A tinkering programmer and author of "Spring Cloud Microservices in Action"
This guide outlines five practical strategies—planning before coding, smart context management, custom rules and skills, parallel model execution, and treating the AI as a collaborator—to help developers harness AI coding assistants like Cursor for faster, higher‑quality software development.
This article shares five surprising, high‑impact lessons from Anthropic on building robust AI agent evaluation suites, covering early failure‑case collections, recognizing clever “failures,” focusing on outcomes over process, choosing the right success metrics, and the irreplaceable value of human review.
This article explains how the TOON data‑serialization format reduces token usage and improves accuracy for large language model calls compared with traditional JSON, provides benchmark results, outlines scenarios where TOON is advantageous or unsuitable, and shows Java integration examples.
This article explains how spec‑driven development transforms AI‑assisted coding from exploratory, chat‑based experiments into a reliable, production‑grade workflow by using formal specifications as the source of truth, systematic validation, and a structured tool ecosystem to ensure quality, security, and maintainability.
This article provides a comprehensive guide to using Claude Code, covering daily workflows, the crucial CLAUDE.md file, custom slash commands, sub‑agents, hooks, planning mode, skills, MCP, the SDK, GitHub Actions, and key configuration settings to help developers harness AI‑driven coding efficiently.
This guide walks you through building a Spring Boot application, registering a UnifiedTTS API key, configuring MiniMax or CosyVoice models, implementing the service layer, running unit tests, and handling production concerns to achieve high‑quality text‑to‑speech synthesis without changing client code.
The article recounts a startup’s painful experiment with 47 microservices, exposing hidden operational costs, deployment delays, and outage risks, and ultimately shows how consolidating back to a well‑structured monolith dramatically improved performance, cost, and delivery speed.
The article reveals how default Jackson JSON serialization can become a hidden CPU bottleneck in high‑traffic Spring Boot services, explains why full entity objects inflate serialization time, and presents practical optimizations such as @JsonView, custom ObjectMapper settings, hand‑written serializers, and alternative data formats to dramatically cut latency and cloud costs.
A recent study shows that deliberately shortening or misspelling Java variable names can reduce latency and increase throughput by up to 49%, revealing hidden performance costs in the JVM's string handling and prompting a data‑driven, selective naming strategy for high‑throughput systems.
This tutorial shows how to integrate UnifiedTTS's free Edge TTS service into a Spring Boot project, covering project setup, API key registration, configuration, request/response models, service implementation, unit testing, and runtime verification with sample code and images.
