Free Course
AI Engineering for
Java Developers
A hands-on, story-driven course that takes you from zero AI knowledge to shipping production-ready AI features with Spring AI. One real project, eight modules, no data science background required.
The story behind this course
Meet Dev — a mid-level Java developer at an e-commerce startup who gets asked to add AI features to the platform with no prior AI experience. Every module follows Dev through a real challenge, with real Spring AI code and a working result at the end. By Module 7, Dev ships a production-ready AI support assistant. By the end of the course, so will you.
What you will build
🔍 RAG-powered Q&A
Answers product and policy questions from real company data, not hallucinations
💬 Conversation memory
Remembers what was said earlier in the session across multiple turns
⚡ Live tool calling
Checks real-time order status by calling your platform's own APIs
🛡️ Production-ready
Tracing, cost controls, testing, safety guardrails, and error handling
Prerequisites
- ✓ Comfortable with Java 17+ (we use Java 21 features like records)
- ✓ Experience building Spring Boot REST APIs
- ✓ Basic familiarity with Maven and YAML configuration
- ✓ An OpenAI API key or Ollama installed locally (Module 2 covers both)
- ✗ No prior AI, ML, or data science experience needed
Course Modules
The New World
AvailableUnderstand the AI engineering landscape, what changed, and what we build across the course.
AI Concepts Every Java Developer Must Know
AvailableBuild mental models for LLMs, tokens, context windows, and prompt engineering before writing any code.
- 01 How LLMs work — a developer's mental model (no PhD required)
- 02 Tokens and context windows — what every developer must understand
- 03 Temperature, top-p, and model parameters — what to actually set
- 04 Choosing an AI model for your Java application — OpenAI, Anthropic, or local
- 05 Prompt engineering basics every developer needs before writing any code
First Contact — Spring AI Setup and Your First LLM Calls
AvailableGet Spring AI running, make real LLM API calls, and build your first AI-powered endpoint.
- 01 Setting up Spring AI in a Spring Boot project — step by step
- 02 Understanding Spring AI's ChatClient — the heart of every AI call
- 03 Prompt templates in Spring AI — stop hardcoding your prompts
- 04 Getting structured JSON responses from LLMs in Spring AI
- 05 Streaming LLM responses in Spring AI for a better user experience
Data and Embeddings — Teaching the AI to Understand Your Content
AvailableUnderstand embeddings, set up a vector database, and enable semantic search over your own data.
- 01 What are embeddings? A practical explanation for Java developers
- 02 Vector databases explained — why regular databases are not enough for AI
- 03 Setting up pgvector with Spring AI — store and search embeddings in PostgreSQL
- 04 Embedding and storing documents with Spring AI — a step-by-step guide
- 05 Semantic search in Spring AI — find by meaning, not by keyword
RAG — Teach the AI About Your Business
AvailableBuild a complete RAG pipeline that grounds LLM answers in your company's real data.
- 01 What is RAG and why your AI app almost certainly needs it
- 02 Building your first RAG pipeline with Spring AI
- 03 Chunking strategy in RAG — the decision that silently kills answer quality
- 04 Building a document Q&A chatbot with Spring AI and RAG
- 05 Improving RAG quality — reranking and hybrid search
Memory — Conversations That Actually Make Sense
AvailableAdd conversation memory so the AI assistant maintains context across multiple turns.
Agents and Tools — AI That Takes Action
AvailableBuild an AI agent that calls Java methods to fetch live data and reason over the results.
- 01 What is an AI agent? Moving beyond single LLM calls
- 02 Function calling in Spring AI — let the LLM use your Java methods
- 03 Building an AI agent that checks order status — a step-by-step example
- 04 Combining RAG and tool calling in one Spring AI agent
- 05 AI agent patterns — when to use simple chains, RAG, or full agents
Production — Shipping AI Features Safely
AvailableAdd observability, cost controls, tests, guardrails, and error handling to go live with confidence.
- 01 Observability for AI applications — tracing and logging LLM calls in Spring Boot
- 02 Controlling AI costs in production — token budgets, caching, and model selection
- 03 Testing AI features — how do you test something non-deterministic?
- 04 Safety and guardrails for AI apps — protecting users and your system
- 05 Error handling for AI apps — rate limits, timeouts, and fallback strategies
- 06 Deployment and configuration best practices for AI-powered Spring Boot apps
Advanced Topics — Beyond the Basics
AvailableLocal models with Ollama, multimodal AI, LangChain4j comparison, and your next learning steps.
Ready to start?
Module 0 is live. No sign-up required — just read, code, and build.
Begin the course →