Spec-Driven Development (SDD) revives the old idea of heavy documentation before coding — an echo of the Waterfall era. While it promises structure for AI-driven programming, it risks burying agility under layers of Markdown. This post explores why a more iterative, natural-language approach may better fit modern development. The Rise of Specification Coding assistants are intimidating: instead of
LLMによるコード補完の登場 (2021年) GitHub Copilotの登場 我々がよく知るLLMによる支援はまず GitHub Copilot から始まりました。これはGPT-3 (OpenAI Codex, 現在のCodexと名前が同じで本当にややこしい) をベースとしたコード補完システムで、タイピングをしていると自動的にその行の続きを予測してくれるものです autocompleteとの違い それ以前にもIntelliSenseのようなautocompleteがありましたし、より進歩したn-gramなどを用いたものはありましたが、LLMをベースとしたものはTabnine (Tabnineは初期はn-gramモデル) やCopilotからとなります チャットベースのコードアシストの時代 (2022-2023年) ChatGPTの登場 ChatGPT以降、チャットによる対話形式でコード
GitHub - modelcontextprotocol/servers: Model Context Protocol Servers
Official integrations are maintained by companies building production ready MCP servers for their platforms. 21st.dev Magic - Create crafted UI components inspired by the best 21st.dev design engineers. 2slides - An MCP server that provides tools to convert content into slides/PPT/presentation or generate slides/PPT/presentation with user intention. ActionKit by Paragon - Connect to 130+ SaaS inte
Googleが提唱したDESIGN.mdとは？Claude CodeとDESIGN.mdでデモサイトをいくつか作ってみた - Qiita
はじめに こんばんは、mirukyです。 個人的にAIにデザインを指定するのって、意外と難しいと思っています。 皆さん、DESIGN.mdをご存知でしょうか。GoogleがStitchプロジェクトの一部として策定した、マークダウンベースのデザインシステム仕様です。「AIコーディングエージェントにデザインの文脈を与える」という、シンプルながら強力なアプローチで、いま海外のAI開発者コミュニティで注目を集めています。 私はこのDESIGN.mdの仕様を読んで「これ、実際に使うとどのくらいのクオリティが出るんだろう？」と気になりました。 そこで今回、DESIGN.mdを5つ書き、それぞれClaude Codeに渡してデモサイトを作ってもらいました。ジャンルはSaaS、カフェ、ポートフォリオ、ヘルスケア、クリエイティブエージェンシーとバラバラにしています。結果は正直、かなり驚きました。 この記事で
Agent skills are reshaping how developers work with AI coding agents. Today we’re launching gh skill, a new command in the GitHub CLI that makes it easy to discover, install, manage, and publish agent skills from GitHub repositories. What are agent skills? Agent skills are portable sets of instructions, scripts, and resources that teach AI agents how to perform specific tasks. They follow the open
What We Learned from a Year of Building with LLMs (Part I)
It’s an exciting time to build with large language models (LLMs). Over the past year, LLMs have become “good enough” for real-world applications. The pace of improvements in LLMs, coupled with a parade of demos on social media, will fuel an estimated $200B investment in AI by 2025. LLMs are also broadly accessible, allowing everyone, not just ML engineers and scientists, to build intelligence into
2025: The year in LLMs
31st December 2025 This is the third in my annual series reviewing everything that happened in the LLM space over the past 12 months. For previous years see Stuff we figured out about AI in 2023 and Things we learned about LLMs in 2024. It’s been a year filled with a lot of different trends. The year of “reasoning” The year of agents The year of coding agents and Claude Code The year of LLMs on th
Welcome to the very first post in a new blog! Here I will discuss software development, SRE work, and other fun stuff. Sometimes an idea is just too good to pass up. I hope this blog will motivate me to turn sparks and little pieces into general knowledge in writing the words down. The other day I was discussing Tabby with a coworker. We talked about whether we should consider AI-autocompleted cod
What makes Claude Code so damn good (and how to recreate that magic in your agent)!?/ vivek / 2025-08-21 Claude Code is the most delightful AI agent/workflow I have used so far. Not only does it make targeted edits or vibe coding throwaway tools less annoying, using Claude Code makes me happy. It has enough autonomy to do interesting things, while not inducing a jarring loss of control like some o
Update 1.99.1: The update addresses these security issues. Update 1.99.2: The update addresses these issues. Update 1.99.3: The update addresses these issues. Downloads: Windows: x64 Arm64 | Mac: Universal Intel silicon | Linux: deb rpm tarball Arm snap Welcome to the March 2025 release of Visual Studio Code. There are many updates in this version that we hope you'll like, some of the key highligh
Edit: A lot of folks have been asking what worfklows I used to write these apps. I used GitHub Copilot in VS Code with a custom agent prompt that you’ll find toward the end of this post. Context7 was the only MCP I used. I mostly just used the built-in voice dictation feature and talked to Claude. No fancy workflows, planning, etc required. The agent harness in VS Code for Opus 4.5 is so good - yo
The Death of the Stubborn Developer I wrote a blog post back in May called The Death of the Junior Developer. It made people mad. My thesis has since been corroborated by a bunch of big companies, and it is also happening in other industries, not just software. It is a real, actual problem, despite being quite inconvenient for almost everyone involved. My beehive-kicking post’s main premise is pre
The economic potential of generative AI: The next productivity frontier
The economic potential of generative AI: The next productivity frontier Generative AI is poised to unleash the next wave of productivity. We take a first look at where business value could accrue and the potential impacts on the workforce. AI has permeated our lives incrementally, through everything from the tech powering our smartphones to autonomous-driving features on cars to the tools retailer
はてなブログ独自の集計による人気記事のランキング。2025年6月8日（日）から2025年6月14日（土）〔2025年6月第2週〕のトップ30です*1。 # タイトル／著者とブックマーク 1 Cursor で100日間アプリを作り続けた中で、全然うまくいかなかったこと - フラミナル by id:lirlia 2 私的年間新作映画ベスト10×10年分（2015年-24年）、全解説 - 名馬であれば馬のうち by id:Monomane 3 陰謀論だらけの桃太郎 - ナナオクプリーズ by id:nanaoku 4 キツくなっていく近代人の条件と、その近代人から落伍しそうな私自身 - シロクマの屑籠 by id:p_shirokuma 5 Claude Codeに保守しやすいコードを書いてもらうための事前準備やガードレール - くらげになりたい。 by id:wannabe-jellyfish
Real-world gen AI use cases from the world's leading organizations | Google Cloud Blog
AI is here, AI is everywhere: Top companies, governments, researchers, and startups are already enhancing their work with Google's AI solutions. Published April 12, 2024; last updated October 9, 2025. Automotive & Logistics Business & Professional Services Financial Services Healthcare & Life Sciences Hospitality & Travel Manufacturing, Industrial & Electronics Media, Marketing & Gaming Public Sec
GitHub Copilot CLI combines model families for a second opinion
When you ask a coding agent to build a data pipeline, it may not use the best structure. But what if the agent got a second opinion before it executed the plan? Today, in GitHub Copilot CLI, we’re introducing Rubber Duck in experimental mode. Rubber Duck leverages a second model from a different AI family to act as an independent reviewer, assessing the agent’s plans and work at the moments where
GitHub Spark in public preview for Copilot Pro+ subscribers - GitHub Changelog
Stuck between idea and implementation? Spending weeks on mock ups or docs that never ship? GitHub Spark takes you from idea to deployed app in minutes. Build and ship full-stack intelligent apps using natural language with access to the full power of the GitHub platform—no setup, no configuration, and no headaches. Key features Natural language to app: Describe your idea and watch Spark build it,
Last updated: Sept 2025 - If you want faster/more frequent/recent updates, buy my low cost context helper tool (cheap!!) AI Code Prep Pro How I Code with AI on a budget/free My Browser Setup: The Free AI Buffet First things first, I have a browser open loaded with tabs pointing to the free tiers of powerful AI models. Why stick to one when you can get multiple perspectives for free? My typical lin
11th March 2025 Online discussions about using Large Language Models to help write code inevitably produce comments from developers who’s experiences have been disappointing. They often ask what they’re doing wrong—how come some people are reporting such great results when their own experiments have proved lacking? Using LLMs to write code is difficult and unintuitive. It takes significant effort
Ever wanted to run a personal AI assistant that monitors your WhatsApp messages 24/7, but worried about giving it access to your entire system? Docker Sandboxes’ new shell sandbox type is the perfect solution. In this post, I’ll show you how to run NanoClaw, a lightweight Claude-powered WhatsApp assistant, inside a secure, isolated Docker sandbox. What is the Shell Sandbox? Docker Sandboxes provid
Version 1.108 is now available! Read about the new features and fixes from December. Release date: August 7, 2025 Update 1.103.1: The update adds GPT-5 prompt improvements, support for GPT-5 mini, and addresses these issues. Update 1.103.2: The update addresses these issues. Downloads: Windows: x64 Arm64 | Mac: Universal Intel silicon | Linux: deb rpm tarball Arm snap Welcome to the July 2025 rele
Advancing Windows for AI development: New platform capabilities and tools introduced at Build 2025
We’re excited to be back at Build, a special moment each year to connect with the global developer community. It’s energizing to share what we’ve been working on, and just as important, to hear how developers are using Microsoft platforms to build what’s next. At Microsoft, we believe the future of AI is being built right now across the cloud, on the edge and on Windows. Windows is, and will remai
What I learned building an opinionated and minimal coding agent
What I learned building an opinionated and minimal coding agent 2025-11-30 It's not much, but it's mine Table of contents In the past three years, I've been using LLMs for assisted coding. If you read this, you probably went through the same evolution: from copying and pasting code into ChatGPT, to Copilot auto-completions (which never worked for me), to Cursor, and finally the new breed of coding
What We’ve Learned From A Year of Building with LLMs – Applied LLMs
A practical guide to building successful LLM products, covering the tactical, operational, and strategic. It’s an exciting time to build with large language models (LLMs). Over the past year, LLMs have become “good enough” for real-world applications. And they’re getting better and cheaper every year. Coupled with a parade of demos on social media, there will be an estimated $200B investment in AI
What I learned building an opinionated and minimal coding agent
What I learned building an opinionated and minimal coding agent 2025-11-30 It's not much, but it's mine Table of contents In the past three years, I've been using LLMs for assisted coding. If you read this, you probably went through the same evolution: from copying and pasting code into ChatGPT, to Copilot auto-completions (which never worked for me), to Cursor, and finally the new breed of coding
Context switching equals friction in software development. Today, we’re removing some of that friction with the latest updates to Agent HQ which lets you run coding agents from multiple providers directly inside GitHub and your editor, keeping context, history, and review attached to your work. Copilot Pro+ and Copilot Enterprise users can now run multiple coding agents directly inside GitHub, Git
From pixels to characters: The engineering behind GitHub Copilot CLI’s animated ASCII banner
Most people think ASCII art is simple, and a nostalgic remnant of the early internet. But when the GitHub Copilot CLI team asked for a small entrance banner for the new command-line experience, they discovered the opposite: An ASCII animation in a real-world terminal is one of the most constrained UI engineering problems you can take on. Part of what makes this even more interesting is the moment
Software collaboration keeps evolving. With Continuous AI, GitHub Next are exploring how LLMs can help teams with documentation, quality, triage, and more. Agentic Workflows is a follow‑up exploration: a research demonstrator focused on expressing repository‑level behaviors in natural language and running them on GitHub. Agentic Workflows is not a product and not even a technical preview; it's a v
【2026年3月更新】Claude Codeを学ぶためにおすすめのサイトや動画まとめ - Qiita
「Claude Codeを使ってみたいけど、どこから手をつければいいかわからない…」と悩んでいませんか？ 2026年に入って、Claude Codeは一気に注目度が上がりました。エンジニアだけでなく、非エンジニアの方にも広がりつつあるツールです。でも、情報が英語だったり、記事が多すぎて取捨選択が難しかったりと、学習のスタート地点で止まってしまう人も少なくないと思います。 私自身も最初はどこから始めていいかわからず、さまざまなサイトや動画を渡り歩いた経験があります。この記事では、そんな経験を踏まえて「本当に役立った」と感じる学習リソースを20個にしぼってご紹介します。公式ドキュメントから日本語の入門記事、動画講座まで幅広くカバーしているので、自分のレベルや目的に合ったものを選んでみてください。 この記事を読むメリット Claude Codeの学習リソースをレベル別に整理して把握できる 日本語
How I run multiple $10K MRR companies on a $20/month tech stack
Last night, I was rejected from yet another pitch night. It was just the pre-interview, and the problem wasn't my product. I already have MRR. I already have users who depend on it every day. The feedback was simply: "What do you even need funding for?" I hear this time and time again when I try to grow my ideas. Running lean is in my DNA. I've built tools you might have used, like websequencediag
📋 この記事の前提 GitHub Copilot Pro以上のサブスクリプションを契約済み AIコーディングエージェント（GitHub Copilot CLI等）を使ったことがある 前回の記事「GitHub Copilot CLIでSuperpowersスキルを導入してみた」を読んでいると理解しやすい TDD（テスト駆動開発）の基本的な考え方を知っている 結論: 自分のワークフローを組み立てる時代 先に結論を書いておく。 Everything Claude Code（ECC） と Superpowers はどちらも優秀なAIエージェントハーネスだが、性格がまったく違う。ECCは「何でも揃った総合ツールボックス」で、Superpowersは「厳格なワークフロー教官」。 どちらが上かという話ではなくて、両方使ってみて初めて「私に必要なものは何か」が見えてきた。私の場合、Superpowers
AI駆動開発に我々Webエンジニアはどう向き合うべきかという話を #devio2025 Osakaでしました | DevelopersIO
2025年9月3日に DevelopersIO 2025 Osaka が弊社大阪オフィスで開催されました。お越しくださった皆様、ありがとうございました！ 私はその中で「AI駆動開発に向けた新しいエンジニアマインドセット」というタイトルで20分の登壇をいたしました。本エントリはその内容をブログ用に再編したものです。AI駆動開発に対するWebエンジニアの不安と、それにどう向き合うべきかについて、私が調べて考えた内容をお伝えします。 自己紹介 製造ビジネステクノロジー部にて、主にバックエンドとインフラを担当するエンジニアをしています。得意領域はまずTerraform、次にEKS(Kubernetes)、その次に AWSでの生成AI(Bedrock)やサーバーレスまわりです。 Terraformに関する知見の共有やコミュニティへの貢献により、HashiCorp Ambassador に3年連続選出
Anthropicは2026年2月20日、Claude Codeデスクトップ版のアップデートを発表した。今回の更新では、デスクトップインターフェース上で開発サーバーを起動し実行中のアプリを直接プレビューする機能、ローカルの差分に対してAIがインラインでコメントを残すコードレビュー機能、GitHub CLI を利用したプルリクエストのステータス監視機能が追加された。 CI失敗の自動修正およびチェック通過後の自動マージにも対応する。また、CLIからデスクトップアプリへのセッション引き継ぎや、デスクトップからウェブ・モバイルアプリへのセッション移行が可能となった。これらの機能はすべてのユーザーに対し即日提供される。 From: Bringing automated preview, review, and merge to Claude Code on desktop 【編集部解説】 今回のアッ
December 2025 OpenAI lets users tweak ChatGPT’s energy and tone OpenAI has added new controls in ChatGPT that let users adjust the chatbot’s warmth, enthusiasm, emoji use, and formatting style. This builds on existing tone options, addressing past complaints about the AI being too sycophantic or cold. OpenAI updates ChatGPT guidelines to protect teen users OpenAI has updated its guidelines for use
An AI-native software engineer is one who deeply integrates AI into their daily workflow, treating it as a partner to amplify their abilities. This requires a fundamental mindset shift. Instead of thinking “AI might replace me” an AI-native engineer asks for every task: “Could AI help me do this faster, better, or differently?”. The mindset is optimistic and proactive - you see AI as a multiplier
January 4, 2026 AI coding assistants became game-changers in 2025, but harnessing them effectively takes skill and structure. These tools dramatically increased what LLMs can do for real-world coding, and many developers (myself included) embraced them. At Anthropic, for example, engineers adopted Claude Code so heavily that today ~90% of the code for Claude Code is written by Claude Code itself.
コーディングエージェント用のオンボーディングドキュメントを、エンジニア用のドキュメントと同一にできるのだろうか - 理系学生日記
コーディングエージェントによるコード生成の精度は結構いい感じになってきていて。GitHub CopilotとかClaude Codeとか、コーディングアシスタントだかエージェントだかがどんどん現場に入ってきています。 でも、これらのツールに「いい感じのコード」を書いてもらうには、プロジェクトの目的とかルールとか、ちゃんと伝えないといけない。いわゆる「オンボーディングドキュメント」ってやつです。 「Projects as a Code」、「Everything as a Code」 ドキュメントは読み手を想定して作るもの 生成AIの知識レベルは人間よりはるかに高い 「同一ドキュメント論」 結論：読み手に応じた最適化が必要ではないか 「Projects as a Code」、「Everything as a Code」 この話をする前に、まず最近の開発現場で起きてることを整理してみると、プロジ
AI Engine
説明 AI Engine seamlessly connects WordPress with the world’s leading AI models. Create intelligent chatbots, generate content, build AI forms, and automate tasks—all from your WordPress dashboard. You can create a chatbot to assist your visitors, answer support questions, or guide users through your products and services. Need fresh content? AI Engine can write posts in your voice, help rewrite exi
300行の失敗から学んだ、AIエージェントを自律駆動させるプロンプト設計5原則 | Wantedly Engineer Blog
シニアエンジニアが2時間かけて回答していた工数見積もりをAIエージェントDevin（Cognition社）に任せてたった5分で完了できる仕組みを作りました。GitHub IssueのURLを渡すだけでPM/PdMが読めるサマリーとエンジニアが検証できる根拠を自動生成します。 プロンプトの完成までに7回書き直しています。その中で一番大きな教訓はフィードバックを忠実に反映して300行まで膨らませた指示書がかえってAIの出力品質を劣化させてしまった経験でした。プロンプトの肥大化による品質劣化は普段の開発でも起きるオーバーエンジニアリングと同じ構造を持っていました。 本記事では試行錯誤の末にたどり着いた「AIエージェントを自律駆動させるための5つの設計原則」を解説します。プロンプト設計はコード設計と本質的に同じであるという知見はDevinに限らずあらゆるAIエージェント活用できると考えています。
GitHub - AmElmo/proofshot: Give AI coding agents eyes. Records browser sessions, captures screenshots, collects errors, and bundles proof artifacts — so humans can verify what the agent built.
Open-source, agent-agnostic CLI that gives AI coding agents eyes. Your agent builds a feature — ProofShot records video proof it works. Works with Claude Code · Cursor · Codex · Gemini CLI · Windsurf · GitHub Copilot · any agent that runs shell commands AI coding agents build UI features blind. They write code but can't verify the result looks right, works correctly, or throws no errors. ProofShot
j次のブックマーク
k前のブックマーク
lあとで読む
eコメント一覧を開く
oページを開く
Spec-Driven Development: The Waterfall Strikes Back
Coding Agentについてのまとめ (2026年1月)
Manage agent skills with GitHub CLI - GitHub Changelog
Test-Driven Development with an LLM for Fun and Profit
What makes Claude Code so damn good (and how to recreate that magic in your agent)!?
March 2025 (version 1.99)
Opus 4.5 is going to change everything
The Death of the Stubborn Developer
今週のはてなブログランキング〔2025年6月第2週〕 - 週刊はてなブログ
My AI Code Prep & Cline Workflow for Budget Coding/Debugging (Part 1)
Here’s how I use LLMs to help me write code
Run NanoClaw in Docker Shell Sandboxes | Docker
July 2025 (version 1.103)
Pick your agent: Use Claude and Codex on Agent HQ
GitHub Next | Agentic Workflows
Everything Claude Code vs Superpowers — AIハーネスの選び方
Claude Codeが開発ワークフローを一変—アプリプレビューからPR自動マージまでデスクトップで完結可能に
ChatGPT: Everything you need to know about the AI chatbot
The AI-Native Software Engineer
My LLM coding workflow going into 2026