Urgent.News

What's breaking now, across thousands of outlets.

AI

New agent skill: Amazon SageMaker optimized generative AI inference for your coding agent

Amazon SageMaker optimized generative AI inference introduces the aws-ai-ml skill through the Agent Toolkit for AWS, giving coding agents like Kiro, Claude Code, and Codex deep expertise in inference optimization and benchmarking. Describe what you want, and your agent generates executable SageMaker Python SDK v3 code to benchmark, recommend, and compare deployments.

Amazon SageMaker AI has introduced a new skill, the aws-ai-ml skill, designed to help coding agents such as Kiro, Claude Code, and Codex optimize inference performance. This skill plugs into any coding agent that supports the Model Context Protocol (MCP), transforming it into an expert in SageMaker AI inference optimization.

With this skill, agents can benchmark endpoints, recommend deployment configurations, compare performance runs, and generate executable SageMaker Python SDK v3 code on behalf of the user. The skill is available through the Agent Toolkit for AWS, which can be installed on a local machine or within an Amazon SageMaker Studio JupyterLab space.

To use the skill, users need to install the Agent Toolkit for AWS and then install the aws-ai-ml skill. Once installed, users can start by describing their intent in natural language, allowing the agent to produce executable code that meets their requirements. The agent asks targeted questions, generates code based on real benchmarks and performance data, and adapts to the user's business constraints.

The aws-ai-ml skill supports various serving modes, including real-time, batch, and asynchronous, and provides on-demand and reserved capacity, heterogeneous instances, VPC isolation, automatic scaling, and integration with SageMaker AI training paths. Users need AWS credentials with permissions to call SageMaker AI APIs, and the skill generates code that runs under these credentials.

Once installed, users can use the skill through their coding agent or within an Amazon SageMaker Studio JupyterLab space. The skill helps bridge the gap between understanding the desired outcome and deploying the appropriate infrastructure, allowing users to focus on their use case and receive executable code that they can review, modify, and run.

Written by urgent.news from AWS Machine Learning's reporting — not their text. Machine-written — may contain errors; check the original before relying on it.

Read the original at aws.amazon.com →

More in AI

More from Monday 5 October →