Your coding agent becomes a SageMaker AI expert with the AWS AI/ML skill!

Hi, it's Shii-chan! Here's an announcement that makes it easier to hand machine learning work to your agent!

AWS What's New aws.amazon.com

What was announced?

According to AWS What's New, the AWS AI/ML skill is now a core skill in the Agent Toolkit for AWS. A coding agent can select, train, optimize, and deploy models on Amazon SageMaker AI in the same natural-language workflow it uses for other AWS skills like EC2 and Bedrock.

What changes

The Agent Toolkit for AWS is now the single, supported integration point, replacing the previous AWS Labs skills and plugins. You also get one consistent install and update path.

The skill is also pre-installed in SageMaker Studio JupyterLab, for use with Kiro or your coding agent of choice.

Dive Deep

The SageMaker AI areas supported by the skill have been extended:

• Inference optimization: optimize deployed models for latency, throughput, and cost
• Model customization: guided fine-tuning workflows, from use case definition through training, evaluation, and deployment
• Serverful training: for both traditional ML and generative AI
• MLflow: experiment tracking and model lifecycle management
• JumpStart: deploy pre-built models and get recommendations on the right model for your use case
• Processing jobs: data preparation and ETL on managed compute

There's no additional charge. You pay only for the AWS resources your agents use. To get started, install the skill from the Agent Toolkit for AWS on GitHub, or use the version pre-installed in SageMaker Studio JupyterLab.

Wrap-up

• The AWS AI/ML skill is now a core skill in the Agent Toolkit for AWS
• It replaces the AWS Labs skills and plugins
• It covers six areas, including inference optimization, model customization, and MLflow
• The skill itself has no additional charge

This is for anyone who wants an agent to handle their SageMaker AI work!