Disciplined AI Development
Systematic constraints and behavioral enforcement for AI collaboration
Prompt Formats
Each format emphasizes different domains. XML/JSON provide code-like structure that may strengthen code generation. Markdown works well for documentation. PAG provides explicit validation gates for CLI agents.
| Format | Best For | Characteristics |
|---|---|---|
| Markdown (.md) | Documentation, web browser AI | Human-readable, AI continues structure naturally |
| XML (.xml) | Machine parsing, structured prompts | Explicit tags, code-like structure |
| JSON (.json) | Configuration, programmatic access | Strict syntax, data exchange |
| PAG (.pag) | CLI agents, explicit constraints | Validation gates, ALWAYS/NEVER rules |
Project State Extraction
Use the included project extraction tool to generate structured snapshots of your codebase for sharing with AI systems.
Configuration Optionsα
Available extraction settings:
SEPARATE_FILES = False
Single THE_PROJECT.md file (recommended for small codebases)
SEPARATE_FILES = True
Multiple files per directory (recommended for large codebases)
INCLUDE_PATHS
Directories and files to analyze
EXCLUDE_PATTERNS
Skip cache directories, build artifacts, generated files
Output Featuresβ
What the extraction tool provides:
- Complete file contents with syntax highlighting
- File line counts with architectural warnings (⚠️ for 140-150 lines, ‼️ for >150 lines)
- Tree structure visualization
- Ready-to-share format for AI context
Usageγ
Run the extraction tool:
Usagepython scripts/project_extract.py
Downloadδ
Get the extraction tool from the repository:
LLM Model Evaluation
All models were asked the exact same questions using the methodology documents as file uploads. This evaluation focuses on methodology understanding and operational behavior.
Evaluation Coverageε
The Q&A documents capture responses across:
Workflow Patterns
Methodology understanding and workflow execution
Context Retention
Collaborative interaction and memory across sessions
Communication Adherence
AI preference compliance and response quality
Phase 0 Requirements
Project initialization and infrastructure understanding
Quality Enforcement
Violation handling and constraint enforcement
User Experience
Behavior across different skill levels
Tested Modelsζ
Models evaluated with identical methodology questions:
Example Projects
Projects developed using this methodology.
Project Galleryη
These projects demonstrate the methodology in practice:
Discord Bot Template
Production-ready bot with plugin architecture, security, API management. 46 files, all under 150 lines.
PhiCode Runtime
Programming language runtime with transpilation, caching, security validation. 70+ modules.
PhiPipe
CI/CD regression detection with statistical analysis and GitHub integration. Go-based service.