CI/CD pipelines using SageMaker Canvas

Yes, you can integrate models created in Amazon SageMaker Canvas into your existing CI/CD processes, though SageMaker Canvas itself doesn't build complete CI/CD pipelines from scratch.

When you create ML models in SageMaker Canvas, you can register them to the SageMaker Model Registry with a single click. This registration process automatically sends model artifacts to the registry, including reference links to the model inference container, feature importance reports, training metrics, and associated charts.

Once registered in the SageMaker Model Registry, your models can be plugged into your existing model deployment CI/CD processes. The Model Registry serves as a repository that catalogs ML models, manages various versions, associates metadata, manages approval status, and facilitates deployment to production.

The approval workflow in the Model Registry can trigger model promotion pipelines - rejecting a model prevents deployment to escalated environments, while approving a model can trigger automatic copying to pre-production AWS accounts and prepare the model for inference workloads.

For more comprehensive MLOps capabilities, you can leverage other AWS services like SageMaker Pipelines, which is a purpose-built CI/CD service for ML that brings practices such as maintaining parity between development and production environments, version control, on-demand testing, and end-to-end automation.
Sources
No-code Machine Learning - Amazon SageMaker Canvas FAQs - AWS
MLOps - Amazon SageMaker AI
MLOps - Machine Learning Best Practices for Public Sector Organizations
No-code Machine Learning - Amazon SageMaker Canvas Features - AWS