{
    "examples": [
        {
            "task": "Create a Monte Carlo simulation for stock price forecasting",
            "domain": "quantitative_analysis",
            "input": {
                "historical_data": "3 years of daily closing prices",
                "forecast_period": "30 days",
                "volatility_method": "historical"
            },
            "output": {
                "code": """import numpy as np\nimport pandas as pd\n\ndef monte_carlo_simulation(prices, days=30, simulations=1000):\n    # Calculate returns\n    returns = prices.pct_change().dropna()\n    mean_return = returns.mean()\n    std_dev = returns.std()\n    \n    # Generate random returns\n    random_returns = np.random.normal(mean_return, std_dev, (days, simulations))\n    \n    # Calculate future prices\n    last_price = prices.iloc[-1]\n    future_prices = last_price * (1 + random_returns).cumprod()\n    \n    return future_prices\n""",
                "analysis": {
                    "confidence": 0.85,
                    "risk_profile": "moderate",
                    "computational_complexity": "medium"
                }
            }
        },
        {
            "task": "Optimize a portfolio using mean-variance optimization",
            "domain": "quantitative_analysis",
            "input": {
                "assets": ["AAPL", "GOOGL", "MSFT", "AMZN"],
                "risk_tolerance": 0.1,
                "expected_returns": [0.12, 0.15, 0.10, 0.13]
            },
            "output": {
                "code": """import numpy as np\nimport cvxpy as cp\n\ndef optimize_portfolio(returns, risk_tolerance):\n    n = len(returns)\n    weights = cp.Variable(n)\n    \n    # Objective: maximize return\n    objective = cp.Maximize(returns @ weights)\n    \n    # Constraints: sum of weights = 1, risk <= tolerance\n    constraints = [cp.sum(weights) == 1,\n                  cp.quad_form(weights, np.cov(returns)) <= risk_tolerance]\n    \n    prob = cp.Problem(objective, constraints)\n    prob.solve()\n    \n    return weights.value\n""",
                "analysis": {
                    "confidence": 0.9,
                    "risk_profile": "low",
                    "computational_complexity": "high"
                }
            }
        }
    ]
}