#llm

A practical comparison of type-safe Java design and LLM-assisted code generation in Spring Boot, with guidance on where each approach adds the most value.

A practical blueprint for building AI agents that stay useful, observable, and safe when real users push them beyond the happy path.

A practical map of how large language models work: tokens, transformers, training, sampling, and the patterns that keep answers grounded.

A Retrieval-Augmented Generation (RAG) system built with Spring AI, designed to chat with local documents.

A practical guide for traditional software developers to transition into AI engineering by layering AI capabilities onto existing skills and systems.