Learn
Connect
Blog
Resource hub
Featured resource
2026 Tech Forecast
2026 Tech Forecast

1,500+ tech insiders, business leaders, and Pluralsight Authors share their predictions on what’s shifting fastest and how to stay ahead.

Download the forecast

Building Production-Ready Agents with Amazon Bedrock AgentCore

Course Summary

This course is designed to bridge the gap between "experimental" AI scripts and production-grade agentic systems. While building a basic agent is easy, scaling one that is secure, stateful, and observable is notoriously difficult. Amazon Bedrock AgentCore provides the infrastructure to solve these enterprise challenges. Participants will move beyond simple prompt engineering to master the AgentCore ecosystem—a suite of services designed for secure tool orchestration, persistent long-term memory, and robust identity management.

Prerequisites:

To get the most out of this session, participants should have:

  • Experience with Python 
  • Experience using AI Agents
  • Experience with an agent framework like LangGraph or LangChain
  • Knowledge of AWS fundamentals - IAM, Lambda, APIs
  • Familiarity with REST APIs and OAuth 2.0
     
Purpose
Build, deploy, and operate autonomous AI agents at scale
Audience
IT professionals looking to build production-grade agentic systems
Role
Software Developers | ML Engineers | Platform Engineers
Skill level
Intermediate
Style
Lecture | Hands-on Activities | Labs
Duration
2 days
Related technologies
AI/ML | Generative AI | Python | AWS | LangChain | REST APIs

 

Learning objectives
  • Explain the role of Amazon Bedrock AgentCore in the AWS AI agent ecosystem
  • Build and run AI agents using the AgentCore Runtime and Gateway
  • Secure agent execution using AgentCore Identity and AWS IAM
  • Implement stateful agent behavior using AgentCore Memory
  • Operate and troubleshoot agents using AgentCore Observability

What you'll learn:

In this Building Production-Ready Agents with Amazon Bedrock AgentCore course, you'll learn:

Introduction to Amazon Bedrock AgentCore

  • What is AgentCore?
  • Relationship to Amazon Bedrock
  • High-level architecture
  • Core pillars overview - Runtime, Gateway, Identity, Memory, and Observability

AgentCore Runtime

  • Serverless Execution
  • Session Management
  • Protocols
  • Deployment Flow

AgentCore Gateway

  • API-based vs. event-based access
  • Standardizing tool access
  • Request/response flow
  • Rate limiting and throttling
  • Versioning and deployment strategies

AgentCore Identity

  • Agent Identity Directory
  • Credentia Management
    • Authentication vs. Authorization
  • IAM roles and policies for agents
  • Delegation and least-provilege design

AgentCore Memory

  • Types of memory in AgentCore
  • Session vs. persistent memory
  • Built-in strategies
  • Memory scoping and lifecycle

AgentCore Observability

  • Observability challenges in agent systems
  • Logs, metrics, and traces in AgentCore
  • Tracking agent decisions and tool calls
  • Performance monitoring and cost visibility
  • Debugging failed or degraded agents

Best Practices and Production Readiness

  • Designing scalable agent architectures
  • Cost control strategies
  • Failure modes and resilience
  • When to use AgentCore vs custom frameworks

Building Production-Ready Agents with Amazon Bedrock AgentCore

real world content

Real-World Content

Project-focused demos and labs using your tool stack and environment, not some canned "training room" lab.
expert practitioners

Expert Practitioners

Industry experts that bring their battle scars into the classroom.
experiential learning

Experiential Learning

More coding than lecture, coupled with architectural and design discussions.
fully customized

Tailored Outlines

Once-size-fits-all doesn't apply to training teams. That's where we come in!

Dive in and learn more

When transforming your workforce, it’s important to have expert advice and tailored solutions. We can help. Tell us your unique needs and we'll explore ways to address them.

Let's chat

By clicking submit, you agree to our Privacy Policy and Terms of Use, and consent to receive marketing emails from Pluralsight.
Related Pages