Season 1 is live — 20 deep tutorials covering Spring AI, LangChain4j, RAG, Agents and MCP. Each with an interactive flowchart, step-by-step bootcamp guide, real-world scenario and complete GitHub project. New seasons ship regularly.
Click any node to see what it does, why it matters, real input/output, and a code example. Watch data animate through the system.
Accordion steps with beginner explanations, folder structures, full code, common mistakes, testing commands and expected output.
Every topic links to a GitHub repo with one-command setup. Clone → add API key → run. Real Spring Boot, not snippets.
Topics 1–5 completely free. Pro topics $4.99 each. Advanced $9.99 each. New seasons added regularly — star on GitHub to get notified.
How AI models receive and respond to requests
System, user and assistant roles — craft effective prompts
Token-by-token SSE streaming with Spring WebFlux
Map LLM responses directly to Java POJOs
Interface-based AI proxies — the production Java pattern
Give LLMs the ability to call your Java methods
Per-user persistent memory with Redis
How text becomes vectors — enabling semantic search
Store, index and search embeddings at scale with pgvector
Complete 6-step Retrieval-Augmented Generation
Hybrid search, re-ranking, HyDE and parent-child chunks
Reasoning + Acting loop — autonomous multi-step agents
Stateful workflows with graph-based orchestration
Build MCP servers that any LLM can call
Orchestrator + specialist agents in parallel
Retry, circuit breaker, fallback and caching for AI services
Track, optimize and cap AI spend in production
Trace every AI call — latency, cost, quality in Grafana
Measure faithfulness, relevance and quality in CI/CD
We're building the next set of deep-dive topics. Star the repo to get notified when they drop.
When to fine-tune a model vs. use RAG — decision framework, cost analysis, and hands-on comparison with Spring AI.
Defend your AI app against prompt injection, jailbreaks, and data leakage. OWASP LLM Top 10 with Spring Boot examples.
Unit testing LLM behaviour, mocking AI responses, contract testing, and automated regression suites for AI features.
Containerise with Docker, deploy to Kubernetes, zero-downtime AI model updates, and blue-green deployments.
Enterprise deployment on Azure OpenAI and AWS Bedrock. Feature flags, multi-region fallback, and compliance.
Route requests across multiple models, enforce policies, centralise auth and rate limiting. Build your own AI gateway.
16 essential AI design patterns — how each works, when to use it, and how to implement it in Spring Boot microservices. Flow diagrams, production code, real project scenarios, and common pitfalls.
No subscriptions. Buy individual topics or save big with bundles.