The article presents a project where the author developed a causal AI model aimed at identifying the real drivers behind stock drawdowns. Using historical data, the model was trained to analyze various factors that could lead to significant declines in stock prices. The author emphasizes the importance of understanding causality rather than mere correlations, as this approach can yield insights that help investors make better decisions. The model incorporates data from multiple sources, including economic indicators and market sentiment. It employs advanced machine learning techniques to sift through vast amounts of information, identifying patterns that traditional analysis might miss. The author outlines the methodology, detailing how they selected variables and the reasoning behind their choices. This transparency is key for anyone interested in replicating the model or applying similar techniques to their own analysis. Key findings indicate that certain economic signals, such as changes in interest rates or shifts in consumer behavior, often precede drawdowns. The author provides specific examples to illustrate how these factors played out in historical events. This level of detail offers practical value for investors seeking to mitigate risk. The overall tone is analytical, focusing on the model's potential applications and implications for future trading strategies.