You work at a bank where you need to develop a credit risk model to support loan application decisions for applicants. To handle the complexity and non-linearity of the data, you decide to implement the model using a neural network in TensorFlow. Regulatory requirements mandate that you must be able to explain the model’s predictions based on its features to ensure transparency and fairness. Additionally, once the model is deployed, it is crucial to monitor the model’s performance over time to ensure it remains accurate and reliable. Vertex AI is chosen for both model development and deployment. What should you do?