AI-DLC: Giving Structure to AI-Assisted Development
AWS's AI-DLC (AI-Driven Development Life Cycle) is an open-source set of workflow rules released by awslabs that steer AI coding agents through a disciplined software development process. It is not a tool or service but a methodology delivered as a bundle of markdown rule files that existing coding agents read and follow. The rules are placed into project instruction files such as CLAUDE.md for Claude Code, .cursor/rules/ for Cursor, .github/copilot-instructions.md for GitHub Copilot, .amazonq/rules/ for Amazon Q, or steering files for Kiro. AI-DLC addresses the problem that AI coding assistants often skip important questions like what exactly to build, why, what the risks are, and how to break down the work, resulting in fast output that solves the wrong problem. The methodology's stated tenet is "methodology first."
AI-DLC gives developers a structured, open-source workflow to prevent AI agents from solving the wrong problem.