A ubiquitous public account for pirate enthusiasts, regularly sharing curated experiences, tech learning, and growth insights. Currently publishing articles on AI RAG customer service, AI MCP technology, and open-source design. Personal free Knowledge Planet: Awakening New World Programmer.
This article explains how to build a TypeScript PromptBuilder that supports variable placeholders, demonstrates three concrete AI code‑review prompt templates, and shows how these templates can be integrated into a code‑review workflow to produce structured, high‑quality feedback.
This article walks through using Vibe Coding’s AI‑driven workflow with the Trae tool to automatically generate a Vue 2‑based web management dashboard, detailing how to extract UI design rules, create project‑level prompts, run commands, troubleshoot, and refine the interface with iterative prompts.
This article walks through Spec‑Driven Development (SDD) as a structured alternative to Vibe Coding, showing how to use GitHub Spec Kit and Copilot to create a 1024 web game by defining requirements, planning, generating tasks, and implementing code step by step.
This article explains the MCP communication protocol, detailing how JSON‑RPC 2.0 structures requests and responses, how tools are listed and invoked via HTTP SSE, and walks through the full client‑server lifecycle with concrete code examples and diagrams.
The article breaks down the fourteen distinct meetings a software requirement must pass—from kickoff and daily stand‑ups to design reviews, testing, and post‑mortems—explaining each session’s purpose, typical participants, preparation steps, common pitfalls, and how they collectively shape a developer’s workload far more than writing code itself.
This article walks through VibeCoding’s immersive AI‑driven workflow, showing how to craft detailed prompts, use ByteDance’s Trae IDE to iteratively generate and refine a two‑page HTML/CSS/JS resume web page, add PDF export, dynamic sections, and achieve a polished final product.
This article demonstrates how to resolve AI hallucination in train‑ticket queries by cleaning data, building a Spring AI‑based Model Context Protocol (MCP) server with HTTP SSE in Java, exposing it as a tool, and seamlessly integrating the server into a FastGPT workflow to enable natural‑language train‑ticket assistance.
The article walks through a detailed Java interview simulation where the candidate designs a high‑performance, microservice‑based e‑commerce transaction and fulfillment system, covering architecture decomposition, caching, concurrency control, distributed transactions, observability, AI‑driven recommendation, and a concrete career roadmap.
The article explains how to replace manual MCP Server development with Higress AI Gateway's API‑to‑MCP feature, showing step‑by‑step Docker setup, configuration of a simple SpringBoot service, MCP tool definition, request‑template options, and the resulting zero‑code deployment for AI agents.
This article walks through a five‑round Java interview simulation where the candidate designs, optimizes, and secures a massive push‑notification system for Sohu, covering Spring Boot high‑concurrency architecture, sharding and cache‑penetration mitigation, Kafka reliability, Kubernetes deployment with gray releases, multi‑region high‑availability, and AI‑driven smart‑push strategies, complete with concrete code snippets and real‑world performance numbers.
