Amazon SageMaker Unified Studio - Autopilot & Model Monitor

Yes, you can still run Amazon SageMaker Autopilot and SageMaker Model Monitor jobs with the new Amazon SageMaker Unified Studio, but there are some changes to be aware of:

For Autopilot: The Autopilot UI has been integrated into the Amazon SageMaker Canvas application in the updated Studio experience. If you want to continue using Autopilot's AutoML capabilities via a user interface, you'll need to use the SageMaker Canvas application. This provides a no-code AutoML experience for tasks such as data preparation, feature engineering, algorithm selection, training, tuning, and inference.

If you prefer to use Autopilot as you did before, you have two options:

1. You can continue using the Autopilot UI in Studio Classic (the previous Studio experience).
2. If you have coding experience, you can use all API references in any supported SDK for technical implementation of Autopilot, regardless of which Studio version you're using.

For Model Monitor: SageMaker Model Monitor continues to be available in the new Unified Studio. You can still use it to automatically monitor your machine learning models in production. Model Monitor supports monitoring for single models and inference pipelines, allowing you to detect data drift, model quality issues, bias drift, and feature attribution drift.

When migrating to the new Unified Studio, you may need to update your permissions and VPC configurations to ensure proper functionality of these services. It's recommended to test your configurations in a test domain before fully migrating your existing domain to the new Studio experience.

Remember that while the UI for some features has changed, the core functionalities of Autopilot and Model Monitor remain available, either through new interfaces or existing APIs.

Sources
SageMaker Autopilot - Amazon SageMaker AI
Automated ML, no-code, or low-code - Amazon SageMaker AI
Migrate the UI from Studio Classic to Studio - Amazon SageMaker AI
Data and model quality monitoring with Amazon SageMaker Model Monitor - Amazon SageMaker AI
Model Monitor FAQs - Amazon SageMaker AI

Yes, you can continue using both SageMaker Autopilot and Model Monitor functionalities in the new Unified Studio environment, but there are some changes to be aware of. The Autopilot UI has been integrated into the Amazon SageMaker Canvas application, providing a no-code AutoML experience for tasks like data preparation, feature engineering, algorithm selection, training, tuning, and inference.

For Model Monitor, the functionality remains fully available in the Unified Studio, allowing you to automatically monitor machine learning models in production. The system can detect quality deviations, data drift, and provide alerts with just a few clicks. A recent enhancement even allows running single execution monitoring jobs on-demand for quick troubleshooting purposes. Model Monitor supports monitoring in four key areas: data quality, model quality, model bias drift, and explainability. However, it's important to note that Model Monitor currently only supports endpoints hosting single models and does not support monitoring multi-model endpoints.

Amazon SageMaker Studio: The First Fully Integrated Development Environment For Machine Learning