Topic
1442 articles found
This article is part of the "Road to Web 4.0" series. Originally published in Japanese on note.com. 代表の僕と副代表の2人。従業員ゼロ。 僕はTAKUYA。合同会社AJARA（アジャラ）の代表社員です。副代表がもう1人いて、人間同士のつながりや、AIが介入できない領域——リアルな人脈構築、対面の交渉、法的な判断——を担当しています。そしてAIエージェント組織「AEGIS」には14の部門と116体のエージェントがいます。今日は、超少人数法人×AIエージェントという働き方のリアルを全部書きます。 理
This article is part of the "Road to Web 4.0" series. Originally published in Japanese on note.com. Claude Code を毎日8時間使い続けて見つけた、公式ドキュメントに書いていない使い方。 僕はTAKUYA。116体のAIエージェント組織「AEGIS」を1人で運営しているエンジニアです。以前の記事でClaude Codeの基本的な使い方を書きましたが、今回はもっとディープな話。毎日使い込んで見つけた、10個の隠れ機能を紹介します。 プロジェクトのルートに「CLAUDE.md」を置くと、Cl
Day 8: The Art of Delegation — Python Functions & Decorators 25 min read ⏳ Prerequisite: We have broken the cycle of O(N²) in the Chakravyuha of Loops. Now, we must move from pure logic into structured action. We must modularize our architecture. The Core Directive: Function Architecture The Yield o
🚀 Introduction I recently built a simple online tool to convert PNG images to WebP — and I challenged myself to do it using only frontend technologies. No backend. No file uploads to a server. At first, it sounded easy… but there were a few interesting challenges along the way. 🤔 Why I Built This
Strategic Unionization Amid the AI Industry Downturn: A Critical Opportunity The AI industry, once buoyed by rapid growth and investor enthusiasm, is now facing a significant downturn characterized by market saturation, declining investments, and impending layoffs. This crisis, however, presents a u
The morning of January 1st, 2026, I turned 60 — a milestone that in Japan carries a significance far beyond the usual birthday fanfare. I celebrated my kanreki (還暦), one of the most meaningful longevity celebrations in Japanese culture. The word itself tells the story: kan (還) means "return" and rek
The web runs on a fundamental bargain: creators publish content, readers consume it, and somewhere in between, value flows back—through advertising, subscriptions, or traffic that converts to business opportunities. AI has upended this equation in ways we're only beginning to understand. This week b
Do you feel the same? You've been working in React (or Vue, or Angular) for years, shipping production code, wrestling with dependency arrays, wrapping vanilla JS libraries in framework-specific adapters, and wondering why your node_modules weighs more than your actual appl. Then you hear about Svel
The AI crawl-and-summarize wave has landed. Google's Gemini, OpenAI's GPT, Anthropic's Claude, Perplexity — they're all hitting your site. If you serve them HTML, they waste tokens parsing `` soup. If you serve them markdown, they get clean context immediately. Cloudflare published a guide to servin
Rotifer is a protocol where AI capabilities are treated as genes — they compete in arenas and evolve through natural selection. v0.6 makes these genes visible to the world. Before v0.6, genes existed only in the CLI. You could rotifer search and rotifer install, but there was no way to browse, compa
An AI agent asks: "What's the Svelte 5 equivalent of useEffect?" Today it has two options — scrape the page HTML and parse it, or fetch api/data.json and filter 100+ items in context. Both work ok, but they both waste tokens. WebMCP gives our AI agent a third option: call get_svelte_equivalent({ fra
Beyond Basic Types: Mastering TypeScript's Advanced Type System for Robust Applications TypeScript has become the de facto standard for building robust JavaScript applications, but many developers only scratch the surface of its type system. While string, number, and boolean are essential building b
Porting Test Drive II from SNES to PC, Part 8: Closing the first 998..1005 ownership block The previous checkpoint made frame 998 a real ownership anchor. That was useful because 998 is the first frame of the direct bridge-extracted 998..1005 block. But an anchor at the start of a block is still onl
Microsoft just open-sourced the Agent Governance Toolkit, a runtime governance platform that covers all 10 risks in the OWASP Agentic Top 10. I've spent the morning reading through the architecture, benchmarks, and OWASP compliance docs, and it's one of the most thorough agent governance framework I
When AI models and human readers encounter the Rotifer Protocol documentation, some arrive at a striking conclusion: this is distributed AGI. They're not making it up. The reasoning has a clear textual trail: our spec describes software entities with birth, growth, death, and reproduction; genes tha
We've all been there. You fire up your AI coding agent, ask it to write a migration script, and it produces something that technically works but misses every convention your team actually uses. Then you ask it to review a PR and it gives you generic advice that ignores your project's architecture en
The Goal Build a clean project structure and capture the current board boot baseline through the serial console. The Problem At first, this level looked simple: create folders But the real system was not that simple. This board is not in confirmed factory-default state. I also hit a second problem:
The Pre-Flight Checklist: 9 Things to Analyze Before Cutting Any AWS Cost Tags: aws finops sre reliability devops Last month I saved $12K/year by cleaning up AWS waste across four accounts. But before I touched a single resource, I spent two days just analyzing. Not because I'm cautious by nature —
Running one AI coding agent is productive. Running five in parallel is chaos. I've been using Claude Code daily for months. It's great — until you realize there are four other tasks sitting idle while you wait for one agent to finish refactoring a module. So you open more terminal tabs, spin up more
From Theory to Reality So far, you’ve learned what agents are, how they think, and when to use them. Now comes the turning point: Let’s build one — conceptually, step by step. No frameworks yet. No code yet. Just a clean mental model you can apply anywhere. 🎯 Goal: Create an AI agent that can Inves
