent Flows with Annotations
  • Agent Flows with DSL
  • Parallelism
  • Using Tools and MCP
  • Testing
  • Observability
  • Deployment
6

Lesson 6: Building Agents with Koog

3 hours

Build multiplatform agents with Koog and its strategy graphs.

  • Where Koog Excels
  • Koog Concepts
  • Multiplatform Deployment: Koog's Killer Feature
  • Your First Agent
  • Strategy Graphs
  • Parallelism
  • Using Tools and MCP
  • Testing
  • Observability
  • Deployment
7

Lesson 7: Agent Patterns

1 hour

Apply longstanding software patterns to agent architecture.

  • Why Patterns Matter
  • Applying Longstanding Patterns to AI
Meet Your Guide

Your Instructor

Course instructor Neil Chaudhuri

"AI is changing the game and fast, and even the biggest companies in the world are having trouble making AI work for them. I want to help you harness AI in a serious way to be productive and build great things."

Neil Chaudhuri
Course Instructor

Want to transform your business?Get in touch today!

Partner with Vidya to modernize your technology, empower your teams, and accelerate your mission.

Contact Us