Amazon SageMaker AI launches AI agent experience for model customization

Amazon SageMaker AI Agentic Experience

Amazon SageMaker AI now offers an agentic experience that accelerates model customization from months to days or hours. This experience streamlines the entire workflow from use case definition to production deployment of high-quality models using natural language interactions with coding agents.

Key Features

• Expertise on fine-tuning for specific use cases
• Transformation to required data formats
• Comprehensive quality evaluation using LLM-as-a-judge metrics
• Flexible deployment options to Amazon Bedrock or SageMaker AI endpoints
• Reusable, editable code artifacts for transparency and reproducibility

What to do

• Install SageMaker AI skills in your IDE using the sagemaker-ai agent plugin
• Sign up for Kiro subscription and start using the agent in SageMaker Studio Notebooks
• Explore advanced customization techniques including supervised fine-tuning, Preference Optimization, and Reinforcement Learning

Regions

• US East (N. Virginia) — us-east-1
• Europe (Ireland) — eu-west-1
• US West (Oregon) — us-west-2
• Asia Pacific (Tokyo) — ap-northeast-1

Source: AWS release notes

If you need further guidance on AWS, our experts are available at AWS@westloop.io. You may also reach us by submitting the Contact Us form.