Amazon Web Services released the new AWS AI/ML skill for the Agent Toolkit for AWS on October 13, 2026, allowing coding agents to handle model selection, training, optimization, and deployment on Amazon SageMaker AI.
Integration and Availability
Amazon Web Services announced that the new AWS AI/ML skill is now a core skill in the Agent Toolkit for AWS. The skill works alongside other toolkit skills such as EC2 and Bedrock in a single natural-language workflow.
According to AWS, the toolkit replaces previous AWS Labs skills and plugins as a single, supported integration point with a consistent install and update path. The skill is also pre-installed into SageMaker Studio JupyterLab for use with Kiro or a coding agent of choice.
Supported Capabilities and Pricing
The company stated that it extended the SageMaker AI capability areas supported by skills. These areas include inference optimization, model customization, serverful training, MLflow experiment tracking and model lifecycle management, JumpStart model deployment and recommendations, and processing jobs.
AWS announced that the AWS AI/ML skill is available at no additional charge, though users pay for the AWS resources their agents use.
What to do
- Install the skill from the Agent Toolkit for AWS on GitHub, or use it pre-installed in SageMaker Studio JupyterLab.
Key facts and where they come from
- AWS released the new AWS AI/ML skill as a core skill in the Agent Toolkit for AWS.
We released the new AWS AI/ML skill on the Agent Toolkit for AWS.
- The toolkit replaces previous AWS Labs skills and plugins.
The toolkit is now the single, supported integration point, replacing the previous AWS Labs skills and plugins
- The skill is pre-installed in SageMaker Studio JupyterLab for Kiro or other coding agents.
The skill is also pre-installed into SageMaker Studio JupyterLab for use with Kiro or your coding agent of choice.
- The skill is available at no additional charge.
The AWS AI/ML skill is available at no additional charge; you pay only for the AWS resources your agents use.
