The article presents a case study of separating architecture and development roles in AI-assisted programming, emphasizing decision boundaries, design baselines, deliverables, and evidence-based handoffs. It shows how architecture handles requirements and design while development implements, with gaps returned to architecture, and how mid-project changes require unified baseline updates to avoid conflicting local facts.
In a weekend experiment, a solo developer used AI tools to port the popular RuoYi-Vue Spring Boot admin system to the native AOT framework Feat, achieving 14 of 18 core features with zero front‑end changes, illustrating the rise of AI‑augmented solo development and the accelerating shift toward AOT‑based Java backends.
This article argues that AI-generated code passing tests is insufficient for delivery, proposing a four-layer acceptance framework—functional, regression, risk, and business verification—backed by a six-part evidence chain and risk-based quality gates to ensure reliable, auditable software releases.
This article details a specification-driven AI collaboration system combining OpenSpec for structured requirements and AI Workflows with skills, hooks, and templates for execution, demonstrated through a Vue/TypeScript retail project where AI accuracy improved from 60% to 90%.
AI WorkflowsAI-assisted developmentDeveloper Productivity
After Bun migrated to Rust with AI assistance, the Zig community forked its abandoned Zig codebase to create Buz, rebuilt it with a modern Zig toolchain, achieved sub‑second incremental builds, and now enforces AI‑assisted contributions while remaining an experimental, platform‑limited project.
Buz, a Zig‑based fork of Bun, inherits the last Zig commit, slashes incremental build time to under one second, removes over 11 000 dead‑code lines, and enforces AI‑assisted contributions, but remains an experimental project far from production‑ready replacement.
A developer couple created 'Love Bean AI Blueprint,' a HarmonyOS app that generates bead art patterns from photos using AI, built with a Cangjie/ArkTS/C++ architecture and AI-assisted migration tools, earning a spot at HDC 2026 Star Avenue.
The article details how Anthropic engineers used Claude Code and multiple AI agents to migrate large codebases—from a million‑line Zig project to Rust and a 165k‑line Python codebase to TypeScript—outlining a six‑step workflow, cost considerations, and practical principles for AI‑assisted large‑scale code migration.
The article analyzes how AI agents and redesigned workflows enable a 10-person software team to achieve the delivery capacity of a traditional 50-person company, shifting from labor-intensive to system-driven production.
Huawei releases DevEco Code 0.1.3 and DevEco CLI 1.2.0 with enhanced ArkTS code generation, new static analysis tools, Goal mode improvements, and comprehensive CLI commands for HarmonyOS app development including build, run, emulator management, and MCP services.
A team that relied entirely on AI tools like Codex to rush a multi‑channel customer‑service chatbot into production ended up with unreadable code, endless bug‑fix loops, performance crashes, and a loss of engineering control, illustrating the hidden risks of AI‑only development.
AI codingAI-assisted developmentCode Maintainability
The article analyzes how AI transforms software company organizations, shifting bottlenecks from coding efficiency to AI collaboration management, proposing autonomous squads, an AI Engineering OS with shared memory and automated review, and a new 'AI Software Director' role blending architecture, business, and AI orchestration.
Anthropic’s Claude Code team reports an eight‑fold increase in engineer code output, but the article explains that the real shift is from writing code to verification, with specs stored in repos, routines that merge feedback, PRs and metrics, a bad/sad quality taxonomy, six concrete interfaces, and new challenges around context switching, accountability and role boundaries.
The interview with Andrew Ambrosino reveals how Codex’s explosive user growth, the shift from costly implementation to costly taste, timing of model upgrades, blurred role boundaries, and the drive to integrate with existing tools shape its merger with ChatGPT and its future direction.
The article analyzes Anthropic engineer Thariq’s experience with Claude Fable 5, showing that the real bottleneck in AI‑assisted development is the developer’s unknowns, and presents a four‑quadrant framework plus a three‑stage methodology to discover and reduce those blind spots throughout a project’s lifecycle.
DevEco CLI launches as an AI-agent-friendly command-line toolkit for HarmonyOS app development, offering one-command integration with tools like OpenCode, a full-lifecycle CLI command set, a local optimized knowledge base, 70+ curated Skills for multi-device adaptation, and a community Skills plaza for sharing reusable AI capabilities.
Most developers treat Claude Code like a junior programmer, but by chaining its primitives—explore subagent, plan mode, CLAUDE.md, hooks, and review subagents—into a repeatable nine‑step loop, you can achieve a disciplined senior‑engineer workflow that includes code exploration, planning, incremental builds, enforced standards, automated testing, and systematic code review before shipping.
At HDC2026's co-construction forum, HarmonyOS partners including Amap, WPS, Tencent Video, and Meituan showcased real-world optimizations: Amap's generative UI framework boosts rendering 20%, WPS uses AI to slash flame-graph analysis from hours to minutes, Tencent Video cuts cold start to 1 second, and Meituan's QUIC tuning improves weak-network latency 27%.
HarmonyOS has open-sourced its first batch of Agent Skills on GitCode, providing AI-assisted coding support for ArkTS syntax checking, ArkUI development, multi-device adaptation, and application stability diagnosis, with demonstrated efficiency gains in foldable device adaptation and freeze analysis.
The author recounts how they leveraged the engineering structure, common capabilities, documentation standards, and AI‑assisted workflows from an existing ERP SaaS project to build a vertical, headquarters‑partner system, highlighting the need to define boundaries, adapt business logic, and use AI for support rather than blind code copying.
The article presents a step‑by‑step, three‑month‑tested workflow that embeds Anthropic Claude and OpenAI Codex into IntelliJ IDEA via the Continue plugin, enabling Java developers to auto‑generate CRUD code, unit tests, and refactorings, connect Claude to the database, and avoid repetitive coding tasks without purchasing a subscription.
Tencent's Kuikly team introduces Kuikly AI, a Harness Engineering foundation for cross-platform development that addresses AI code quality and client complexity challenges through open-sourced Rules for framework conventions and Skills for scenario-specific AI agents, alongside MCP, design-to-code, preview tools, and migration agents.
This article walks through a complete Agentic Engineering workflow for a backend Go service, showing how AI‑driven Skills and Commands automate requirement capture, clarification, planning, parallel development, code review, deployment, log analysis, MR creation, AI‑assisted review, automated fixes, and final merge, while highlighting token consumption and practical lessons.
JetBrains AIR redefines the IDE by making AI the default workflow, offering a step‑by‑step guide that covers installation on macOS, project opening, task definition, execution, review, and advanced MCP server integration, while emphasizing deterministic, explainable AI and developer control.
JetBrains AIR transforms the IDE landscape by embedding AI as the default workflow, offering macOS installation, Git project handling, chat-based task definition, configurable permission modes, context addition, parallel task execution, review tools, and advanced MCP server integration, all while keeping developers in full control of code changes.
Sogou Input Method shares its Kuikly cross-platform AI engineering practice, adopting Spec-Kit standardized workflow, GAN-inspired iterative context document generation, and Kuikly's built-in AI tools (MCP, Rules, Skills) to achieve 3x faster new page development (3 days → 1 day) with high code quality and minimal architectural rework.
AI context engineeringAI-assisted developmentKuikly
The article explains that the most dangerous moment in development is when you think the code is finished, and introduces the /review and /investigate skills to catch structural risks and root‑cause issues before merging, especially in the AI‑driven era.
The article introduces IDAKE, a three‑layer, five‑step methodology that combines intent‑driven testing, specification‑driven contracts, multi‑agent collaboration, knowledge‑graph guidance, and complex‑adaptive system theory to address the imbalance between unconstrained AI coding and over‑specification in modern software engineering.
The article demonstrates how CodeGenie uses MCP to connect external knowledge bases and Rules to enforce ArkTS standards, enabling AI to detect deprecated APIs, retrieve official docs, and generate compliant HarmonyOS code through a four-step workflow.
Boris Cherny, the founder of Claude Code, reveals a detailed 13‑step workflow that combines aggressive parallelism, Opus 4.5 with Thinking mode, a shared CLAUDE.md knowledge base, custom slash commands, sub‑agents, automated formatting hooks, permission presets, deep tool integrations, and a strict verification loop to dramatically boost AI‑driven development productivity.
This article walks through using GPT‑5 and ByteDance’s Trae tool within the VibeCoding workflow to iteratively generate a complete MCP service marketplace front‑end UI, refine it through multiple prompt rounds, produce a PRD, design backend APIs, build a SpringBoot 2.7 project with MyBatis Plus and MySQL, and finally test and deploy the full system.
The article explains how Easy Code Reader MCP Server integrates with Joycode and large language models to automatically retrieve and analyze Java source code across multiple projects or JAR files, improving code‑agent accuracy and developer productivity.
This article explores how modern AI IDEs like Cursor and Trae empower developers to rapidly prototype and implement a Chrome extension that automatically switches Whistle proxy rules, generate project scaffolding in minutes, and produce comprehensive documentation through AI‑driven analysis and prompt engineering.
This article reviews practical Model‑Chat Plugins (MCP) that front‑end developers can integrate into their workflow—covering Figma, Apifox, Context7, and Chrome DevTools MCPs—explaining setup steps, code examples, and how they dramatically improve efficiency and code maintainability.
CodeGenie leverages a Huawei-curated HarmonyOS corpus to provide context-aware code completion with three trigger modes, fine-grained acceptance controls, cross-module dependency resolution, and adaptive style learning, enabling developers to generate accurate ArkTS code while maintaining full control over suggestions.
This article details how integrating the AI coding assistant Cursor into a membership‑system frontend project increased development efficiency by 21%, reduced a 188‑hour task to 149 hours, and outlines practical methods for AI‑generated routing, UI‑to‑DOM conversion, mock data creation, code refactoring, and the limits of AI assistance in complex interactions.
The author shares how they built a low-code platform in two months with 90% AI-generated code by adopting an architect-and-tamer role, decomposing tasks, feeding context, and iterating with tests across four core modules.
This article explains low-code platforms in plain language, covering what they are, what business users can build with them (forms, databases, workflows, reports, apps), who they suit, the underlying technology, how AI enhances them, how to get started, common misconceptions, and why low-code is becoming an essential workplace skill like Excel.
AI-assisted developmentbusiness automationcitizen development
This article explores ambient programming, a paradigm merging natural language intent, AI code generation, and low-code platforms to build systems through conversation, analyzing current tooling, development stages, five-year predictions, and challenges like context consistency and maintainability.
AI-assisted developmentAmbient ProgrammingGenerative AI
This article shows how to rapidly build a configurable cadre management system using AI-generated SQL schemas and the Chengwu low-code platform, covering eight database tables, auto-generated UI pages, and drag-and-drop workflow configuration for approval processes, reducing development time from months to days.
This article details a real‑world M‑site homepage refactor where AI‑powered Cursor and structured prompts were used to migrate a Rax waterfall component to React, rewrite DX components, optimize business logic, enforce project standards, and evaluate the benefits and limits of AI‑assisted development.
The article traces software engineering from the waterfall era to agile and DevOps, then explains how large language models reshape development into a "program‑plus‑model" paradigm, outlining new human‑AI collaboration patterns, quality‑assurance challenges, and strategic considerations for the emerging SE 3.0 era.
This article chronicles how a developer transformed the TransDuck audio‑video SaaS tool into a native desktop application using Tauri, Vue, and ffmpeg, while leveraging the AI‑driven CodeBuddy extension to automate project scaffolding, code generation, error fixing, and UI refinement, cutting development time from days to a few hours.
The article explains how integrating the Cursor AI assistant into front‑end development reshapes workflow by separating planning from execution, using iterative context loops for analysis, design, and impact assessment, guiding minimal‑change code generation and testing, and ultimately shifting developer skill from memorizing APIs to asking precise questions.
Vibe Coding, popularized by Andrej Karpathy’s 400‑line iOS calorie‑tracker built entirely through conversational prompts with ChatGPT, showcases a hands‑off workflow—initializing a project, adding core features, persisting data, and deploying—while the broader community replicates the approach, underscoring both AI’s rapid prototyping power and the continued need for professional code review and maintenance.
The article analyses Daniel Jackson’s concept‑driven software design presented at the 2024 Global Software R&D Conference, relates it to domain‑driven design and business services, and demonstrates how AI‑augmented prompts can generate Java domain models and a Spring‑Boot RESTful API for order submission.
This article explores how large language models can be integrated into software architecture governance, turning architectural rules into code, enhancing design, development, and runtime phases, and improving code generation quality through explicit knowledge, DSLs, and full‑process AI assistance.