Search AWS Educational Content

Samsung operates a massive Kubernetes environment on Amazon EKS, using Cast AI across CPU and GPU workloads for unified infrastructure optimization. Samsung engineers reveal how they deployed AI agents that continuously optimize cloud infrastructure in real time. Beyond Spot Instance savings, Cast AI's binpacking optimization delivers remarkable efficiency gains.

Guy Ben-Baruch, Principal Solution Architect at AWS, provides a comprehensive overview of the AWS AI stack, from infrastructure to applications. AWS provides custom AI chips (Trainium, Inferentia, Graviton), GPU partnerships with Nvidia and other established chipset vendors; and the new AWS AI Factories that can bring compute capabilities on-premise to telco data centers.

AWS DevOps Agent is a frontier agent that resolves and proactively prevents incidents, continuously improving reliability and performance. AWS DevOps Agent investigates incidents and identifies operational improvements as an experienced DevOps engineer would: by learning your resources and their relationships, working with your observability tools, runbooks, code repositories, and CI/CD pipelines, and correlating telemetry, code, and deployment data across all of them to understand the...

Ready to modernise your incident response? Learn how Infor accelerated their security operations using AWS Security Incident Response service. Through Infor's implementation journey, learn how to automate investigation and remediation while maintaining consistency at scale. We'll cover service integration with Security Hub and GuardDuty, automated playbook execution, and cross-account coordination.

AWS Backup's Multi-party approval for logically air-gapped vaults enables organizations to require multiple authorized approvers before critical backup operations can be executed. This distributed approval process helps protect against both inadvertent and malicious events by preventing any single person from making unilateral changes to backup access.

To overcome the performance and scale limitations of relational databases, AWS built Amazon DynamoDB to deliver consistent single-digit millisecond performance at any scale for the most demanding applications on the planet. In this session, learn about the architecture choices for Amazon DynamoDB. Gain a better understanding of when to use DynamoDB and why DynamoDB is used by over one million AWS customers, and powers hundreds of applications that exceed half a million requests per second.

Chapter 9 of the Building AI Agent Harnesses with Strands Agents course. Chapter 8 covered managing context within a session. This chapter covers what happens when the session ends and the user comes back. Without persistence, every conversation starts from zero. The agent has no memory of prior interactions, no accumulated knowledge about the user, no awareness of decisions made yesterday.

Discover how Visa revolutionized real-time payment security by leveraging AWS services, including AWS Nitro Enclaves, Amazon EKS, and Amazon MemoryDB, for their Visa Protect solution. This session explores Visa's journey to a rapidly scalable, cloud-based fraud detection solution. Learn how Visa processes massive volumes of sensitive financial data with ultra-low latency while maintaining stringent security standards.

While AI agents offer powerful automation capabilities, many critical business workflows require human oversight and approval. This 20-minute lightning talk demonstrates practical patterns for integrating human-in-the-loop (HITL) controls within multi-agent AI systems. Learn how to design asynchronous agent workflows that incorporate human decision points using serverless architectures.

Chapter 11 of the Building AI Agent Harnesses with Strands Agents course. In Chapter 10, the parent agent decided when to call a child agent. That works when one agent is clearly in charge. But some workflows have a fixed structure: step A feeds into step B, step B branches based on a condition, both branches converge at step C. You don't want the model deciding whether to run step B. You want it guaranteed. Graph workflows let you define that structure explicitly.

In this video learn strategies like cache aside, write-through, and how to implement them using Valkey on Amazon ElastiCache. We will dive into the world of in-memory databases and how they can improve your application's performance. Whether you're a seasoned developer or just getting started with AWS, this video will equip you with the knowledge to implement effective caching solutions. Read more about Database Caching on AWS with Valkey: https://builder.aws.

AI agents are changing how organizations find and act on information, but they share one structural limitation: their knowledge is frozen at training time. When you ask an agent that relies only on its training data about today’s stock price, a sports score, or a release that shipped an hour ago, it can’t respond. Amazon Bedrock AgentCore websearch helps AI agents get access to the current information without any infrastructure overhead.