Search AWS Educational Content

Watch the full podcast episode today at https://youtu.be/62K4N95HJWg?si=03_J8Lsg-5uqNkIE #AWS #AmazonWebServices #CloudComputing #AgenticAI #AI #Travel #GenAI

The systems that sustain human life — clean water, healthy soil, stable supply chains — are the same systems that drive economic growth. For a long time, sustainability lived in its own lane, apart from core business strategy. The cost of keeping them separate is now too high to ignore.

In this episode of AWS Show and Tell we will take you on ways you can customize move models to meet your business needs on performance of LLMs. We will show you what all techniques are available now in your tool box when it comes to customization when to think of using which techniques and how these customization options differ from each other. We will also take you to the On Demand inference on custom nova models and what it means for your business.

Your weekly deep dive into cloud security, where technical expertise meets real-world application. Join hosts Russ Noll and Tristan Watty Ph.D. every Monday at 11am PST for an hour that bridges technical implementation and practical business solutions. In this season finale, we power up to the next level of cloud security, defined by autonomous, decision-making AI.

Panos Panay, Amazon SVP Devices, shares an inside look at how Amazon approaches groundbreaking innovation across some of its most ambitious projects—including Kuiper, Zoox, Alexa+, Ring, and the broader constellation of devices that connect and protect our customers every day. Watch this Executive Summit at re:Invent session to hear him unpack the vision and mental models that guide product-making at scale.

Amazon S3 internally processes hundreds of petabytes daily across microservices, generating millions of logs. This session chronicles S3's journey from basic log analysis to a modern Apache Iceberg-based data lake. We’ll explore key architectural transitions: replacing legacy processing with SQL capabilities, migrating from unstructured text to Iceberg tables, and implementing enhanced ingestion engines.

Chapter 2 of the Building AI Agent Harnesses with Strands Agents course. This chapter covers model providers: how Strands abstracts the underlying LLM so your agent logic stays the same regardless of which model you're calling. We go through how to configure different providers (Amazon Bedrock, Anthropic, OpenAI, local/custom endpoints), how to switch between them with one line, and why this matters in practice. Maybe you prototype on a cheap fast model and deploy on a stronger one.

This follow-up episode focuses on the operational aspects of Oracle Database@AWS. We'll cover: * Day-to-day management tasks for ODB networks, Exadata infrastructure and VM clusters * Monitoring capabilities using CloudWatch metrics and EventBridge * Security and compliance features including IAM integration * Migration * Integration with other AWS services

Most enterprises are stuck in AI pilot purgatory—impressive demos, no ROI. Garther predicts that by 2028 80% of successful GenAI apps will run on existing data platforms, yet many still treat AI as “magic” exempt from existing data challenges. This session shows why batch pipelines kill model value and how Confluent’s data streaming platform and Streaming Agents, AWS Bedrock, Amazon SageMaker, and MCP Servers unlock scalable multi-agents systems that monitor business events and instantly act or...

Discover how to gain visibility into the performance of your workloads going over the AWS global network with the latest Amazon CloudWatch Network Monitoring feature. Learn how to monitor traffic flowing between AWS Regions and quickly identify network performance issues affecting your multi-Region workloads.

Chapter 8 of the Building AI Agent Harnesses with Strands Agents course. Every turn, the model receives the full conversation history plus system prompt plus tool results. That window fills up fast. Once it does, you either hit token limits, start paying significantly more per request, or the model starts missing information buried in the middle. Context engineering is the practice of deliberately shaping what goes into that window. Conversation management is the Strands mechanism for doing it.

The SAP landscape is changing—with customers not just asking “How can you help us migrate and run our SAP applications in the cloud?”, but instead: “How can you help us transform our business and better serve our customers?”. Join this session to learn how Hyundai Motors group is combining SAP modernization with Amazon's extensive portfolio to revolutionize customer experiences.