AWS Machine Learning Blog

Category: Generative AI

AI Workforce: using AI and Drones to simplify infrastructure inspections

Inspecting wind turbines, power lines, 5G towers, and pipelines is a tough job. It’s often dangerous, time-consuming, and prone to human error. This post is the first in a three-part series exploring AI Workforce, the AWS AI-powered drone inspection system. In this post, we introduce the concept and key benefits. The second post dives into the AWS architecture that powers AI Workforce, and the third focuses on the drone setup and integration.

Ray jobs on Amazon SageMaker HyperPod: scalable and resilient distributed AI

Ray is an open source framework that makes it straightforward to create, deploy, and optimize distributed Python jobs. In this post, we demonstrate the steps involved in running Ray jobs on SageMaker HyperPod.

Using Large Language Models on Amazon Bedrock for multi-step task execution

This post explores the application of LLMs in executing complex analytical queries through an API, with specific focus on Amazon Bedrock. To demonstrate this process, we present a use case where the system identifies the patient with the least number of vaccines by retrieving, grouping, and sorting data, and ultimately presenting the final result.

Introducing AWS MCP Servers for code assistants (Part 1)

We’re excited to announce the open source release of AWS MCP Servers for code assistants — a suite of specialized Model Context Protocol (MCP) servers that bring Amazon Web Services (AWS) best practices directly to your development workflow. This post is the first in a series covering AWS MCP Servers. In this post, we walk through how these specialized MCP servers can dramatically reduce your development time while incorporating security controls, cost optimizations, and AWS Well-Architected best practices into your code.

Harness the power of MCP servers with Amazon Bedrock Agents

Today, MCP is providing agents standard access to an expanding list of accessible tools that you can use to accomplish a variety of tasks. In this post, we show you how to build an Amazon Bedrock agent that uses MCP to access data sources to quickly build generative AI applications.

AWS App Studio introduces a prebuilt solutions catalog and cross-instance Import and Export

In a recent AWS What’s New Post, App Studio announced two new features to accelerate application building: Prebuilt solutions catalog and cross-instance Import and Export. In this post, we walk through how to use the prebuilt solutions catalog to get started quickly and use the Import and Export feature

Build agentic systems with CrewAI and Amazon Bedrock

In this post, we explore how CrewAI’s open source agentic framework, combined with Amazon Bedrock, enables the creation of sophisticated multi-agent systems that can transform how businesses operate. Through practical examples and implementation details, we demonstrate how to build, deploy, and orchestrate AI agents that can tackle complex tasks with minimal human oversight.

Enable Amazon Bedrock cross-Region inference in multi-account environments

In this post, we explore how to modify your Regional access controls to specifically allow Amazon Bedrock cross-Region inference while maintaining broader Regional restrictions for other AWS services. We provide practical examples for both SCP modifications and AWS Control Tower implementations.

Generative AI-powered game design: Accelerating early development with Stability AI models on Amazon Bedrock

Generative AI has emerged as a game changer, offering unprecedented opportunities for game designers to push boundaries and create immersive virtual worlds. At the forefront of this revolution is Stability AI’s cutting-edge text-to-image AI model, Stable Diffusion 3.5 Large (SD3.5 Large), which is transforming the way we approach game environment creation. In this post, we explore how you can use SD3.5 Large to address practical gaming needs such as early concept art and character design.