Search AWS Educational Content

Agent Toolkit for AWS gives AI coding agents the tools, knowledge, and guardrails they need to work effectively with AWS services. Instead of relying on agents' general knowledge of AWS -- which can be outdated or incomplete -- it provides access to up-to-date documentation, best practices, and tested procedures that improve success rates and reduce wasted effort.

In this session, learn how Kiro is helping you go from idea to production faster with spec-driven development. Learn how to delagate and automate development tasks using Kiro's agent hooks, multimodal agent chat and MCP support. We'll show you how Kiro’s agents challenge you to think beyond the code and work alongside you to solve hard engineering problems with confidence. Learn more: More AWS events: https://go.aws/3kss9CP Subscribe: More AWS videos: http://bit.

Chapter 1 of the Building AI Agent Harnesses with Strands Agents course. This chapter covers the difference between an agent and an agent harness, and walks through the agent loop: how the model reasons, calls a tool, observes the result, and decides what to do next. The distinction matters because the agent is just the model making decisions.

Learn how to build and deploy AI agents to production using AWS Bedrock Agent Core and Strands Agents. Using Kiro for development, follow along as we demonstrate agent building, chain-of-thought prompting, and production deployment best practices. Explore Amazon Bedrock Agents 👉 https://go.aws/47NHsvZ Resources: Strands Agents: https://go.aws/4ofh1oN AWS Bedrock Agent Core: https://go.aws/43F7LSD Follow AWS Developers! 📺 Instagram: https://go.aws/4olJSrM 🆇 X: https://go.

Is your operations team consumed by daily firefighting? Do you lack the time to evaluate and improve your operational posture? Move from reactive firefighting to proactive operational improvement with AWS DevOps Agent, a frontier agent that resolves and proactively prevents incidents, continuously improving reliability and performance of applications in AWS, multicloud, and hybrid environments.

For more details on this topic, visit the AWS Knowledge Center on AWS re:Post and read the full article associated with this video: https://repost.aws/knowledge-center/sqs-queue-access-permissions The AWS Knowledge Center contains trusted, expert-reviewed answers to frequently asked questions across AWS services — including EC2, S3, IAM, Lambda, Bedrock, and more. Tom shows you how to grant access to an Amazon Simple Queue Service (SQS).

In this session, we will walk through the architecture for the Amazon DynamoDB DNS management system that triggered the service disruption on October 20, 2025. We will share the lessons that the DynamoDB team learned from this event and explain how we are using these insights to improve both DynamoDB and AWS. You will walk away with actionable knowledge that you can apply to the systems you build. Learn more: More AWS events: https://go.aws/3kss9CP Subscribe: More AWS videos: http://bit.

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.

In a landscape of rapid AI evolution and daily headlines, senior leaders need clarity on what Agentic AI means for their business. This session cuts through the noise to provide a practical understanding of autonomous AI agents and their strategic implications for your organization. We will demystify Agentic AI and focus on what matters most to leaders. We will share how both management and architecture models will need to evolve to get value out of the autonomous AI systems.

AWS Lambda durable functions enhances Lambda's programming model to simplify building fault-tolerant applications using familiar programming language patterns in JavaScript, TypeScript, or Python. We'll explore new capabilities that simplify failure handling through built-in retry mechanisms, efficient handling of human-in-the-loop interactions, and state management to track progress.

Twitch stream from aws

System design interviews test whether you can reason about performance trade-offs. This is the five I keep coming back to: architecture shape, communication patterns, hosting model, caching strategy, and content delivery. All demonstrated on an e-commerce flow. Microservices let you scale the payment service independently during a flash sale, but every call between services adds network latency the monolith didn't have.