Mingqi HouI build production web apps with React, Node.js, and AI. Available for freelance.https://houmq.dev/en-usThe Six Pillars of Coding Agents (and How to Evaluate Any New Product)https://houmq.dev/writing/agent-six-pillars/https://houmq.dev/writing/agent-six-pillars/Agent loop, tools, context, memory, multi-agent, and harness—one framework I use instead of chasing every new launch.Wed, 03 Jun 2026 00:00:00 GMTai-agentsarchitecturecursorclaude-codeHow I Use Cursor in Production (Without Losing Ownership of the Code)https://houmq.dev/writing/cursor-ai-coding-in-production/https://houmq.dev/writing/cursor-ai-coding-in-production/Model choice, context discipline, rules, MCP, and why AI helps more on legacy code than greenfield demos—lessons from seven years of shipping web apps.Wed, 03 Jun 2026 00:00:00 GMTcursorai-codingworkflowfull-stackHow I Structure AI-Assisted Development: SDD, Rules, Skills, and MCPhttps://houmq.dev/writing/ai-coding-architecture-stack/https://houmq.dev/writing/ai-coding-architecture-stack/A stack I use on real repos—spec-driven changes, persistent rules, procedural skills, and MCP for design, browser, and API truth.Wed, 03 Jun 2026 00:00:00 GMTcursorai-codingmcpworkflowOptimizing INP for React Apps (Core Web Vitals)https://houmq.dev/writing/inp-interaction-performance/https://houmq.dev/writing/inp-interaction-performance/What Interaction to Next Paint measures, how I profile it, and practical fixes for main-thread blocking, handlers, and rendering.Wed, 03 Jun 2026 00:00:00 GMTreactperformancecore-web-vitalsfrontendFrontend Permission Design: Routes, Buttons, Data Scope, and Feature Flagshttps://houmq.dev/writing/frontend-permission-rbac/https://houmq.dev/writing/frontend-permission-rbac/How I wire backend-driven permission codes into dynamic routes, menus, action buttons, row-level scope, and gray releases in React admin apps.Wed, 03 Jun 2026 00:00:00 GMTreactarchitecturerbacnextjsSchema-Driven UI: From Hard-Coded Screens to Configurable Platformshttps://houmq.dev/writing/configurable-ui-schema-platform/https://houmq.dev/writing/configurable-ui-schema-platform/How I render forms, tables, and pages from JSON schema—component maps, dynamic loaders, and where permissions plug in.Wed, 03 Jun 2026 00:00:00 GMTreactarchitecturelow-codetypescriptBuilding Mini Claude Code: A Coding Agent from Scratchhttps://houmq.dev/writing/build-mini-claude-code/https://houmq.dev/writing/build-mini-claude-code/How I wired workspace sandboxing, tool schemas, the agent loop, system prompts, and background dev servers—before trusting black-box agent frameworks.Wed, 03 Jun 2026 00:00:00 GMTai-agentspythonopenaitutorialGoverning React SSR Hydration Mismatches in Next.js Appshttps://houmq.dev/writing/nextjs-ssr-hydration-governance/https://houmq.dev/writing/nextjs-ssr-hydration-governance/How I detect, fix, and prevent “server HTML didn't match the client”—ESLint rules, CI diff checks, and standard repair patterns.Wed, 03 Jun 2026 00:00:00 GMTreactnextjsssrperformanceReAct vs Plan-and-Execute: When to Use Which Agent Patternhttps://houmq.dev/writing/react-plan-execute-agent-patterns/https://houmq.dev/writing/react-plan-execute-agent-patterns/Two patterns I use for tool-using agents—tight think-act-observe loops versus upfront planning with replanning on failure.Wed, 03 Jun 2026 00:00:00 GMTai-agentsreactarchitecturelangchainTokens, Chinese Text, and Streaming: What Agent Builders Should Knowhttps://houmq.dev/writing/tokens-streaming-agent-cost/https://houmq.dev/writing/tokens-streaming-agent-cost/Why CJK prompts cost more tokens, how autoregressive generation affects tool calls, and practical budget margins for multi-step agents.Wed, 03 Jun 2026 00:00:00 GMTai-agentsllmperformancecostRefactoring a 500-Line React useEffect with AI (As the Architect, Not the Passenger)https://houmq.dev/writing/legacy-react-refactor-with-ai/https://houmq.dev/writing/legacy-react-refactor-with-ai/A five-step prompt workflow I use on legacy admin code: analyze, extract pure logic, test, rewrite orchestration, then add features safely.Tue, 02 Jun 2026 00:00:00 GMTreactrefactoringai-codingtypescriptChatbot, Copilot, or Agent? Who Owns the Loophttps://houmq.dev/writing/chatbot-copilot-agent-loop/https://houmq.dev/writing/chatbot-copilot-agent-loop/Same frontier models, wildly different products—the while-loop behind agents, production exit paths, and a minimal TypeScript harness.Tue, 02 Jun 2026 00:00:00 GMTai-agentscursorarchitecturetypescriptAI Memory Is Not Chat Logs—It Is Context Budget Managementhttps://houmq.dev/writing/ai-memory-context-budget/https://houmq.dev/writing/ai-memory-context-budget/Why long conversations need truncation, summarization, and retrieval layers—and how to assemble prompts for production agents.Tue, 02 Jun 2026 00:00:00 GMTai-agentsmemorylangchainllmBeyond Storing Vectors: A Production-Style RAG Pipeline with Milvushttps://houmq.dev/writing/production-rag-milvus-ebook/https://houmq.dev/writing/production-rag-milvus-ebook/An EPUB semantic Q&A walkthrough—loaders, splitters, Milvus schema, retrieval parameters, and prompt boundaries that map to enterprise knowledge bases.Mon, 01 Jun 2026 00:00:00 GMTragmilvusvector-databaselangchainRAG Ingestion: Why Loaders and Splitters Come Before Vector Searchhttps://houmq.dev/writing/rag-loaders-and-splitters/https://houmq.dev/writing/rag-loaders-and-splitters/Knowledge does not arrive as LangChain Documents. How loaders normalize sources and splitters set retrieval granularity—with a web-scraping demo.Sat, 30 May 2026 00:00:00 GMTraglangchaindocument-processingai-engineeringWhy RAG Depends on Vector Search: From Embeddings to Semantic Retrievalhttps://houmq.dev/writing/why-rag-needs-vector-search/https://houmq.dev/writing/why-rag-needs-vector-search/How retrieval-augmented generation works in production—why keyword search falls short, what embeddings do, and a runnable LangChain demo.Thu, 28 May 2026 00:00:00 GMTragembeddingslangchainai-engineering