We're excited to introduce AI-DLC, a methodology for structured, iterative software development with AI assistants.

The Challenge

Working with AI assistants like Claude has transformed how we write software. But with this power comes new challenges:

How do we maintain focus when context can shift at any moment?
How do we ensure quality when development speed increases dramatically?
How do we measure progress when traditional metrics no longer apply?

We built AI-DLC to address these challenges.

The Solution

AI-DLC introduces two core concepts: hats and units.

Hats

Hats represent distinct mindsets and responsibilities:

Researcher: Understand the problem before acting
Planner: Design the approach with clear steps
Builder: Execute the plan with focus
Reviewer: Validate quality and completeness

By explicitly switching between hats, you prevent context drift and ensure each phase gets proper attention.

Units

Units are focused pieces of work with clear success criteria. Breaking work into units ensures:

Progress is measurable
Scope is controlled
Quality is verifiable
Momentum is maintained

Getting Started

AI-DLC is distributed as a Claude Code plugin. Install it with:

/install-plugin thebushidocollective/ai-dlc

Then start using the hat commands to structure your workflow.

Part of Han

AI-DLC is part of the Han plugin ecosystem for Claude Code. Han provides a curated marketplace of plugins built on Bushido principles: quality, honor, and mastery.

We believe AI-assisted development deserves the same rigor and discipline as traditional software engineering - just with new tools and methods.

What's Next

This is just the beginning. We're actively developing:

More documentation and guides
Integration with CI/CD pipelines
Team collaboration features
Metrics and analytics

Follow our progress on GitHub and join the conversation.

Built with discipline. Shipped with confidence.