Search AWS Educational Content

In this session, deep dive into the newly launched AWS Database Savings Plans, a flexible pricing model that works across multiple AWS database services. With Database Savings Plans, reduce your database costs by up to 35% when using serverless deployments and eligible instances over a 1-year term with no upfront payment. Learn how to analyze usage patterns, implement cost optimization strategies, and maximize savings while maintaining workload flexibility.

Chapter 13 of the Building AI Agent Harnesses with Strands Agents course. We're now in the production section of the course, and it starts here because you can't improve what you can't measure. Agent evaluation is harder than traditional software testing. The output is non-deterministic. A "correct" answer might be phrased differently every time. A tool might be called in a valid but unexpected order.

Many of your users ask the same question worded differently, and you're paying your LLM to answer every single one from scratch. Give your application a semantic cache to reuse answers for questions that mean the same thing for lower inference costs and faster responses. If your #AI project is stuck in prototype because the production cost doesn't work or your application latency gets worse with production traffic, this one's for you.

Need to share QuickSight datasets and dashboards across AWS accounts and Regions? Navid walks through using templates to set up cross-account access, from creating and sharing a template in one account to building the dashboard in another. 0:00 Introduction 0:24 Account A: list dashboards 0:52 Get dashboard and dataset details 1:29 Create the template in Account A 2:12 Confirm template creation 2:44 Share template with Account B 3:29 Account B: create the dataset 4:53 Build the...

One moment you're experimenting with AI agents on AWS, and suddenly you're $2000 in the hole with your CEO asking questions. Whether you're building chatbots, shopping assistants, or multi-agent workflows, understanding your costs before deployment is critical. In this video, you'll see techniques for estimating and monitoring costs for AI agents built with Amazon Bedrock AgentCore. Learn how to use native AWS tools to understand what you're actually paying for—beyond just input/output tokens.

Join us for a conversation with Willie Pang (Amazon Ads ANZ), Zarak Khan (Netflix APAC), and Liam Hickey (Spotify JPAC) on how programmatic partnerships are driving full-funnel outcomes for Australian retailers. Subscribe to AWS: https://go.aws/subscribe Create a free AWS account: https://go.aws/signup Try AWS for free: https://go.aws/free Connect with an expert: https://go.aws/contact Explore more: https://go.aws/more Next steps: Explore on AWS in Analyst Research: https://go.

Vercel founder and CEO Guillermo Rauch presents the web's transformation from Pages to Agents. Vercel's AI Cloud provides "Self-Driving Infrastructure" built on AWS, enabling developers to focus on building applications. Learn more about AWS events: https://go.aws/events Subscribe: More AWS videos: http://bit.ly/2O3zS75 More AWS events videos: http://bit.

Watch the full podcast episode today: https://go.aws/4e3LHW8 #AWS #AmazonWebServices #CloudComputing #AgenticAI #AI #AWS #Travel #GenAI

As organizations build and customize multiple AI models and agents, managing experiments, versions, and evaluations becomes increasingly complex. In this session, see how Intuit, a leader in financial technology, is using Amazon SageMaker with MLflow to accelerate their AI initiatives and empower their teams to build and deploy AI solutions with confidence.

Unlock the full potential of AI model customization with Amazon SageMaker AI. This session explores SageMaker AI's comprehensive model development tools, highlighting how it caters to any use case - from hands-on compute control to fully managed solutions. Dive into key features like Amazon Nova customization, end to end development with HyperPod, and flexible development environments.

Chapter 6 of the Building AI Agent Harnesses with Strands Agents course. Individual tools solve individual problems. But some capabilities require multiple tools working together with specific hooks and prompt instructions to function correctly. That's what a plugin is: a packaged bundle of tools + hooks + system prompt additions that you attach to an agent as a unit. Think of it this way: a "memory" capability isn't just a save_memory tool.

What does it take to run AI in production? — Moving AI from a pilot to a production workload takes two changes at once: adopting the technology and changing the operating model that delivers it. In this episode, Matt Wood, VP and Chief AI and Technology Officer at AWS, explains why top-down change management fails for AI, how to choose models without locking yourself in, and why the cost of a fixed level of intelligence keeps falling. Subscribe to AWS: https://go.