• 12 Factor Agents
• 2025 年 AI 编程趋势：智能体 10 倍生产率放大下的“粪围”蔓延
• 2025年のアウトプットふりかえり
• 2026 in LLMs (so far)
• 60 million Copilot code reviews and counting
• A Fireside Chat with Cat and Thariq from the Claude Code team
• A Guide to Fine-Tuning FunctionGemma
• Месяц пишу язык программирования Nova с Claude Code. Где ломаются автономные агенты
• 基于大语言模型的 Vibe Coding 综述
• Команда агентов в Claude Code: от задачи до релиза
• 진짜 AI 에이전트형 코딩 툴 ＇Claude-Code＇
• Год с Claude Code: главное — не он сам, а то, что в .claude/
• ACP 协议 + 多 AI 编程智能体：企业研发的新生产力平台
• Advanced Context Engineering for Coding Agents
• AIに「レビューして」はもう古い？「敵対的検証」のすすめ
• コーディングエージェントの実行過程を検証する Agent as a Judge をフィードバックループに導入する
• I think “agent” may finally have a widely enough agreed upon definition to be useful jargon now
• Agent design lessons from Claude Code
• Agent-driven development in Copilot Applied Science
• Agent Frameworks, Runtimes, and Harnesses- oh my!
• Agent Harness Engineering
• Agent Middleware
• Agent Plugins package your skills, tools, and more
• Agent 编程方法论：不教工具教方法，让 AI 按你的规矩干活
• Agent pull requests are everywhere. Here’s how to review them.
• Agent Skills
• Claude Code Agent Skillsを活用したTECH BLOGレビュー ── AIで推進するレビュー自動化
• Agentic AI基础设施实践经验系列（九）：Context Engineering 上下文工程
• Agentic Autonomy Levels
• Agentic Code Quality
• Agentic Code Review
• Agentic Coding Hooks: Deterministic AI Guardrails
• Agentic Coding mit Spec-Driven Development: Warum Ihr KI-Agent Struktur braucht, bevor er Code schreibt
• Agentic Design Pattern #1: Tool Calling
• Agentic Design Patterns Part 3, Tool Use
• Agentic Engineering at Zalando: a snapshot
• Agentic Engineering: How Swarms of AI Agents Are Redefining Software Engineering
• Agentic Skill Decay
• Agents CLI in Agent Platform: create to production in one CLI
• AI Agent Guardrails: Rules That LLMs Cannot Bypass
• AI Assisted Code Reviews - Augmenting Pull Requests in .NET Projects
• AI-assisted Coding과 개발 생산성 향상 (부제: 실리콘밸리 개발자가 바라보는 AI 생산성 툴 및 개발 방식의 변화)
• 「AI Code Agents祭り」成功の裏側：大企業でAIコードエージェントを浸透させる7つのテクニック
• AI 代码审查再进化：AutoDev 多智能体协作架构深度解析
• AIコードレビューの理想と現実 ─ Devinをチームに導入して気づいたこと
• AI 代码评审在七猫的实践
• AI 编程 2025 总结：国产模型“能力追平”，国产编程工具还在“情感陪伴”
• 2026年のAI Coding Agent活用 ── スピードと安全性を両立させる
• AI Coding Agents: Adoption Trends
• AI Coding与单元测试的协同进化：从验证到驱动
• 谈谈 AI 编程工具的进化与 Vibe Coding
• AI駆動開発を2コマンドで組織標準に ── Claude Code × Codexで設計からテストまで
• AI 友好架构：DevOps 平台 & 平台工程赋能 AI 自动编程
• 要件策定から本番環境への展開までの完全自動化を目指して96プロダクトのAI活用力を強化した話｜プロダクトのキーパーソン向け施策『AIナレッジ共有会』
• AI writes code faster. Your job is still to prove it works.
• The Anatomy of Harness Engineering: How to Evaluate, Iterate, and Guard AI Coding Agents
• Anchoring AI to a reference application
• Are Harnesses Worth the Cost?
• Assessing internal quality while coding with an agent
• Audit your Agent files
• AutoDev CLI：构建 AI Agent 生成的 AI Agent 质量保障与验证架构
• AutoDev DevIns —— 开源 AI 智能体语言，构建 AI 驱动的自动编程
• AutoDev Remote 编程智能体：你何必只让 AI 在白天分析需求、设计方案
• Automate repository tasks with GitHub Agentic Workflows
• Automate security reviews with Claude Code
• コーディングガイドライン運用をAIで自動化し、レビュー知見を資産化する
• AIによる実装の品質が微妙で毎回自分で指摘しまくる必要があったので、確認前に自動で品質を上げさせるようにした
• Beyond permission prompts: making Claude Code more secure and autonomous
• Brownfield Agentic Engineering
• Build Better AI Agents: 5 Developer Tips from the Agent Bake-Off
• Build with Google Antigravity, our new agentic development platform
• Build with Jules, your asynchronous coding agent
• Build zero-trust AI agents that judge intent, not just syntax
• Building a C compiler with a team of parallel Claudes
• Pythonでゼロから作るコーディングエージェント
• Building agents with the Claude Agent SDK
• Building effective agents
• Building safeguards for Claude
• Building your first MCP server: How to extend AI tools with custom capabilities
• AI-Nativeという選択 ー 正解のない時代に、メルカリが選んだ指針
• Claude Code for web—a new asynchronous coding agent from Anthropic
• Claude Code Hooks Complete Guide - Deterministic Enforcement Across the Tool Lifecycle
• Claude Codeの自己レビューを信じてた。レビュー役だけ別モデルにしたら、見逃してたバグが出てきた
• Claude Code Swarms
• Claude Code 省 Token 指南：慎用 1M 上下文，不开新会话或者总是开新会话都不对
• Closing the knowledge gap with agent skills
• The Code Agent Orchestra - what makes multi-agent coding work
• Code execution with MCP: Building more efficient agents
• Codex as a platform: build on the open agent harness
• 人材紹介開発におけるコーディングエージェントの導入状況や勉強会の様子
• Comprehension Debt - the hidden cost of AI generated code.
• Conductor Update: Introducing Automated Reviews
• Context-Efficient Backpressure for Coding Agents
• Context Engineering for Agents
• Context Engineering for Coding Agents
• Continuous AI in practice: What developers can automate today with agentic CI
• Crush, Welcome Home
• From one-off prompts to workflows: How to use custom agents in GitHub Copilot CLI
• Custom Code Review rules for Codex
• AIレビューを6系統から1系統へ——「指摘ゼロ」で終われないループの切り方
• DeepSWE: Training a Fully Open-sourced, State-of-the-Art Coding Agent by Scaling RL
• Demystifying evals for AI agents
• Design Patterns for Securing LLM Agents against Prompt Injections
• Designing agentic loops
• Designing AI agents to resist prompt injection
• 開発組織のAI活用レベルを可視化する「エンジニア版AI番付」の設計と運営
• 设计流动摩擦：AI 原生团队的核心能力
• Developer’s Guide to AI Agent Protocols
• Developer’s Guide to Building ADK Agents with Skills
• AIエージェント時代の開発 — エージェンティックコーディング実践
• Devin’s 2025 Performance Review: Learnings From 18 Months of Agents At Work
• Devstral
• AIに渡す指示書の役割分担: AGENTS.md/SKILL.md/DESIGN.mdと仕様駆動開発の現在地
• Prüfen Coding-Agents Lizenzen?
• Do you really need a human in every loop?
• Don’t Build Multi-Agents
• Effective context engineering for AI agents
• Effective harnesses for long-running agents
• Effizientes Agentic Coding
• Embracing the parallel coding agent lifestyle
• Enabling AI usage at Mercari with Secure Devin Management
• Encoding Team Standards
• 2028年「開発プロセス完全自動化」を見据えた、エンジニア組織の構造改革
• 소프트웨어 3.0 시대를 맞이하며
• Equipping agents for the real world with Agent Skills
• 构建演进式 AI 辅助编码，融合 DevOps 规范和实践
• Evolving Spec-Driven Development: Conductor Now Supports Antigravity
• Exercise caution when building off LLMs
• Claude Codeで試すHarness Engineeringの実験的検証
• 約2,000人が使うClaude Codeと向き合う。
• The Factory Model: How Coding Agents Changed Software Engineering
• 5 Minuten reden, ein Proof of Concept - unser KI-Experiment mit AI-Assisted Coding und Spec Driven Development
• Fragments: September 29
• AI가 만든 코드가 어드민이 되기까지
• From Coding Loop to Business Loop: Thinking AI Engineering Holistically
• From idea to PR: A guide to GitHub Copilot’s agentic workflows
• Del Vibe Coding al Spec Driven Development: cómo dirigir agentes de IA sin perder el control
• The future of agentic coding: conductors to orchestrators
• GitHub Copilot coding agent 101: Getting started with agentic workflows on GitHub
• GitHub Copilot: Meet the new coding agent
• How GitHub’s agentic security principles make our AI agents as secure as possible
• How to write a good spec for AI agents
• AIコードレビューを「単一責任の原則」で育てた話
• Harness design for long-running application development
• Harness engineering for coding agent users
• Harness Engineering 实践指南：落地探索的三大原则
• How and when to build multi-agent systems
• How far can we push AI autonomy in code generation?
• 個人的AIコーディングエージェントとの向き合い方（2026）
• How I Fixed the Infinite Feedback Loop When Auditing Project Plans with Claude
• How StrongDM’s AI team build serious software without even looking at the code
• How to build reliable AI workflows with agentic primitives and context engineering
• How we built our multi-agent research system
• How we contain Claude across products
• Как мы учили Yandex Code Assistant помогать разработчикам с написанием кода и делать их счастливыми
• How we’re making GitHub Copilot smarter with fewer tools
• 人間は意図、AIは実装：Codexが導く「要件を伝えるだけ」のAI駆動開発ワークフロー
• Human judgment doesn’t leave the software factory. It relocates.
• Humans and Agents in Software Engineering Loops
• Impact de l’IA sur l’état de l’art de l’ingénierie logicielle en 2026
• Implementing effective guardrails for AI agents
• Claude CodeのSkillsでハーネスエンジニアリングを実装した — ルール自動生成でコード品質を継続改善する
• Improving Deep Agents with harness engineering
• Improving token efficiency in GitHub Agentic Workflows
• 云端与 IDE 智能体整合：解决工具碎片化，实现 AI 全流程自动编码
• 2026 Agentic Coding 趋势报告解读：从写代码到编排代理
• Introducing advanced tool use on the Claude Developer Platform
• Introducing Agent HQ: Any agent, any way you work
• Introducing Agent Skills
• Introducing All Hands AI
• Introducing Codex
• Introducing Devin, the first AI software engineer
• Introducing: Devstral 2 and Mistral Vibe CLI.
• Introducing Google Antigravity, a New Era in AI-Assisted Software Development
• Introducing Support for Local AI Models in the Antigravity SDK
• 仕様から書くAI駆動開発へ ― cc-sdd 入門
• ハーネスエンジニアリング入門 ── CLAUDE.mdの次に来るAIエージェント制御パラダイム
• Keep Agentic AI Simple: A Practical Workflow for Software Development
• Context Engineering
• Large Language Models can run tools in your terminal with LLM 0.26
• Learning to Verify AI-Generated Code
• 진짜 ‘딸깍’으로 다 되나요? — 보수적 개발자가 AI 에이전트로 프로덕트를 릴리즈하며 깨달은 것들
• Long-running Agents
• Loop Engineering
• ループエンジニアリング実践：プロンプトチューニングをClaude Codeに任せてみた
• Maintainability sensors for coding agents
• AI に t-wada の TDD を頑張らせる
• AI가 팀 규칙을 지키도록 하는 방법
• Making frontier cybersecurity capabilities available to defenders
• 用Agent评测思路管理AI Coding —— 31万行代码AI重构的实践
• Managing context on the Claude Developer Platform
• Spec-driven development: Using Markdown as a programming language when building with AI
• Maybe We Shouldn’t Be Reviewing All This Code
• Measuring What Matters with Jules
• Meet Jules Tools: A Command Line Companion for Google’s Async Coding Agent
• mercari-pm-agent Design — Automating the PM Workflow with Claude Code Skills and MCP
• Mitigating Indirect AGENTS.md Injection Attacks in Agentic Environments
• Mitigating Prompt Injection Attacks in Software Agents
• Mitigating the risk of prompt injections in browser use
• More than just code review
• My LLM coding workflow going into 2026
• New Gemini API updates for Gemini 3
• The New Software Lifecycle
• Not all AI-assisted programming is vibe coding (but vibe coding rocks)
• Onboarding your AI peer programmer: Setting up GitHub Copilot coding agent for success
• One Year of OpenHands: A Journey of Open Source AI Development
• OpenHands Context Condensensation for More Efficient AI Agents
• Orchestrating AI Code Review at scale
• Organiser une équipe de développement à l’ère de l’IA - Part II.2
• Organiser une équipe de développement à l’ère de l’IA - Part III
• Own the Outer Loop
• Peer Programming with LLMs, For Senior+ Engineers
• pj-double: メルカリの開発生産性向上に向けた挑戦 — AI-Native化が辿り着いたASDDとプロセス変革の全貌
• 2026 年，万物皆 Coding Agent 的平台工程（A2A / ACP / MCP / Skill）
• Practical Loop Engineering
• Claude Codeでハーネスエンジニアリングを実践する — 5層の設計パターン
• Claude Code를 활용한 예측 가능한 바이브 코딩 전략
• Программирование для тех, кто не пишет код: как устроен VibeCraft
• Prompt injection and jailbreaking are not the same thing
• Prompt Injection as Role Confusion
• Prompt injection attacks against GPT-3
• Quantifying infrastructure noise in agentic coding evals
• Software 3.0 시대, Harness를 통한 조직 생산성 저점 높이기
• Ralph Wiggum as a “software engineer”
• コミット数2倍でもレビュー品質を維持！AI時代のコードレビューフロー再設計
• Redesigning source control at Anthropic
• Claude Codeで”指摘ゼロになるまで回すレビューループ”を組んだが、ゼロにならなかった
• Routa 桌面版发布：内建 Harness 工程的 AI Coding 研发协作工作台
• Scaling Managed Agents: Decoupling the brain from the hands
• Unityクライアント環境におけるSDD活用事例 ── アンチパターンとその改善
• SDD: El Futuro Agéntico de la Ingeniería de Software y el Desarrollo AI-First
• Securing LLM Systems Against Prompt Injection
• Self-Improving Coding Agents
• Sequoia Ascent 2026 summary
• 複数チームで1つのClaude Codeプラグインマーケットプレイスを育てる ── 共同運用で直面した5つの課題と対策
• 複数のコーディングエージェントでSkillsを共有する（Claude Code / Codex対応）
• Shell + Skills + Compaction: Tips for long-running agents that do real work
• Shift Left & Right: Wie KI-Integration über das Coding hinauswächst
• Skill Issue: Harness Engineering for Coding Agents
• Le développement logiciel à l’ère des agents IA
• Rekayasa Perangkat Lunak: Bongkar Mitos, Sambut Vibe Coding!
• Software Factories, Light and Dark
• Spec-Driven Development: A Spec-First Approach to AI-Native Engineering
• Spec駆動開発におけるコンテキストエンジニアリングとCustom Slash Commandsのベストプラクティス
• Spec-Driven Development – Wer die Spec schreibt, bestimmt, was gebaut wird
• Spec-driven Development mit KI-Agenten – Wie Spezifikationen Code, Tests und KI-Agenten in Softwareprojekten synchron halten
• Spec-driven development with AI: Get started with a new open source toolkit
• Spec-Driven Development mit Claude Code: Workflow gegen Chaos
• Specification-Driven Development: el regreso de las especificaciones en la era de los agentes de IA
• Claude Code で1体のAIレビューに欲張って失敗し、3エージェントに分けた話
• Steering Claude Code: when to use CLAUDE.md, skills, hooks, and subagents
• Stop Using /init for AGENTS.md
• 停止“氛围编程”（Vibe Coding），拥抱新一代软件工程
• Structured Tools
• 学生よ、コーディングエージェントを使え。
• Taming Agents in the Mercari Web Monorepo
• AIエージェント時代に、テスト駆動開発（TDD）は「ガードレール」になる【t_wada×やっとむ対談】
• Testing Agent Skills Systematically with Evals
• Testing out Crush, a TUI based coding agent (in neovim btw)
• The Anatomy of an Agent Harness
• 楽しかったコーディングエージェントサブスク時代の終わり
• The lethal trifecta for AI agents: private data, untrusted content, and external communication
• A Nova Era do Desenvolvimento de Software: do Vibe Coding à Engenharia Agêntica
• The New Skill in AI is Not Prompting, It’s Context Engineering
• The rise of “context engineering”
• The State Of AI Harness Engineering 2026
• The uncomfortable truth about vibe coding
• The VibeSec Reckoning
• 3層エージェントオーケストレーションで実現する高精度AIコードレビュー
• 仕様書駆動開発の課題をチームで改善した3つの工夫
• Tool Calling with LangChain
• Tool Design for AI Agents: Lessons from 50+ Claude Code Tools
• 토스팀이 AI 파도를 마주하는 방법: AI Surf Day
• An important update: Transitioning Gemini CLI to Antigravity CLI
• Trustworthy agents in practice
• エンジニア2人 × AI で回すプロダクト開発 — “開発プロセスの半分以上をAIが主導的に行う” 体制の実践
• Two publishers and three authors fail to understand what “vibe coding” means
• Understanding Spec-Driven-Development: Kiro, spec-kit, and Tessl
• An update on recent Claude Code quality reports
• Using skills to accelerate OSS maintenance
• AIエージェント向けコーディングルールをArchUnitで機械的に検証する運用
• Vibe coding and agentic engineering are getting closer than I’d like
• Boas práticas de vibe coding: o que não dá pra deixar passar
• バイブコーディングはもう古い！エージェンティックエンジニアリングで差をつけろ
• Vibe coding – Was nun?
• Vibe engineering
• We’re going to need default hard budget caps on pretty much everything
• Welcome to the Eternal September of open source. Here’s what we plan to do for maintainers.
• AIが教えてくれたコードレビューの本質　― 意図共有という学び ―
• 什么是「驾驭工程」（Harness Engineering）？
• What Is Spec-Driven Development? A Practitioner’s Guide (and When to Skip It)
• WINTICKETで仕様書作成にAIが定着するまでにやったこと
• “When AI reviews AI’s code, you’ve built an infinite loop. Here’s how we stopped it.”
• Write a coding agent from first principles: better tools
• Writing a good CLAUDE.md
• Writing about Agentic Engineering Patterns
• Writing effective tools for agents — with agents
• Вам не нужен ещё один Claude Code: зачем Pi оставляет сборку агента пользователю
• Your Agent Needs a Harness, Not a Framework
• Your AI coding agents need a manager
• Your job is to deliver code you have proven to work
• Your parallel Agent limit