Search AWS Educational Content

AI coding assistants promise explosive productivity gains, but they're creating a new problem: uncontrolled code chaos. Teams are generating code faster than they can review it, coding standards are very hard to enforce when humans aren't writing the code and codebases are becoming unmaintainable messes. Kiro solves this with its Spec driven development. A structured, deterministic development flow that replaces vibe coding" with repeatable outputs.

In this episode of "AWS Show and Tell – Trust your agent with Policy in Amazon Bedrock AgentCore", we explore how Policies in Amazon Bedrock AgentCore gives you deterministic, auditable control over your agent's behavior, enforced at the gateway before any tool call is ever executed.

In this livestream, we'll demonstrate how to rapidly build a production-ready full stack agentic application using the Fullstack AgentCore Solution Template (FAST). FAST is a starter project that handles the undifferentiated heavy lifting of infrastructure setup, enabling developers to go from zero to a deployed, secured web application connected to AgentCore in minutes rather than weeks.

In this session, we will introduce AWS Analytics Model Context Protocol (MCP) Servers, including the Data Processing MCP Server and Amazon Redshift MCP Server, which enable agentic workflows across AWS Glue, Amazon EMR, Amazon Athena, and Amazon Redshift. You will learn how these open-source tools simplify complex analytics operations through natural language interactions with AI agents.

Multi-agent AI systems now orchestrate complex workflows requiring frequent foundation model calls. In this session, learn how you can reduce latencies to single-digit milliseconds from single-digit seconds with vector search for Amazon ElastiCache for Valkey in agentic AI applications using semantic caching, while also reducing the cost incurred from your foundation models for production workloads.

Twitch stream from aws

AI is making it easier than ever to ship code fast... but are you actually learning anything? In this video, I respond to a comment that struck a nerve with thousands of junior developers: how do you build real experience and intuition when companies expect you to use AI from day one? I break down 5 practical strategies to help you grow as a developer while still leveraging AI tools. 📚 Book Links📚 : Head First Design Patterns - https://amzn.

Discover how Amazon is building production-ready AI agents with Island and Amazon Bedrock—solving the security, governance, and deployment challenges that generally stop enterprises from going live. Join this lightning talk with Adam Hoyos-Marré, Sr. PMT at Amazon, and Island to see real use cases, real results. This presentation is brought to you by Island, an AWS Partner. Learn more: More AWS events: https://go.aws/3kss9CP Subscribe: More AWS videos: http://bit.

Join us for an exciting deep dive into cutting-edge AI solutions for financial services and insurance Partners using AWS technologies! Discover how to harness Amazon Bedrock AgentCore and Strands SDK to enhance customer experiences. Learn to build intelligent underwriting assistant for insurance and explore diverse use cases in Financial Services. Recommended for teams looking to strengthen their AI capabilities in financial services. Learn more: More AWS events: https://go.

Want to start something new in 2026? Learn how to leverage Model Context Protocol (MCP) in serverless environments to build powerful AI-integrated applications on AWS. Build serverless applications using natural language, run your own MCP servers remotely, and connect MCP servers to tools like Lambda without compromising on performance! Join the conversation with other devs on AWS Builder Center: https://go.aws/4p8XrdC Serverless MCP Servers on GitHub: https://go.

Going from a pilot to a secure, scalable, and reliable agent system requires more than great prompts. In session, we'll show how Amazon Bedrock AgentCore helps teams move from proof-of-concept to production using enterprise-grade services, including Runtime, Gateway, Identity, Memory, Observability, Code Interpreter, and Browser. Learn how these services simplify development, reduce operational burden, and improve time-to-value.

Learn how organizations can fine tune or re-train large language models to meet the needs of their unique use cases. By fine tuning an LLM with your own domain data you can provide the model with the vocabulary, context, and expertise needed to operate in your environment. Amazon SageMaker AI offers various model fine-tuning techniques such as supervised fine tuning, preference alignment, continued pre-training, and re-training to fine tune open source LLMs for your domain adapted LLMS.