<?xml version="1.0" encoding="UTF-8"?><rss version="2.0"><channel><title>Feel Flow Inc. / Blog</title><description>Engineering and AI insights from Feel Flow — on AI Spec-Driven Development and building with AI.</description><link>https://feelflow.net/</link><language>en</language><item><title>Who Decides What, and How Does AI Execute? — Reading the Division of Labor from Anthropic&apos;s Claude Code Analysis</title><link>https://feelflow.net/en/blog/2026-06-anthropic-claude-code-human-ai-division/</link><guid isPermaLink="true">https://feelflow.net/en/blog/2026-06-anthropic-claude-code-human-ai-division/</guid><description>Anthropic&apos;s Claude Code usage analysis reveals a division of labor: humans set the goal, constraints, and definition of done; AI handles exploration, editing, and execution. From official data on ~400,000 sessions, here&apos;s what engineers should hold onto in the AI era.</description><pubDate>Wed, 24 Jun 2026 13:02:18 GMT</pubDate><category>Claude Code</category><category>Anthropic</category><category>AI Agents</category><category>AI Spec-Driven Development</category><category>AI Coding</category><category>Development Process</category></item><item><title>Claude Code in Large Codebases: Best Practices and Where to Begin</title><link>https://feelflow.net/en/blog/2026-05-claude-code-large-codebases-best-practices/</link><guid isPermaLink="true">https://feelflow.net/en/blog/2026-05-claude-code-large-codebases-best-practices/</guid><description>Anthropic&apos;s guide to running Claude Code in large codebases is a practical starting point for organizations adopting AI coding at scale. We break down Agentic Search, the harness around the model (CLAUDE.md, Hooks, Skills, Plugins, MCP, LSP, Subagents), three design patterns, and where to begin.</description><pubDate>Tue, 19 May 2026 00:00:00 GMT</pubDate><category>Claude Code</category><category>Anthropic</category><category>AI Agents</category><category>AI Coding</category><category>Large Codebases</category><category>Context Engineering</category><category>CLAUDE.md</category><category>MCP</category><category>LSP</category><category>Subagents</category><category>Best Practices</category><category>Generative AI</category></item><item><title>Why AI Spec-Driven Development Was Born — Its Originator on the Origin and the Road to Proof</title><link>https://feelflow.net/en/blog/2026-05-why-ai-spec-driven-was-born/</link><guid isPermaLink="true">https://feelflow.net/en/blog/2026-05-why-ai-spec-driven-was-born/</guid><description>I used to think &apos;letting AI build software is impossible.&apos; Feel Flow CTO Futoshi Okazaki looks back on why he changed his mind — the origin of AI Spec-Driven Development and the numbers that proved it out on our own SaaS.</description><pubDate>Mon, 18 May 2026 00:00:00 GMT</pubDate><category>AI Spec-Driven Development</category><category>AI Development</category><category>AI Coding</category><category>AI Agents</category><category>Methodology</category><category>Software Development</category><category>Context Engineering</category></item><item><title>The Development Revolution of the AI Era: Why Documentation Is Better When There&apos;s Less of It</title><link>https://feelflow.net/en/blog/2025-07-ai-driven-design/</link><guid isPermaLink="true">https://feelflow.net/en/blog/2025-07-ai-driven-design/</guid><description>In 2025, software development has hit a major turning point. With AI tools generating most of the code, why does the old, human-centric documentation system quietly sabotage efficiency — and what does an AI-optimized structure look like?</description><pubDate>Mon, 28 Jul 2025 00:00:00 GMT</pubDate><category>AI Development</category><category>Documentation</category><category>AI Spec-Driven Development</category><category>Context Engineering</category></item></channel></rss>