AI

In the previous article, we ran a Spring AI application in about twenty lines of Java. It worked. A ChatClient appeared out of nowhere, we called .prompt().user(...).call().content(), and Claude answered. That’s the magic of Spring Boot autoconfiguration — and also the danger of it. When things work without explanation, you’re fine right up until you need to debug something, customise something, or explain to a colleague what exactly is happening. Then you’re stuck. I’ve been there more times than I care to admit — staring at a NoSuchBeanDefinitionException at 4pm on a Friday, completely unable to explain why a bean that “should just be there” isn’t. (It was a missing property. It’s always a missing property.) ...

I still remember the moment it clicked — and the much longer stretch before it did. I’d been building Spring Boot applications for years. I knew the ecosystem. I knew how to wire beans, configure starters, and navigate the autoconfiguration magic without panicking. Then I started exploring Spring AI, and suddenly I was lost again. Embeddings. Vector stores. RAG pipelines. Advisors. ChatClient vs ChatModel. A wall of new terminology that felt completely disconnected from everything I already knew. ...

Claude Code — Teaching It Your Standards with Skills In Part 2, we turned CLAUDE.md into a precision instrument. We wrote down our conventions, our architecture, our rules — and watched Claude Code go from producing generic boilerplate to code that could survive a code review. But here’s the thing I noticed after a few weeks of working this way: my CLAUDE.md was getting fat. It started small. Build commands, naming conventions, a few architecture rules. Then I added a section on how to generate a complete REST slice. Then testing patterns. Then a procedure for running database migrations with Flyway. Before I knew it, the file was 300 lines long, and every single line was loaded into every single session — whether Claude needed it or not. ...

In Part 1, I showed you what Claude Code is and what it can do. You saw an AI agent that reads your project, writes code, runs your build, and fixes its own mistakes. Impressive stuff. But here’s the thing. If you just fire up Claude Code and start prompting, the output you get is… generic. It’s correct, sure. But it doesn’t know your team uses MapStruct instead of manual mapping. It doesn’t know your POST endpoints need authentication. It doesn’t know you measure everything with Micrometer and that a controller without metrics is considered incomplete. ...

I remember the first time I tried a GitHub Copilot suggestion in IntelliJ IDEA. It felt like magic. You start typing a method name, and suddenly the entire implementation materialises in grey ghost text. You press Tab, and — bam — it’s there. That was impressive. But it was still you doing the driving. In 2026, the landscape has shifted. Claude Code feels different. It’s less “autocomplete on steroids” and more “a colleague who sits next to you, holds the entire 1M token context of your codebase in their head, and then just… gets to work.” Let me show you what I mean. ...