AWS Atlas

AgentCore Observability helps you trace, debug, and monitor agent performance in production environments. It offers detailed visualizations of each step in the agent workflow, enabling you to inspect an agent's execution path, audit intermediate outputs, and debug performance bottlenecks and failures.

Model Context Protocol (MCP) provides the foundation for building AI agents and code assistants that connect to your data, infrastructure, and services. Whether developing enterprise customer service AI or code that runs on AWS, MCP brings together intelligence and integration. The session demonstrates how Kiro accelerates building AI agent development with MCP servers, while exploring Amazon Bedrock AgentCore for AWS deployment.

Rust's safety, performance, and reliability make it an ideal choice for cloud applications on AWS. From Amazon Aurora DSQL to AWS Firecracker and AWS Bottlerocket, AWS has demonstrated Rust's capabilities in critical infrastructure. This session explores practical applications of Rust, demonstrating serverless implementations and concurrent processing patterns. Discover how Rust's memory safety and efficient abstractions enhance AWS applications.

Intelligent agents with memory capabilities can deliver smarter, more personalized interactions—but implementing memory in production is no easy task. In this session, we’ll cover how to build context-aware agents using Amazon Bedrock AgentCore Memory. Learn to manage short-term and long-term memory securely, structure agent interactions around user history, and scale memory. Hear from Experian on how they are reimagining conversational memory architecture across their AI ecosystem.

Are your legacy applications holding you back from AI-driven workflows? In this live-coding session, discover how Kiro and Amazon Bedrock AgentCore Gateway bridge the gap between traditional business systems and modern AI agents without touching existing code. We'll demonstrate how to make REST APIs instantly accessible to AI agents using Kiro's vibe coding approach to naturally understand your intent alongside AgentCore Gateway's integration framework and Model Context Protocol (MCP).

Simplify building multi-step applications and AI workflows with Lambda durable functions. After turning on a simple configuration setting, you can write, test, and debug durable functions using your preferred programming languages and IDEs. Durability strengthens application resilience. You can preserve progress despite interruptions through built-in error handling, automatic retries, and recovery after failures.

Organizations face mounting challenges from manual patching, fragmented compliance, and limited visibility. In this code talk, we'll build an agentic solution with Strands Agents SDK and AWS services to transform patch management. We’ll walk through turning operational requirements into interactive, production-ready agent workflows—driving automated remediation and rapid vulnerability checks.

The rise of generative and agentic AI is transforming how organizations build, operate, and secure applications. As systems become increasingly autonomous and complex, intelligent operations are essential. Join us to discover how AWS Cloud Operations continues to innovate—helping you monitor AI agents wherever deployed, operate smarter across environments, and unlock insights through accelerated analytics.

Discover the future of software development as we explore the transformative power of agents with Amazon Bedrock AgentCore and Kiro’s spec-driven development in modernizing your entire software development lifecycle (SDLC). Agentic AI is impacting software development by automating tasks, improving efficiency, and enabling more autonomous workflows throughout the development lifecycle.

An AI Agent that performs big data analytics by using strands tools and tools from MCP server to query large and many parquet files in Amazon S3 using AWS Glue and Amazon Athena. It demonstrates the power of using natural language to perform research on big data, or ask ad-hoc questions to generate insights. Learn more at - http://go.aws/4njdjJU Subscribe to AWS: https://go.aws/subscribe Sign up for AWS: https://go.aws/signup AWS free tier: https://go.aws/free Explore more: https://go.

Amazon Connect transforms routine interactions into memorable moments by seamlessly embedding AI across every customer touchpoint - built from the ground up as a unified solution that's been cloud and AI-native since day one. By driving seamless coordination between human and AI agents, it preserves context across every interaction to drive differentiated customer experiences.

While generative AI captures headlines, the untapped potential lies in combining it with decades-proven symbolic AI techniques. This session explores how organizations can leverage symbolic AI, such as ontologies and logic-based reasoning to build knowledge graphs and to enhance their AI capabilities. Dive deep into these topics to understand what ontologies look like, where semantics comes from, and what it means to build working knowledge graphs.