A deployed generative AI model predicts housing prices. Over time, market conditions change, and new types of property features become popular. The MLOps team notices that the distribution of input features (e.g., average square footage, number of new amenities) in the live prediction requests is significantly different from the data the model was originally trained on. Which Vertex AI MLOps capability is specifically designed to detect this kind of input data skew or drift, which can trigger model updates or retraining?