LLM Advisor

An autonomous trading agent that combines statistical mean reversion with LLM-based sentiment analysis for risk management.

PythonGemini APIAlpacaPandasBacktesting

View Code

USER: Analyze SPY sentiment

AGENT: Volatility high. Reducing position size.

Backtest Sharpe

2.14

📉Max Drawdown

-8.5%

Avg Trade

+0.45%

Risk Checks

Real-time

Agentic Workflow

1. Sentiment Analysis

Every 15 minutes, the system feeds headlines and market context into Gemini 1.5 Flash. The LLM outputs a "Market State" score (Bullish/Bearish/Choppy) and a suggested risk multiplier.

2. Statistical Execution

The core engine calculates Z-scores on price action. If the Z-score exceeds thedynamically adjusted threshold (set by the Agent), it executes mean reversion trades via Alpaca.

Automated Risk Manager

Safety is paramount. The system includes hard-coded circuit breakers that override AI decisions if maximum drawdown is hit.

risk_manager.py

def check_risk_parameters(current_pnl, max_drawdown_limit):
    """
    Hard stop if we exceed daily loss limit.
    """
    if current_pnl < -max_drawdown_limit:
        logger.critical(f"Daily stop loss hit: {current_pnl}")
        return {
            "can_trade": False,
            "action": "LIQUIDATE_ALL",
            "reason": "MAX_DRAWDOWN_HIT"
        }
    
    # ... other checks (exposure, volatility) ...
    return {"can_trade": True}