10 copy-paste AI prompts for Hibernate and JPA development. Covers entity relationship design, fixing LazyInitializationException, writing JPQL queries, generating Flyway migrations, second-level cache, bulk operations, soft delete, auditing with @EntityListeners, Criteria API Specifications, and full entity model reviews.
10 copy-paste AI prompts for reviewing and improving Java code quality. Covers SOLID violations, thread-safety bugs, virtual thread carrier pinning, N+1 query patterns, resource leaks, exception handling, null safety, logging quality, and full quality audits. Works in Claude, ChatGPT, Gemini, and Cursor.
10 copy-paste AI prompts for Spring Boot development. Covers scaffolding REST endpoints, configuring Spring Security JWT, debugging autoconfiguration, global exception handling, production tuning, Actuator health checks, CORS, caching, and migrating from Spring Boot 2.x to 3.x. Works in Claude, ChatGPT, Gemini, and Cursor.
Complete runnable LLM Gateway project: full directory structure, docker-compose, pom.xml with Spring Boot 3.4.5 and Spring AI 1.1.0, all source files, build instructions, and five end-to-end I/O demos covering normal routing, cache hits, rate limiting, and provider failover.
Complete runnable Spring AI 1.1.0 RAG project: full directory structure, docker-compose, pom.xml, all source files, build instructions, and an end-to-end PDF ingestion and query walkthrough.
A copy-paste playbook of AI prompts for migrating Java codebases between every LTS jump: 8→11, 11→17, 17→21, and 21→25. Use them in Claude, ChatGPT, Gemini, or Cursor to automate the repetitive parts of a version upgrade.
A complete implementation of a semantic search engine in pure Java — no external libraries. Covers TF-IDF vectorisation, cosine similarity, and document ranking by meaning. Explains the mathematics behind vector embeddings, how they power RAG and AI search systems, and provides a working query engine with annotated code and sample output. The same architecture used by Pinecone, Weaviate, and Elasticsearch — built from scratch.
A complete, from-scratch implementation of a feedforward neural network in pure Java — no TensorFlow, no DL4J, no external libraries. Covers the Neuron model, forward propagation, sigmoid activation, backpropagation with gradient descent, and trains the network to learn the XOR function. Every line of code is annotated with the underlying mathematics so you understand exactly what the network is doing at each step.