AWS Atlas

Discover how Amazon Ads harnesses the power of large language models (LLMs) to enhance shopper discovery and drive better outcomes for advertisers. This session explores the AWS-based machine learning infrastructure that fuels these innovations, including fine-tuning, model serving, and real-time inference at scale. Learn how we optimized cost, latency, and reliability to deliver LLM-powered solutions across the Amazon Ads ecosystem while maintaining the high performance our customers expect.

Join this session to learn the core concepts of Amazon DynamoDB data modeling. Explore best practices for common access patterns used by DynamoDB customers for applications that need consistent, fast performance at any scale. Developers experienced with DynamoDB can learn best practices and trade-offs to make when deciding on single-table and multi-table designs, indexing strategies, and more. Learn more: More AWS events: https://go.aws/3kss9CP Subscribe: More AWS videos: http://bit.

In this session, learn how to transform your existing containerized applications into powerful components of modern AI-powered workflows. We'll demonstrate how AgentCore Gateway acts as a bridge, enabling your Amazon EKS-based microservices to seamlessly interact with AI agents without requiring substantial refactoring or rebuilding.

Large language models and agentic tools have reached enterprise viability, with Service Oriented Architecture (SOA) principles providing the foundation for robust agentic systems. This session examines which SOA design principles translate directly to generative AI implementations and which require rethinking for agent orchestration and nondeterministic behaviors.

Discover the latest Amazon OpenSearch Service launches and capabilities that enable and quickly deploy agentic AI applications and vector search operations. Learn how new integrations with Amazon Q enable intelligent data discovery and automated insights, while enhanced Amazon S3 connectivity streamlines data management.

This session will focus on the latest Industry & LOB solutions, from Generative AI solutions in radiology to geospatial modeling for power. We will explain the opportunity for AWS Partners to increase visibility of their offerings, as well as develop joint business with AWS and we unlock new innovations for customers. We will share with partners the approach AWS is taking to address key industry use cases with Agentic AI, via partner solutions running on AWS.

We are infusing Agentic AI into the entire Software Development Lifecycle from brainstorming new ideas, implementing a plan, crafting new code, reviewing code reviews, releasing software, and bringing insights back to the development team. See how GitHub Copilot is being reimagined through this entire lifecycle to boost productivity across teams. This presentation is brought to you by GitHub, an AWS Partner. Learn more: More AWS events: https://go.

On October 22, 2024, we announced the availability of the Aurora Global Database writer endpoint, a highly available and fully managed endpoint for your global database that Aurora automatically updates to point to the current writer instance in your global cluster after a cross-Region switchover or failover, alleviating the need for application changes and simplifying routing requests to the writer instance.

Managing thousands of SaaS customer domains doesn’t have to be complex. In this session, discover how Amazon CloudFront SaaS Manager lets you deliver multi-tenant applications with speed, security - reducing operational overhead. See how to enforce security policies across every tenant, automate SSL/TLS provisioning with AWS Certificate Manager, and deliver branded, low-latency experiences worldwide.

Want to build and ship to customers faster than ever? Want to see a smile on your developers faces as they build SaaS applications, web apps, or event driven apps that delight end-users? Then swing by this session and see what's possible when infrastructure "disappears"! Discover how AWS Serverless transforms ideas into production applications at unprecedented speed, delivering enterprise governance and cost control by default.

Go behind the scenes of Amazon's internal Quick Suite deployment across multiple organizations and thousands of employees. This session covers the challenges of implementing enterprise AI at scale, including data integration complexities, orchestration layer design, and overcoming organizational silos. Learn from Amazon teams about deployment strategies, change management approaches, security considerations, and lessons learned from rolling out Quick Suite across diverse business units.

Discover how to build powerful AI agents using Amazon Bedrock's suite of tools, with a focus on Amazon Bedrock AgentCore. This session explores AI agent architectures, from implementing Bedrock Flows to configuring knowledge bases and guardrails. Learn to design dynamic inline agents and understand multi-agent collaboration frameworks. We'll demonstrate how AgentCore's modular components enable you to create secure, enterprise-ready AI solutions that scale.