Amazon Agentcore Scale Your Agentic AI To Production

What you'll learn
Deploy an agentic AI application into production using Amazon Bedrock AgentCore on AWS, managing serverless runtime, scaling, and reliability.
Implement authentication and identity management for agents to ensure secure access, user verification, and proper credentials in real‑world scenarios.
Add both short‑term and long‑term memory to agents to improve context awareness, persistence, and user experience over time.
Integrate external tools, APIs, and third‑party data sources via Gateways, and leverage the OpenAI Agents SDK for orchestrating tool usage.
Monitor, observe, and debug your agentic systems using AgentCore's observability features, log metrics, and performance dashboards in production.
Understand best practices and design patterns for deploying generative AI systems securely and efficiently with Amazon AgentCore and Bedrock.
Requirements
Familiarity with Python programming
Experience in developing with agentic AI frameworks
Basic familiarity with AWS and the AWS console
Hands-on activities require an OpenAI account, an AWS account, and a Python development environment
Description
Tired of building AI prototypes that never make it to production?You're not alone. Many engineers can build impressive agentic AI demos-but hitting a wall when trying to scale those systems into production is common.This course solves that problem.You'll learn how to use Amazon Bedrock AgentCore-part of AWS's cutting-edge generative AI stack-to deploy real, secure, scalable agent systems. You'll take a working OpenAI Agents SDK project and transform it into a production-grade service, using AgentCore's built-in memory, identity, tools, and observability features.By the end of this course, you won't just understand agentic AI-you'll have deployed one.What You'll LearnHow to use Amazon AgentCore to host your AI agents serverlessly in productionAdd memory to your agents (short-term and long-term)Handle user identity and secure authentication in agent workflowsIntegrate real tools, APIs, and third-party data using Bedrock's GatewaysMonitor and debug agents using AgentCore's observability featuresBuild a complete hands-on agentic AI project using the OpenAI Agents SDKWhy Amazon AgentCore?Amazon Bedrock AgentCore provides a serverless runtime purpose-built for agentic AI. It handles scaling, security, and tool integrations so you don't have to. With first-class support in AWS, it's the fastest way to take your generative AI project from experiment to enterprise.Who This Course Is ForAI engineers and developers who've built agent prototypes-but haven't shipped themML practitioners ready to operationalize generative AISoftware engineers looking to upskill in AWS AI tools and infrastructureBuilders who want hands-on, project-based experience with agent systems in productionIf you've been exploring agentic AI or the OpenAI Agents SDK, this course will show you how to make it real-on a secure, scalable production stack.About the InstructorHi, I'm Frank Kane. I spent 9 years at Amazon and IMDb, where I helped build and lead the AI systems behind some of the most-visited websites on the planet.Since leaving Amazon, I've taught over one million students around the world how to succeed in machine learning and data science through Sundog Education.This course brings my real-world engineering experience at Amazon together with today's most powerful agentic AI tools-so you can stop prototyping and start deploying.What You'll Walk Away WithBy the end, you'll have:A working, full-featured agentic AI system deployed with Amazon AgentCoreThe confidence to scale, monitor, and maintain your own production agentsPractical experience that applies directly to your work or portfolioPlease Note:Following along hands-on with the project in this course requires an OpenAI developer account and an AWS account, as well as a Python development environment. Total costs should not exceed a few dollars, or you can just watch the videos without incurring any cloud costs.
AI / ML engineers, software developers, or cloud architects who need to take Ai prototypes into production


Homepage