Search AWS Educational Content

Join us as we explore MCP servers and optimization techniques. In this episode, we'll dive into three essential libraries: * The CFM Tips MCP * Cost Optimization MCP * Pricing MCP Learn how these tools work together to enhance secure computation and optimization in distributed environments. Perfect for developers and architects interested in MCP technology and cloud optimization strategies

AWS and Cerebras announced a collaboration to set a new standard for AI inference speed and performance in the Cloud, which will be available through Amazon Bedrock. The solution combines AWS Trainium3-powered servers, Cerebras CS-3 systems, and Elastic Fabric Adapter (EFA) networking. The Trainium3 + CS-3 solution enables “inference disaggregation,” a technique which separates AI inference into two stages: prompt processing, or “prefill,” and output generation, or “decode.

Join AWS She Builds Tech Skills host Brittany Wolfrom and guest expert Neelam Koshiya will take viewers on a comprehensive journey from AI experimentation to enterprise-grade deployment. As AI agents become critical business assets, learn the proven strategies and AWS services that transform fragile prototypes into robust, scalable production systems that can handle real-world demands.

Hear from the leaders behind Aurora as they share an engaging retrospective of their groundbreaking journey. This exclusive session features candid stories from Swami Sivasubramanian, Yan Leshinsky, Grant McAlister, and Raman Mittal as we celebrate a decade of Aurora. Through firsthand accounts and interactive discussions, discover the engineering decisions, architectural pivots, and lessons learned that transformed Aurora into AWS fastest-growing service.

Amazon SageMaker HyperPod removes the undifferentiated heavy lifting involved in building generative AI models. It helps quickly scale model development tasks such as training, fine-tuning, or inference across a cluster of hundreds or thousands of AI accelerators.

Discover how startup AI Hay from Ho Chi Minh City, Vietnam is building an AI-powered knowledge discovery platform on AWS that enables social, community-driven, generative search. AI Hay was selected for the 2024 cohort of the AWS Generative AI Accelerator, providing them credits and support to accelerate their mission. Learn more about the AWS Generative AI Accelerator: https://aws.amazon.com/startups/programs/generative-ai?

Full Episode: http://go.aws/47tFYrc Step into the heart of Sydney, where the familiar scent of fresh pages welcomes you into a Dymocks bookstore. For more than 140 years, Dymocks has been a beloved destination for readers, a place where stories are discovered and communities are formed. But as the world of bookselling changes, Dymocks is writing a new chapter—one where tradition and technology walk hand in hand.

Dive into Amazon Simple Email Service (SES) with this comprehensive six-part technical series. Based on our popular SES workshop, this series guides you through essential implementations from domain verification to template personalization, designed for developers and solution architects. Follow hands-on demonstrations covering identity management, sending methods, configuration sets, list management, and email templating - everything you need to build a robust email solution with Amazon SES.

Discover how startup Hero Guest from Mexico City, Mexico is using generative AI on AWS to transform hospitality and service industry employees training through personalized, AI-powered learning experiences. Hero Guest was selected for the 2024 cohort of the AWS Generative AI Accelerator, providing them credits and support to accelerate their mission. Learn more about the AWS Generative AI Accelerator: https://aws.amazon.com/startups/programs/generative-ai?

Amazon EKS Auto Mode fully automates Kubernetes cluster management for compute, storage, and networking on AWS. In this session, discover how EKS Auto Mode reduces operational complexity through automatically provisioned infrastructure, managed core add-ons, streamlined upgrades, and seamless integration with AWS services. EKS Auto Mode continuously selects optimal EC2 instance types, dynamically scales resources, and optimizes costs to efficiently utilize compute.

Full Episode: https://www.youtube.com/watch?v=hPHFcTH8mD8&list=PLhr1KZpdzukevIWxQPbYmL9XWyBgj9xbz Step into the heart of Sydney, where the familiar scent of fresh pages welcomes you into a Dymocks bookstore. For more than 140 years, Dymocks has been a beloved destination for readers, a place where stories are discovered and communities are formed. But as the world of bookselling changes, Dymocks is writing a new chapter—one where tradition and technology walk hand in hand.

Learn how to build a complete video moderation system using AWS Lambda Durable Functions in just 40 minutes! In this hands-on tutorial, we'll walk you through building a production-ready video content moderation service using AWS Lambda Durable Functions.