Upload 4 files

README.md

@@ -1,13 +1,232 @@
 ---
-title: Gcc Insurance Ai Hub
+title: GCC Insurance AI Hub
 emoji: 🏢
-colorFrom: green
-colorTo: indigo
+colorFrom: indigo
+colorTo: blue
 sdk: gradio
-sdk_version: 6.2.0
+sdk_version: 4.44.0
 app_file: app.py
 pinned: false
-short_description: 🏢 GCC Insurance AI Hub - Central navigation hub for all ins
+license: mit
 ---
 
-Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference
+# GCC Insurance AI Hub
+
+## Overview
+
+The **GCC Insurance AI Hub** is a central access point for a collection of insurance AI demonstration tools and datasets. This hub provides links and documentation for all related repositories.
+
+## Available Repositories
+
+### 1. Insurance Datasets (Synthetic)
+
+**Purpose**: Synthetic insurance datasets for testing and development
+
+**Contents**:
+- Claims data (amounts, dates, types)
+- Policy information
+- Fraud indicators
+
+**Features**:
+- Interactive data viewer
+- Download capabilities
+- Multiple dataset formats
+
+**Use Cases**:
+- Testing applications
+- Training and education
+- Prototyping analytics
+
+---
+
+### 2. Fraud Triage Sandbox
+
+**Purpose**: Rule-based fraud detection demonstration
+
+**Features**:
+- Interactive claim input
+- Risk scoring system
+- Triage recommendations
+- Configurable thresholds
+
+**Use Cases**:
+- Understanding fraud detection
+- Testing triage workflows
+- Training claims staff
+
+---
+
+### 3. IFRS 17 Claim Accrual Estimator
+
+**Purpose**: Actuarial reserve estimation under IFRS 17
+
+**Features**:
+- Chain ladder method
+- Risk adjustment
+- Present value discounting
+- Complete accrual breakdown
+
+**Use Cases**:
+- Learning IFRS 17 concepts
+- Understanding actuarial methods
+- Reserve estimation demos
+
+---
+
+### 4. Document RAG Compliance Assistant
+
+**Purpose**: Retrieval-Augmented Generation for compliance Q&A
+
+**Features**:
+- Document retrieval
+- Answer generation
+- Source transparency
+- Multiple compliance topics
+
+**Use Cases**:
+- Compliance Q&A
+- Policy guidance
+- Knowledge management
+
+---
+
+## Technology Stack
+
+- **Framework**: Gradio 4.44.0
+- **Language**: Python 3.9+
+- **Deployment**: Hugging Face Spaces
+- **Libraries**: pandas, numpy (in individual repos)
+
+## Repository Structure
+
+```
+gcc-insurance-ai-hub/
+├── app.py              # Main hub interface
+├── requirements.txt    # Python dependencies
+├── README.md          # This file
+└── model_card.md      # Detailed documentation
+```
+
+## Quick Start
+
+1. Visit this Hugging Face Space
+2. Browse available repositories
+3. Click on repository links to access demos
+4. Explore interactive features
+
+## Important Disclaimers
+
+⚠️ **All repositories in this hub:**
+
+- Use **100% synthetic data**
+- Are for **demonstration purposes only**
+- Provide **advisory outputs only**
+- Should **not be used for production**
+- Require **professional guidance for real implementations**
+
+### What This Hub Does NOT Include
+
+- Real insurer names or policies
+- Actual customer data
+- Proprietary actuarial formulas
+- KYC or sensitive fields
+- Pricing or quoting functionality
+- Production-ready code
+
+## Target Audience
+
+### Developers
+- Test insurance applications
+- Prototype workflows
+- Learn implementation patterns
+
+### Business Analysts
+- Understand insurance operations
+- Explore AI applications
+- Analyze processes
+
+### Students & Educators
+- Study insurance concepts
+- Learn AI/ML in insurance
+- Practice with realistic scenarios
+
+## Use Case Examples
+
+**Testing & Development**:
+- Use synthetic datasets to test applications
+- Prototype fraud detection workflows
+- Validate calculation logic
+
+**Training & Education**:
+- Teach insurance operations
+- Demonstrate AI capabilities
+- Explain regulatory concepts
+
+**Prototyping & Demos**:
+- Showcase potential solutions
+- Test user interfaces
+- Validate business logic
+
+## Compliance & Safety
+
+### Data Privacy
+- No real personal information
+- All data is synthetic
+- No GDPR/CCPA concerns
+
+### Security
+- No sensitive data
+- No authentication required
+- Public demonstration only
+
+### Ethics
+- Fair and unbiased examples
+- Transparent limitations
+- Clear disclaimers
+
+## Documentation
+
+Each repository includes:
+
+- **README.md**: Overview and usage
+- **model_card.md**: Technical details
+- **requirements.txt**: Dependencies
+- **Utility files**: Supporting code
+
+## Repository Links
+
+Update these links with your actual Hugging Face Space URLs:
+
+- [Insurance Datasets (Synthetic)](https://huggingface.co/spaces/YOUR_USERNAME/insurance-datasets-synthetic)
+- [Fraud Triage Sandbox](https://huggingface.co/spaces/YOUR_USERNAME/fraud-triage-sandbox)
+- [IFRS 17 Accrual Estimator](https://huggingface.co/spaces/YOUR_USERNAME/ifrs-claim-accrual-estimator)
+- [RAG Compliance Assistant](https://huggingface.co/spaces/YOUR_USERNAME/doc-rag-compliance-assistant)
+
+## Future Enhancements
+
+Potential additions:
+- Additional datasets
+- More calculators
+- Advanced ML models
+- Integration examples
+- API documentation
+
+## Version History
+
+- **v1.0.0** (January 2026): Initial release with 4 repositories
+
+## License
+
+MIT License
+
+## Author
+
+Built by Qoder for Vercept
+
+## Contact
+
+For questions or feedback, contact Vercept.
+
+---
+
+**For educational and demonstration purposes only**

app.py

@@ -0,0 +1,318 @@
+"""
+GCC Insurance AI Hub
+Central hub linking all insurance AI demonstration repositories.
+"""
+
+import gradio as gr
+
+# Repository information
+REPOS = {
+    "insurance-datasets-synthetic": {
+        "title": "📊 Insurance Datasets (Synthetic)",
+        "description": "Synthetic insurance datasets for claims, policies, and fraud indicators",
+        "url": "https://huggingface.co/spaces/YOUR_USERNAME/insurance-datasets-synthetic",
+        "features": [
+            "3 synthetic CSV datasets",
+            "Claims data with amounts and dates",
+            "Policy information",
+            "Fraud indicators",
+            "Interactive data viewer",
+            "Download capabilities"
+        ],
+        "use_cases": [
+            "Testing and development",
+            "Training and education",
+            "Prototyping analytics",
+            "Demo applications"
+        ]
+    },
+    "fraud-triage-sandbox": {
+        "title": "🔍 Fraud Triage Sandbox",
+        "description": "Rule-based fraud detection and claim triage demonstration",
+        "url": "https://huggingface.co/spaces/YOUR_USERNAME/fraud-triage-sandbox",
+        "features": [
+            "Interactive claim input",
+            "Rule-based fraud detection",
+            "Risk scoring system",
+            "Triage recommendations",
+            "Configurable thresholds",
+            "Detailed explanations"
+        ],
+        "use_cases": [
+            "Understanding fraud detection",
+            "Testing triage logic",
+            "Training claims adjusters",
+            "Workflow prototyping"
+        ]
+    },
+    "ifrs-claim-accrual-estimator": {
+        "title": "📈 IFRS 17 Claim Accrual Estimator",
+        "description": "Actuarial reserve estimation under IFRS 17 principles",
+        "url": "https://huggingface.co/spaces/YOUR_USERNAME/ifrs-claim-accrual-estimator",
+        "features": [
+            "Chain ladder method",
+            "Risk adjustment calculation",
+            "Present value discounting",
+            "Complete accrual breakdown",
+            "Multiple claim types",
+            "Interactive parameters"
+        ],
+        "use_cases": [
+            "Learning IFRS 17 concepts",
+            "Understanding actuarial methods",
+            "Reserve estimation demos",
+            "Accounting training"
+        ]
+    },
+    "doc-rag-compliance-assistant": {
+        "title": "📚 Document RAG Compliance Assistant",
+        "description": "Retrieval-Augmented Generation for compliance Q&A",
+        "url": "https://huggingface.co/spaces/YOUR_USERNAME/doc-rag-compliance-assistant",
+        "features": [
+            "Document retrieval",
+            "Answer generation",
+            "Source transparency",
+            "Multiple compliance topics",
+            "Natural language queries",
+            "Relevance scoring"
+        ],
+        "use_cases": [
+            "Compliance Q&A",
+            "Policy guidance",
+            "Training and education",
+            "Knowledge management"
+        ]
+    }
+}
+
+# Create Gradio interface
+with gr.Blocks(title="GCC Insurance AI Hub", theme=gr.themes.Soft()) as demo:
+    gr.Markdown("""
+    # 🏢 GCC Insurance AI Hub
+    
+    Welcome to the **GCC Insurance AI Demonstration Hub** - your central access point for insurance AI tools and datasets.
+    
+    ## 🎯 Purpose
+    
+    This hub provides access to a collection of **demonstration tools** for insurance operations, including:
+    - Synthetic datasets for testing
+    - Fraud detection systems
+    - Actuarial calculations
+    - Compliance assistance
+    
+    ⚠️ **Important**: All tools use **synthetic data** and are for **demonstration purposes only**.
+    
+    ---
+    """)
+    
+    # Repository 1: Datasets
+    with gr.Accordion("📊 Insurance Datasets (Synthetic)", open=True):
+        gr.Markdown(f"""
+        ### {REPOS['insurance-datasets-synthetic']['title']}
+        
+        {REPOS['insurance-datasets-synthetic']['description']}
+        
+        **Features:**
+        {chr(10).join(['- ' + f for f in REPOS['insurance-datasets-synthetic']['features']])}
+        
+        **Use Cases:**
+        {chr(10).join(['- ' + u for u in REPOS['insurance-datasets-synthetic']['use_cases']])}
+        
+        **Access:** [Open Repository]({REPOS['insurance-datasets-synthetic']['url']})
+        """)
+    
+    # Repository 2: Fraud Triage
+    with gr.Accordion("🔍 Fraud Triage Sandbox", open=False):
+        gr.Markdown(f"""
+        ### {REPOS['fraud-triage-sandbox']['title']}
+        
+        {REPOS['fraud-triage-sandbox']['description']}
+        
+        **Features:**
+        {chr(10).join(['- ' + f for f in REPOS['fraud-triage-sandbox']['features']])}
+        
+        **Use Cases:**
+        {chr(10).join(['- ' + u for u in REPOS['fraud-triage-sandbox']['use_cases']])}
+        
+        **Access:** [Open Repository]({REPOS['fraud-triage-sandbox']['url']})
+        """)
+    
+    # Repository 3: IFRS Estimator
+    with gr.Accordion("📈 IFRS 17 Claim Accrual Estimator", open=False):
+        gr.Markdown(f"""
+        ### {REPOS['ifrs-claim-accrual-estimator']['title']}
+        
+        {REPOS['ifrs-claim-accrual-estimator']['description']}
+        
+        **Features:**
+        {chr(10).join(['- ' + f for f in REPOS['ifrs-claim-accrual-estimator']['features']])}
+        
+        **Use Cases:**
+        {chr(10).join(['- ' + u for u in REPOS['ifrs-claim-accrual-estimator']['use_cases']])}
+        
+        **Access:** [Open Repository]({REPOS['ifrs-claim-accrual-estimator']['url']})
+        """)
+    
+    # Repository 4: RAG Assistant
+    with gr.Accordion("📚 Document RAG Compliance Assistant", open=False):
+        gr.Markdown(f"""
+        ### {REPOS['doc-rag-compliance-assistant']['title']}
+        
+        {REPOS['doc-rag-compliance-assistant']['description']}
+        
+        **Features:**
+        {chr(10).join(['- ' + f for f in REPOS['doc-rag-compliance-assistant']['features']])}
+        
+        **Use Cases:**
+        {chr(10).join(['- ' + u for u in REPOS['doc-rag-compliance-assistant']['use_cases']])}
+        
+        **Access:** [Open Repository]({REPOS['doc-rag-compliance-assistant']['url']})
+        """)
+    
+    gr.Markdown("""
+    ---
+    
+    ## 🛠️ Technology Stack
+    
+    All repositories are built with:
+    - **Framework**: Gradio for interactive interfaces
+    - **Language**: Python 3.9+
+    - **Libraries**: pandas, numpy for data processing
+    - **Deployment**: Hugging Face Spaces
+    
+    ## 📋 Repository Overview
+    
+    | Repository | Type | Primary Function |
+    |------------|------|------------------|
+    | **Insurance Datasets** | Data | Synthetic datasets for testing |
+    | **Fraud Triage Sandbox** | Application | Rule-based fraud detection |
+    | **IFRS Accrual Estimator** | Calculator | Actuarial reserve estimation |
+    | **RAG Compliance Assistant** | Q&A System | Document-based compliance guidance |
+    
+    ## ⚠️ Important Disclaimers
+    
+    ### Synthetic Data Only
+    - All datasets are **100% synthetic**
+    - No real customer, policy, or claim data
+    - Generated for demonstration purposes only
+    
+    ### Advisory Only
+    - All outputs are **advisory and illustrative**
+    - Not suitable for production use
+    - Not intended for actual business decisions
+    
+    ### No Real Business Logic
+    - No real insurer names or policies
+    - No actuarial formulas from real companies
+    - No KYC fields or sensitive data
+    - No pricing or quoting functionality
+    
+    ### Professional Guidance Required
+    - Consult qualified professionals for real implementations
+    - Verify all information with authoritative sources
+    - Follow regulatory requirements and standards
+    
+    ## 🎓 Educational Use
+    
+    These tools are designed for:
+    - **Learning**: Understanding insurance AI concepts
+    - **Training**: Teaching insurance operations
+    - **Prototyping**: Testing workflows and ideas
+    - **Demonstration**: Showcasing capabilities
+    
+    ## 🔒 Compliance & Safety
+    
+    All repositories follow these principles:
+    - **Privacy**: No real personal data
+    - **Security**: No sensitive information
+    - **Transparency**: Clear disclaimers and limitations
+    - **Ethics**: Fair and unbiased demonstrations
+    
+    ## 📖 Documentation
+    
+    Each repository includes:
+    - **README.md**: Overview and usage instructions
+    - **model_card.md**: Detailed technical documentation
+    - **requirements.txt**: Python dependencies
+    - **Utility files**: Supporting code and functions
+    
+    ## 🚀 Getting Started
+    
+    1. **Browse** the repositories above
+    2. **Click** on the repository links to access
+    3. **Explore** the interactive demos
+    4. **Learn** from the examples and documentation
+    
+    ## 💡 Use Case Examples
+    
+    ### For Developers
+    - Test insurance applications with synthetic data
+    - Prototype fraud detection workflows
+    - Learn actuarial calculation methods
+    - Implement RAG systems for compliance
+    
+    ### For Business Analysts
+    - Understand fraud triage processes
+    - Learn IFRS 17 measurement principles
+    - Explore compliance documentation approaches
+    - Analyze synthetic insurance data
+    
+    ### For Students & Educators
+    - Study insurance operations
+    - Learn AI/ML applications in insurance
+    - Practice with realistic (but synthetic) scenarios
+    - Understand regulatory frameworks
+    
+    ## 🔄 Updates & Maintenance
+    
+    These repositories are demonstration tools and may be updated periodically with:
+    - Bug fixes and improvements
+    - Additional features
+    - Enhanced documentation
+    - New examples and use cases
+    
+    ## 📞 Contact & Feedback
+    
+    For questions, feedback, or suggestions:
+    - Visit individual repository pages
+    - Review documentation and model cards
+    - Contact Vercept for more information
+    
+    ---
+    
+    ## 🏗️ Architecture Overview
+    
+    ```
+    GCC Insurance AI Hub (This Page)
+            |
+            ├── Insurance Datasets (Synthetic)
+            |   └── Claims, Policies, Fraud Indicators
+            |
+            ├── Fraud Triage Sandbox
+            |   └── Rule-based Detection & Triage
+            |
+            ├── IFRS 17 Accrual Estimator
+            |   └── Chain Ladder & Reserve Calculation
+            |
+            └── RAG Compliance Assistant
+                └── Document Retrieval & Q&A
+    ```
+    
+    ## 🎯 Future Enhancements
+    
+    Potential additions to this hub:
+    - Additional datasets (underwriting, claims processing)
+    - More specialized calculators
+    - Advanced ML models (with synthetic data)
+    - Integration examples
+    - API documentation
+    
+    ---
+    
+    **Built by Qoder for Vercept** | All data synthetic | Advisory only
+    
+    **Version**: 1.0.0 | **Last Updated**: January 2026
+    """)
+
+if __name__ == "__main__":
+    demo.launch()

model_card.md

@@ -0,0 +1,331 @@
+# Model Card: GCC Insurance AI Hub
+
+## Model Details
+
+### Model Description
+
+This is a **central hub interface** that provides access to a collection of insurance AI demonstration repositories. It is not a model itself, but rather a navigation and documentation portal.
+
+- **Developed by:** Qoder for Vercept
+- **Type:** Hub/Portal interface
+- **Purpose:** Central access point for insurance AI demos
+- **Framework:** Gradio
+- **License:** MIT
+
+### Model Sources
+
+- **Repository:** Hugging Face Spaces
+- **Interface:** Gradio web application
+
+## Uses
+
+### Direct Use
+
+This hub is designed for:
+
+- **Navigation**: Finding and accessing insurance AI demos
+- **Documentation**: Understanding available tools and datasets
+- **Discovery**: Exploring insurance AI capabilities
+- **Reference**: Quick access to all related repositories
+
+### Downstream Use
+
+Not applicable - this is a navigation hub, not a functional tool.
+
+### Out-of-Scope Use
+
+⚠️ **This hub should NOT be used for:**
+
+- Actual insurance operations
+- Production deployments
+- Real business decisions
+- Any purpose beyond navigation and documentation
+
+## Linked Repositories
+
+### 1. Insurance Datasets (Synthetic)
+
+**Type**: Dataset repository
+
+**Contents**:
+- Synthetic claims data
+- Synthetic policy data
+- Synthetic fraud indicators
+
+**Purpose**: Testing and development
+
+**Limitations**:
+- 100% synthetic data
+- Not representative of real distributions
+- Limited size and complexity
+
+---
+
+### 2. Fraud Triage Sandbox
+
+**Type**: Application
+
+**Method**: Rule-based fraud detection
+
+**Purpose**: Demonstration of triage workflows
+
+**Limitations**:
+- Simplified rules
+- No machine learning
+- Not suitable for production
+
+---
+
+### 3. IFRS 17 Claim Accrual Estimator
+
+**Type**: Calculator
+
+**Method**: Chain ladder + IFRS 17 components
+
+**Purpose**: Educational demonstration of reserve estimation
+
+**Limitations**:
+- Simplified assumptions
+- Synthetic development patterns
+- Not compliant with full IFRS 17
+
+---
+
+### 4. Document RAG Compliance Assistant
+
+**Type**: Q&A System
+
+**Method**: Retrieval-Augmented Generation (keyword-based)
+
+**Purpose**: Demonstration of compliance knowledge retrieval
+
+**Limitations**:
+- Synthetic compliance documents
+- Keyword matching (not semantic)
+- Not suitable for actual compliance guidance
+
+---
+
+## Hub Features
+
+### Navigation
+
+- **Repository Cards**: Overview of each repository
+- **Feature Lists**: Key capabilities of each tool
+- **Use Case Examples**: Suggested applications
+- **Direct Links**: Access to each repository
+
+### Documentation
+
+- **Technology Stack**: Common frameworks and libraries
+- **Architecture Overview**: System structure
+- **Disclaimers**: Important limitations and warnings
+- **Contact Information**: Support and feedback channels
+
+### Organization
+
+- **Categorization**: Repositories grouped by type
+- **Consistent Structure**: Uniform documentation across repos
+- **Version Tracking**: Hub and repository versions
+
+## Bias, Risks, and Limitations
+
+### Known Limitations
+
+**Hub Limitations**:
+1. **Static Links**: Repository URLs must be manually updated
+2. **No Search**: Cannot search across repositories
+3. **No Analytics**: Doesn't track usage or popularity
+4. **Manual Updates**: Requires manual maintenance
+
+**Linked Repository Limitations**:
+1. **Synthetic Data**: All data is artificial
+2. **Simplified Logic**: Real systems are more complex
+3. **No Production Use**: Not suitable for real operations
+4. **Limited Scope**: Covers only basic scenarios
+
+### Potential Risks
+
+**Misuse Risk**:
+- Users might attempt to use demo tools for production
+- Synthetic data might be mistaken for real patterns
+- Simplified logic might be considered sufficient
+
+**Expectation Risk**:
+- Users might expect production-ready code
+- Demos might set unrealistic expectations
+- Complexity of real systems might be underestimated
+
+### Recommendations
+
+Users should:
+
+- Understand all tools are **demonstrations only**
+- Never use for actual insurance operations
+- Consult professionals for real implementations
+- Recognize the gap between demos and production systems
+- Review official documentation for real standards
+
+## How to Get Started
+
+### Accessing the Hub
+
+1. Visit the Hugging Face Space
+2. Browse repository descriptions
+3. Click on repository links
+4. Explore individual demos
+
+### Using Individual Repositories
+
+1. Read the repository README
+2. Review the model card
+3. Try the interactive demo
+4. Examine the code (if interested)
+
+## Technical Specifications
+
+### Hub Architecture
+
+**Components**:
+- Gradio interface for navigation
+- Markdown documentation
+- Repository metadata
+- External links
+
+**No Computation**:
+- Hub performs no calculations
+- No data processing
+- No model inference
+- Pure navigation interface
+
+### Linked Repository Technologies
+
+**Common Stack**:
+- Python 3.9+
+- Gradio 4.44.0
+- Pandas 2.1.4
+- NumPy 1.26.2
+
+**Deployment**:
+- Hugging Face Spaces
+- CPU-only (no GPU required)
+- Public access
+
+### Compute Infrastructure
+
+**Hub Requirements**: Minimal - static interface
+
+**Individual Repository Requirements**: Vary by repository (see individual model cards)
+
+## Model Card Contact
+
+For questions or feedback, contact Vercept.
+
+## Glossary
+
+- **Hub**: Central navigation portal
+- **Repository**: Individual demo or dataset
+- **Synthetic Data**: Artificially generated data
+- **Demonstration**: Educational/illustrative tool
+- **Production**: Real-world operational use
+- **RAG**: Retrieval-Augmented Generation
+- **IFRS 17**: International accounting standard for insurance
+- **Chain Ladder**: Actuarial reserving method
+
+## Repository Comparison
+
+| Repository | Type | Complexity | Primary Use |
+|------------|------|------------|-------------|
+| **Datasets** | Data | Low | Testing/Development |
+| **Fraud Triage** | Application | Medium | Workflow Demo |
+| **IFRS Estimator** | Calculator | Medium | Education |
+| **RAG Assistant** | Q&A System | Medium | Knowledge Demo |
+
+## Maintenance & Updates
+
+### Hub Maintenance
+
+**Regular Tasks**:
+- Update repository links
+- Add new repositories
+- Refresh documentation
+- Fix broken links
+
+**Version Control**:
+- Hub version tracked in README
+- Individual repos have own versions
+- Change log maintained
+
+### Individual Repository Updates
+
+Each repository is maintained independently with:
+- Bug fixes
+- Feature enhancements
+- Documentation updates
+- Dependency updates
+
+## Best Practices
+
+### For Users
+
+1. **Start with Documentation**: Read READMEs and model cards
+2. **Understand Limitations**: Review disclaimers carefully
+3. **Explore Interactively**: Try the demos hands-on
+4. **Don't Misuse**: Never use for production
+
+### For Developers
+
+1. **Consistent Structure**: Follow established patterns
+2. **Clear Documentation**: Comprehensive READMEs
+3. **Explicit Disclaimers**: Warn about limitations
+4. **Synthetic Data**: Never use real data
+
+### For Educators
+
+1. **Set Expectations**: Explain demo vs. production
+2. **Use as Examples**: Illustrate concepts
+3. **Encourage Exploration**: Let students experiment
+4. **Discuss Limitations**: Teach critical thinking
+
+## Future Enhancements
+
+### Potential Hub Improvements
+
+1. **Search Functionality**: Search across repositories
+2. **Analytics Dashboard**: Usage statistics
+3. **Version Tracking**: Automated version display
+4. **Dependency Graph**: Show relationships between repos
+
+### Potential New Repositories
+
+1. **Underwriting Assistant**: Risk assessment demo
+2. **Claims Processing**: Workflow automation demo
+3. **Customer Service Bot**: Chatbot demonstration
+4. **Risk Modeling**: Catastrophe modeling demo
+
+## Model Card Authors
+
+Qoder (Vercept)
+
+## Disclaimer
+
+⚠️ **CRITICAL NOTICE**:
+
+This hub and all linked repositories are **demonstration tools only** using synthetic data and simplified logic. They are **not suitable for**:
+
+- Production insurance operations
+- Actual business decisions
+- Regulatory compliance
+- Financial reporting
+- Customer-facing applications
+- Any real-world insurance use
+
+**All data is synthetic. All outputs are advisory only.**
+
+**For actual insurance operations, consult qualified professionals and use production-grade systems.**
+
+---
+
+## Acknowledgments
+
+This hub and its repositories were created to demonstrate insurance AI concepts for educational purposes. They represent simplified versions of complex real-world systems and should be used accordingly.

requirements.txt

@@ -0,0 +1 @@
+gradio==4.44.0