Category
AI駆動開発・開発生産性（Spec駆動 / Claude Code / 品質ゲート）の実践ガイド
AI駆動開発の成否は、AIに『実装』を任せつつ『仕様の決定』は人間が握れるかで決まります。本クラスタは、vibe codingの対極にあるSpec駆動開発——探索→計画→実装→検証の4フェーズ、受け入れ条件のテスト化、規約のファイル化——と、AIの速度を安全にする品質ゲート（型安全のNeverError網羅検査、ゴールデンベクタ、秘密情報・脆弱性スキャン、鍵レスCI/CD）を扱います。一人×生成AIで経済産業大臣賞のB2B SaaSや本番二重課金0件の決済基盤を作ってきた、速さと本番品質を両立させるワークフローを公開します。
4 articles in total
Foundational guide
Foundational guide (start here)
Spec-driven development × Claude Code: a production workflow that doesn't break even when you hand large implementations to AI
With spec-driven development — the opposite of vibe coding — this explains a workflow that keeps production quality even when you hand large implementations to an AI coding agent (Claude Code). Make the spec the single source of truth, have the AI 'implement' rather than 'decide,' and harden it with verification gates — it systematizes the four phases of explore→plan→implement→verify and the design of machine-checkable acceptance criteria, from real-project know-how.
Related practical articles
- Claude CodeAI駆動開発セキュリティAI
Security governance for rolling Claude Code out to an organization — permission modes, managed settings, sandboxing and CI
What to decide before handing Claude Code to a team: which of the six permission modes to allow, the deny→ask→allow evaluation order, delivering managed settings and the keys users can't override, the sandbox that is off by default, hook governance, and the CI trust trap, per the official docs as of October 2026.
17 min read - Claude CodeAI駆動開発セキュリティAI
Using third-party MCP servers safely with Claude Code — trust decisions, allowlists and managed-mcp.json
Before you connect a third-party MCP server to Claude Code: local servers run outside the sandbox, and Anthropic does not audit MCP servers. Covers .mcp.json approval, writing allowlists and denylists correctly, managed-mcp.json, and a vetting checklist, per the official docs.
11 min read - AI駆動開発型安全テストCI/CDセキュリティ
Designing quality gates for AI-driven development: enforce types, tests, static analysis, and security in CI to make AI's speed safe
An explanation of designing quality gates that keep an AI coding agent's output at production quality. Mechanically enforce type safety (mypy strict / tsc), tests, static analysis, and security scanning in pre-commit and CI, structurally eliminating humans' forgotten reviews. From exhaustiveness checking via NeverError to golden vectors, it systematizes the topic from real-project know-how of running in production with 100% test coverage.
7 min read