AI Prompt Engineering Made Magic ✨
Transform any prompt into professional-grade output through Brickz! Brickz are tag words of phrases that you can drag and drop into a template to optimize your query. Intuitive brick selection and automatic two-pass optimization are all done with the help of Brickz wizard. He will analyze your code, prompt, idea etc, and produce a template and list of suggestion Brickz to use. My end goal is to speed up Model evaluations and alignment A/B by magnitudes if possible.
- Intelligent Content Analysis: Automatically detects code, workflows, data, documents, images, and conversations
- Smart Brick Suggestions: AI-powered recommendations based on content type
- Humorous Commentary: TARS-like personality with 85% humor setting
- Easter Eggs: Hidden interactions and witty responses
- Cutting-Edge Design: Ocean blue, jet yellow, and midnight black color scheme
- Interactive Animations: Bubble effects, floating wizard, liquid glass morphism
- Mac-Style Navigation: Bottom dock with magnification effects
- Progress Animations: Engaging circles with humorous commentary
- PSE(Perspective Shift Effect) Enhancement: Additional output pruning with PSE for optimal code refinement
- Always-On Processing: Users see only the final optimized output
- Content-Aware Templates: Different approaches for code, conversations, and workflows
- Production Ready: Professional-grade prompts automatically
- Six Categories: Styles, Goals, Scopes, Personas, Formats, Contexts
- Smart Selection: Content-aware brick suggestions
- Custom Creation: Guidance for personal bricks
- Professional Colors: Bright pastels for visual organization
Beautiful glassmorphism design with interactive elements
AI assistant providing intelligent suggestions
Engaging progress circles with humor and real-time updates
- Python 3.8+
- Node.js (optional for future enhancements)
-
Clone the repository
git clone https://github.com/tylerbessire/prompt-brickz.git cd prompt-brickz -
Set up virtual environment
python -m venv venv source venv/bin/activate # On Windows: venv\Scripts\activate
-
Install dependencies
pip install -r requirements.txt
-
Configure API keys (optional)
cp .env.example .env # Edit .env with your API keys -
Run the application
python app.py
-
Open your browser Navigate to
http://localhost:5002
# Upload your Python script
# Wizard suggests: Pythonic + Optimize + Function + Senior Engineer
# Result: Professional, optimized code with best practices# Paste your automation workflow
# Wizard suggests: Structured + System + Consultant + Step-by-Step
# Result: Enterprise-ready process documentation
# Upload your CSV or analysis request
# Wizard suggests: Verbose + Research + Detailed + Educational
# Result: Comprehensive insights and explanations
- Modern HTML5/CSS3: Glassmorphism effects with backdrop blur
- Vanilla JavaScript: No framework dependencies for speed
- Responsive Design: Mobile-first approach
- Progressive Enhancement: Works without JavaScript
- Flask Application: Lightweight Python web framework
- Modular Design: Wizard, Bricks, and Optimizer components
- API Integration: Support for OpenAI, Anthropic, and Gemini
- Two-Pass System: Backend optimization for better results
- BrickzWizard: Content analysis/User guidance
- TwoPassOptimizer: PSE enhancement engine
- BrickLibrary: Modular prompt components
- Glassmorphism UI: Modern visual effects
- Glassmorphism Effects: Frosted glass aesthetic with blur effects
- Interactive Animations: Hover effects and micro-interactions
- Color Psychology: Orange for energy, blue for trust, yellow for creativity
- Typography: Inter for UI, JetBrains Mono for code
- Zero Learning Curve: Intuitive drag-and-drop interface
- Immediate Feedback: Real-time wizard commentary
- Progressive Disclosure: Features revealed as needed
# Multiple AI providers supported
ANTHROPIC_API_KEY=your_key_here
OPENAI_API_KEY=your_key_here
GEMINI_API_KEY=your_key_hereCreate personalized prompt modifiers through guidance:
- Styles: How should it be written?
- Goals: What should it achieve?
- Scopes: What level of detail?
- Personas: From whose perspective?
- Formats: How should it be structured?
- Contexts: In what situation?
- Code Files: .py, .js, .html, .css, .yml
- Documents: .pdf, .txt, .md
- Data: .csv, .json, .xlsx
- Images: Visual content analysis
- Any Format: Wizard adapts to content
- Local Processing: No data sent to third parties EVER
- API Key Protection: Environment variables for sensitive data
- No Logging: Personal information never stored
- Open Source: Full transparency in code
- Voice integration with OpenAI Realtime API
- Advanced file format support
- Collaborative brick sharing
- Performance analytics dashboard
- Plugin system for custom analyzers
- Team collaboration features
- Advanced export formats
- Integration with popular tools
- Self-improving brick suggestions
- Advanced AI model switching
- Enterprise features
- Mobile app companion
We welcome contributions! Please see our Contributing Guidelines for details.
- Fork the repository
- Create a feature branch:
git checkout -b feature-name - Make your changes
- Add tests if applicable
- Submit a pull request
- Python: Follow PEP 8
- JavaScript: Use ES6+ features
- CSS: BEM methodology
- Comments: Explain the why, not the what
This project is licensed under the MIT License - see the LICENSE file for details.
- TARS: Inspiration for the wizard personality
- PSE Research: Foundation for optimization techniques
- Glassmorphism: Modern UI design principles
- Open Source Community: For tools and inspiration
- Documentation: GitHub Wiki
- Issues: GitHub Issues
- Discussions: GitHub Discussions
- Email: tylerbessire@gmail.com
Built with ❤️ by Tyler Bessire and Claude
Making AI prompt engineering accessible to everyone