The AWS AI/ML skill is now a core feature of the Agent Toolkit for AWS, enhancing coding agent capabilities. This new skill allows agents to manage the entire machine learning lifecycle on Amazon SageMaker, including model selection, training, optimization, and deployment. It integrates seamlessly with other AWS services like EC2 and Bedrock. The Agent Toolkit is the sole supported integration point, replacing older AWS Labs skills and plugins with a streamlined installation process. The AI/ML skill is pre-installed in SageMaker Studio JupyterLab for immediate use. Its expanded capabilities include inference optimization for latency and cost, guided fine-tuning for model customization, and serverful training for both traditional and generative AI. Additionally, it supports MLflow for experiment tracking and model lifecycle management, along with JumpStart model deployment and recommendations. Processing jobs for data preparation and ETL are also managed. The AWS AI/ML skill is free to use, with users only paying for the AWS resources consumed by their agents. Users can install the skill from GitHub or access it directly within SageMaker Studio. Further details on integrating coding assistants with SageMaker AI workflows can be found in the official Amazon SageMaker AI documentation.