AWS Atlas

Learn to build a production-grade agentic RAG system using Amazon Bedrock Knowledge Bases, Strands, and AgentCore in this expert-level code talk. Through live coding and detailed walkthroughs, learn how to build an intelligent event assistant agent that integrates knowledge retrieval, long-term memory, and user authentication.

Do you want to take advantage of the full power of serverless architectures for your production workloads? Are you wondering how events can help your applications scale? Have you been trying to tune your applications for higher performance and lower cost? This session provides architectural best practices, optimizations, and useful shortcuts that experts can use to build secure, high-scale, and high-performance serverless applications. Learn more: More AWS events: https://go.

The open-source Strands Agents SDK enables building production-ready, multi-agent AI systems in a few lines of code. The session demonstrates creating custom tools for video content analysis and converting them into Model Context Protocol (MCP) servers. Live code examples show how to implement scalable chat memory with Amazon S3 Vectors, from local development to enterprise production.

Learn how Cox Automotive scaled Agentic AI from experimentation to production in just one month using Amazon Bedrock AgentCore and Strands. We'll share Cox's methodology for scaling Agentic AI, including reference architectures and governance frameworks that enable startup speed with enterprise controls. Discover how AgentCore primitives—runtime, identity, gateway, and memory—accelerated their journey.

Amazon S3 Vectors introduces native support for you to store, retrieve, and query vectors in S3. In this session, explore how S3 Vectors complements high-performance vector databases, reducing storage and querying costs by up to 90%. Learn how to integrate S3 Vectors with Amazon Bedrock Knowledge Bases and OpenSearch Service for RAG and semantic search at reduced cost and complexity.

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.

In this session, Toyota Connected North America and Toyota Enterprise AI showcase how they transformed dealer operations using Amazon Bedrock and Claude to create an intelligent assistant that answers complex vehicle questions in seconds. The system now serves 2,300+ dealerships with instant, accurate vehicle expertise and handles 7,000+ monthly dealer interactions across multiple Toyota models and years, leveraging Amazon Bedrock, OpenSearch Serverless, and Amazon EKS for enterprise-scale...

Learn how Amazon CloudWatch helps you go from data to decisions faster, simpler and more autonomously — from streamlined data ingestion and analytics workflows to new AIOps capabilities. We’ll showcase the latest innovations across CloudWatch that make ingesting and analyzing data easier at any scale. We’ll show how you can use agentic observability systems that make your operations faster and smarter.

Stay ahead with the cutting-edge capabilities of Amazon's robust block storage solution in Amazon EBS. Join this session for a comprehensive overview of the latest advancements and features in Amazon Elastic Block Store (EBS). Learn about recent performance improvements, cost optimization strategies, new features that enhance data resiliency and storage efficiency, and practical insights for leveraging EBS in modern cloud environments.

Discover how AWS partners are leveraging Amazon Bedrock and Kiro to revolutionize both software architecture design and DevSecOps practices. Through real-world examples, explore powerful patterns that enhance the entire development lifecycle. Learn how to use GenAI to accelerate cloud architecture design processes—generating standardized patterns, optimizing configurations, ensuring compliance, and creating documentation.

Join this session to learn about the latest capabilities in Amazon SageMaker Catalog that help organizations govern data and AI more effectively. We will walk through new features that make it easier to discover, govern, and securely share structured and unstructured data, models, business intelligence dashboards, and applications. You’ll hear how customers are using these capabilities to improve data discovery and access, streamline compliance, and support AI initiatives.

In this session, learn how to design mission-critical systems that process millions of transactions daily, on serverless services. Beginning with a legacy system, we'll decompose a monolith and discuss key serverless patterns to help accelerate modernization efforts.