diff --git a/.github/dependabot.yml b/.github/dependabot.yml
new file mode 100644
index 0000000..2707605
--- /dev/null
+++ b/.github/dependabot.yml
@@ -0,0 +1,55 @@
+# Dependabot configuration for automated dependency updates
+# Documentation: https://docs.github.com/github/administering-a-repository/configuration-options-for-dependency-updates
+
+version: 2
+updates:
+  # Python dependencies via pip/uv
+  - package-ecosystem: "pip"
+    directory: "/"
+    schedule:
+      interval: "weekly"
+      day: "monday"
+      time: "03:00"
+    open-pull-requests-limit: 5
+    reviewers:
+      - "niksacdev"
+    labels:
+      - "dependencies"
+      - "python"
+    commit-message:
+      prefix: "chore"
+      prefix-development: "chore"
+      include: "scope"
+    groups:
+      development:
+        patterns:
+          - "pytest*"
+          - "mypy*"
+          - "ruff*"
+          - "black*"
+          - "pre-commit*"
+      openai:
+        patterns:
+          - "openai*"
+          - "agents*"
+      documentation:
+        patterns:
+          - "mkdocs*"
+          - "sphinx*"
+
+  # GitHub Actions
+  - package-ecosystem: "github-actions"
+    directory: "/"
+    schedule:
+      interval: "weekly"
+      day: "monday"
+      time: "03:00"
+    open-pull-requests-limit: 3
+    reviewers:
+      - "niksacdev"
+    labels:
+      - "dependencies"
+      - "github-actions"
+    commit-message:
+      prefix: "ci"
+      include: "scope"
\ No newline at end of file
diff --git a/.gitignore b/.gitignore
index b491021..69a54db 100644
--- a/.gitignore
+++ b/.gitignore
@@ -209,6 +209,49 @@ __marimo__/
 # SpecStory (AI code documentation)
 .specstory/
 
-# Application results and logs
+# ============================================================================
+# Project-Specific Ignores
+# ============================================================================
+
+# Results and output files
 results/
 console_app/results/
+loan_processing/results/
+*.result.json
+*.decision.json
+
+# Temporary files
+*.tmp
+*.temp
+*.bak
+*.swp
+*.swo
+*~
+
+# Local development
+.env.local
+.env.*.local
+local_notes.md
+scratch/
+
+# MCP Server data
+mcp_server_data/
+*.db
+*.sqlite
+
+# Generated documentation
+docs/_build/
+docs/generated/
+
+# Performance profiling
+*.prof
+*.pstats
+profile_output/
+
+# Test coverage reports (duplicates removed as they're already above)
+
+# IDE specific files
+.idea/
+.vscode/
+*.sublime-*
+.DS_Store
diff --git a/.pre-commit-config.yaml b/.pre-commit-config.yaml
new file mode 100644
index 0000000..750bdcb
--- /dev/null
+++ b/.pre-commit-config.yaml
@@ -0,0 +1,73 @@
+# Pre-commit hooks for security and code quality
+# Install: pip install pre-commit && pre-commit install
+
+repos:
+  # Security - Detect secrets
+  - repo: https://github.com/Yelp/detect-secrets
+    rev: v1.4.0
+    hooks:
+      - id: detect-secrets
+        args: ['--baseline', '.secrets.baseline']
+        exclude: .*\.lock|package-lock\.json
+
+  # Python code quality
+  - repo: https://github.com/astral-sh/ruff-pre-commit
+    rev: v0.4.4
+    hooks:
+      - id: ruff
+        args: [--fix]
+      - id: ruff-format
+
+  # Python type checking
+  - repo: https://github.com/pre-commit/mirrors-mypy
+    rev: v1.10.0
+    hooks:
+      - id: mypy
+        additional_dependencies: [types-all]
+        args: [--ignore-missing-imports]
+
+  # Check for common issues
+  - repo: https://github.com/pre-commit/pre-commit-hooks
+    rev: v4.6.0
+    hooks:
+      - id: trailing-whitespace
+      - id: end-of-file-fixer
+      - id: check-yaml
+      - id: check-added-large-files
+        args: ['--maxkb=1000']
+      - id: check-case-conflict
+      - id: check-merge-conflict
+      - id: check-json
+      - id: check-toml
+      - id: detect-private-key
+      - id: no-commit-to-branch
+        args: ['--branch', 'main']
+
+  # Markdown formatting
+  - repo: https://github.com/igorshubovych/markdownlint-cli
+    rev: v0.39.0
+    hooks:
+      - id: markdownlint
+        args: ['--fix']
+
+  # Security - Safety check
+  - repo: https://github.com/Lucas-C/pre-commit-hooks-safety
+    rev: v1.3.3
+    hooks:
+      - id: python-safety-dependencies-check
+
+# Additional local hooks
+- repo: local
+  hooks:
+    - id: no-env-files
+      name: Block .env files
+      entry: .env files must not be committed
+      language: fail
+      files: '^\.env$'
+    
+    - id: no-api-keys
+      name: Check for API keys
+      entry: 'sk-[a-zA-Z0-9]{48}|AKIA[0-9A-Z]{16}'
+      language: pygrep
+      types: [text]
+      exclude: \.env\.example|SECURITY\.md
\ No newline at end of file
diff --git a/CONTRIBUTING.md b/CONTRIBUTING.md
new file mode 100644
index 0000000..18aaa53
--- /dev/null
+++ b/CONTRIBUTING.md
@@ -0,0 +1,297 @@
+# Contributing to Multi-Agent Loan Processing System
+
+Thank you for your interest in contributing! This document provides guidelines and instructions for contributing to the project.
+
+## 🚀 Getting Started
+
+### Prerequisites
+
+- Python 3.10 or higher
+- `uv` package manager (`pip install uv`)
+- OpenAI API key (or Azure OpenAI credentials)
+
+### Development Setup
+
+1. **Fork and clone the repository**
+   ```bash
+   git clone https://github.com/your-username/multi-agent-system.git
+   cd multi-agent-system
+   ```
+
+2. **Install dependencies with uv**
+   ```bash
+   uv sync
+   ```
+
+3. **Set up environment variables**
+   ```bash
+   cp .env.example .env
+   # Edit .env with your API keys
+   ```
+
+4. **Install pre-commit hooks**
+   ```bash
+   uv pip install pre-commit
+   pre-commit install
+   ```
+
+5. **Run tests to verify setup**
+   ```bash
+   uv run pytest tests/test_agent_registry.py -v
+   ```
+
+## 📝 Development Workflow
+
+### 1. Create a Feature Branch
+
+```bash
+git checkout -b feature/your-feature-name
+```
+
+### 2. Make Your Changes
+
+Follow these guidelines:
+- Write clean, readable code following PEP 8
+- Add type hints to all functions
+- Include docstrings for modules, classes, and functions
+- Keep functions focused and small
+- Follow existing patterns in the codebase
+
+### 3. Write Tests
+
+- Add tests for new functionality
+- Ensure existing tests pass
+- Maintain >80% code coverage
+
+```bash
+# Run specific tests
+uv run pytest tests/test_your_feature.py -v
+
+# Run with coverage
+uv run pytest tests/ --cov=loan_processing --cov-report=term-missing
+```
+
+### 4. Run Quality Checks
+
+Before committing, run all quality checks:
+
+```bash
+# Linting
+uv run ruff check . --fix
+uv run ruff format .
+
+# Type checking
+uv run mypy loan_processing/
+
+# Tests
+uv run pytest tests/test_agent_registry.py tests/test_safe_evaluator.py -v
+```
+
+### 5. Commit Your Changes
+
+Write clear, descriptive commit messages:
+
+```bash
+git commit -m "feat: add income trend analysis to income agent"
+```
+
+Commit message format:
+- `feat:` New feature
+- `fix:` Bug fix
+- `docs:` Documentation changes
+- `test:` Test additions or changes
+- `refactor:` Code refactoring
+- `chore:` Maintenance tasks
+
+### 6. Push and Create PR
+
+```bash
+git push origin feature/your-feature-name
+```
+
+Then create a Pull Request on GitHub with:
+- Clear description of changes
+- Link to related issues
+- Screenshots/examples if applicable
+- Test results
+
+## 🏗️ Architecture Guidelines
+
+### Agent Development
+
+When adding new agents:
+
+1. **Create persona file**: `loan_processing/agents/agent-persona/your-agent-persona.md`
+2. **Update configuration**: Add to `loan_processing/config/agents.yaml`
+3. **Define output format**: Specify structured output requirements
+4. **Add tests**: Create `tests/test_your_agent.py`
+
+### MCP Server Development
+
+When adding MCP servers:
+
+1. **Create server module**: `loan_processing/tools/mcp_servers/your_server/`
+2. **Implement server.py**: Follow existing server patterns
+3. **Add to configuration**: Update `agents.yaml` with server details
+4. **Document tools**: List all tools the server provides
+
+## 📋 Code Style
+
+### Python Style Guide
+
+- Use `ruff` for linting and formatting
+- Follow PEP 8 with 120 character line limit
+- Use descriptive variable names
+- Add type hints for all functions
+- Write comprehensive docstrings
+
+### Example Function:
+
+```python
+def calculate_debt_to_income_ratio(
+    monthly_debt: Decimal,
+    monthly_income: Decimal,
+    include_proposed_payment: bool = True
+) -> float:
+    """
+    Calculate the debt-to-income ratio for loan qualification.
+    
+    Args:
+        monthly_debt: Total monthly debt payments
+        monthly_income: Gross monthly income
+        include_proposed_payment: Whether to include proposed loan payment
+        
+    Returns:
+        DTI ratio as a percentage (0-100)
+        
+    Raises:
+        ValueError: If monthly_income is zero or negative
+    """
+    if monthly_income <= 0:
+        raise ValueError("Monthly income must be positive")
+        
+    return float((monthly_debt / monthly_income) * 100)
+```
+
+## 🧪 Testing Guidelines
+
+### Test Structure
+
+- Unit tests: `tests/test_*.py`
+- Integration tests: `tests/test_integration_*.py`
+- Use pytest fixtures for common test data
+- Mock external dependencies
+- Test both success and failure cases
+
+### Example Test:
+
+```python
+def test_agent_creation():
+    """Test that agents are created with correct configuration."""
+    agent = AgentRegistry.create_agent("intake", model="gpt-4")
+    
+    assert agent.name == "Intake Agent"
+    assert agent.model == "gpt-4"
+    assert len(agent.mcp_servers) == 0  # Optimized for speed
+```
+
+## 📚 Documentation
+
+### Documentation Requirements
+
+- Update README.md for user-facing changes
+- Update CLAUDE.md for AI development instructions
+- Add docstrings to all new code
+- Create ADRs for architectural decisions
+- Update configuration examples
+
+### ADR Format
+
+Create `docs/decisions/adr-XXX-title.md`:
+
+```markdown
+# ADR-XXX: Title
+
+## Status
+Accepted/Proposed/Deprecated
+
+## Context
+Why this decision is needed
+
+## Decision
+What we're doing
+
+## Consequences
+What happens as a result
+```
+
+## 🐛 Reporting Issues
+
+### Bug Reports
+
+Include:
+- Python version
+- Steps to reproduce
+- Expected behavior
+- Actual behavior
+- Error messages/logs
+- Environment details
+
+### Feature Requests
+
+Include:
+- Use case description
+- Proposed solution
+- Alternative approaches considered
+- Impact on existing functionality
+
+## 🔒 Security
+
+- Never commit secrets or API keys
+- Report security issues privately (see SECURITY.md)
+- Use secure coding practices
+- Validate all inputs
+- Follow principle of least privilege
+
+## 📊 Performance
+
+- Profile code for bottlenecks
+- Optimize database queries
+- Use async operations where appropriate
+- Cache expensive computations
+- Monitor memory usage
+
+## 🎯 Pull Request Checklist
+
+Before submitting a PR, ensure:
+
+- [ ] Code follows style guidelines
+- [ ] Tests pass locally
+- [ ] Coverage maintained >80%
+- [ ] Documentation updated
+- [ ] Pre-commit hooks pass
+- [ ] No hardcoded values
+- [ ] No sensitive data exposed
+- [ ] Commit messages follow format
+- [ ] PR description is complete
+
+## 💬 Getting Help
+
+- Open an issue for bugs/features
+- Check existing issues first
+- Join discussions in issues/PRs
+- Review documentation thoroughly
+- Ask questions - we're here to help!
+
+## 🏆 Recognition
+
+Contributors will be recognized in:
+- README.md contributors section
+- Release notes
+- Project documentation
+
+Thank you for contributing to make loan processing more efficient and accessible!
+
+---
+
+*By contributing, you agree that your contributions will be licensed under the MIT License.*
\ No newline at end of file
diff --git a/SECURITY.md b/SECURITY.md
new file mode 100644
index 0000000..2bf5ed8
--- /dev/null
+++ b/SECURITY.md
@@ -0,0 +1,123 @@
+# Security Policy
+
+## 🔒 Security Best Practices
+
+This repository demonstrates secure coding practices for AI-powered loan processing systems.
+
+### API Key Security
+
+**NEVER commit API keys or secrets to version control!**
+
+1. Copy `.env.example` to `.env`
+2. Add your API keys to `.env` 
+3. Ensure `.env` is in `.gitignore` (already configured)
+4. Use environment variables for all sensitive configuration
+
+### Data Privacy
+
+This system implements privacy-by-design principles:
+
+- **No Real SSNs**: The system uses UUID-based `applicant_id` instead of SSNs
+- **No PII in Logs**: Sensitive data is never logged
+- **Secure Parameters**: All MCP server calls use secure identifiers
+- **Data Minimization**: Only necessary data is collected and processed
+
+### Secure Development
+
+- All dependencies are managed through `uv` with lock files
+- Regular security audits with `uv pip audit`
+- Comprehensive test coverage (>83%)
+- Type checking with mypy
+- Linting with ruff
+
+## 🐛 Reporting Security Vulnerabilities
+
+We take security seriously. If you discover a security vulnerability, please follow responsible disclosure:
+
+1. **DO NOT** create a public GitHub issue
+2. Email security concerns to: [your-email@example.com]
+3. Include:
+   - Description of the vulnerability
+   - Steps to reproduce
+   - Potential impact
+   - Suggested fix (if any)
+
+We will acknowledge receipt within 48 hours and provide a detailed response within 5 business days.
+
+## 🛡️ Security Features
+
+### Authentication & Authorization
+- API key-based authentication for AI services
+- Secure MCP server communication
+- Role-based agent permissions
+
+### Data Protection
+- Applicant IDs (UUIDs) instead of SSNs
+- Encrypted sensitive data in transit
+- Audit logging for compliance
+
+### Input Validation
+- Pydantic models for data validation
+- Regex patterns for format verification
+- Boundary checking for numerical inputs
+
+## 📋 Security Checklist for Contributors
+
+Before submitting a PR:
+
+- [ ] No hardcoded credentials
+- [ ] No real PII in test data
+- [ ] All inputs validated
+- [ ] Error messages don't leak sensitive info
+- [ ] Dependencies updated and audited
+- [ ] Tests pass with >80% coverage
+
+## 🔄 Dependency Management
+
+Regular dependency updates:
+```bash
+# Update dependencies
+uv sync
+
+# Audit for vulnerabilities
+uv pip audit
+
+# Update to latest secure versions
+uv update
+```
+
+## 📜 Compliance
+
+This system is designed with compliance in mind:
+
+- **FCRA**: Fair Credit Reporting Act compliance
+- **ECOA**: Equal Credit Opportunity Act adherence  
+- **GDPR**: Privacy-by-design principles
+- **SOC2**: Audit trail and access controls
+
+## 🚨 Known Security Considerations
+
+1. **MCP Servers**: Currently run on localhost without authentication. In production:
+   - Add authentication to MCP servers
+   - Use TLS for MCP communications
+   - Implement rate limiting
+
+2. **API Keys**: Currently single API key for all agents. In production:
+   - Use separate keys per agent
+   - Implement key rotation
+   - Add usage monitoring
+
+3. **Audit Logging**: Basic logging implemented. In production:
+   - Send logs to SIEM
+   - Implement tamper-proof audit trail
+   - Add compliance reporting
+
+## 📞 Contact
+
+Security Team: [your-email@example.com]
+Project Maintainer: [your-github-username]
+
+---
+
+*Last Updated: August 2025*
+*Security Policy Version: 1.0*
\ No newline at end of file