AI & Dev

Building Production-Ready Agents with Amazon Bedrock AgentCore

Intermediate
Amazon Bedrock AgentCore Runtime & Gateway Identity & IAM Agent Memory Traces & Observability
Building Production-Ready Agents with Amazon Bedrock AgentCore Hands-on deployment lab

Overview

Participants learn how Amazon Bedrock AgentCore supports the execution and operation of agentic applications. The course follows one request from an authenticated caller through Runtime, Gateway, Identity, Memory, and Observability, and distinguishes managed infrastructure from a production-ready system: the platform supplies managed execution and session isolation, while the application still owns authorization, memory governance, tool safety, evaluation, and operational response.

Who Is This For

  • Software developers, ML engineers, and platform engineers building agents on AWS

Prerequisites

  • Working knowledge of Python and the AWS CLI
  • Familiarity with core AWS concepts such as IAM roles and policies
  • Basic understanding of LLM-based agents and tool calling

Learning Path

  • Explain the roles of Runtime, Gateway, Identity, Memory, and Observability in an AgentCore request flow
  • Explain why Runtime session isolation does not replace user-to-session authorization or tenant partitioning
  • Distinguish AgentCore Gateway from Amazon API Gateway and identify where each appears in an enterprise design
  • Identify the human caller, Runtime workload, and downstream service credentials in an agent transaction
  • Compare broad development permissions with a least-privilege IAM policy
  • Deploy a Python agent on AgentCore Runtime, invoke a read-only tool through Gateway, and verify memory continuity
  • Inspect an end-to-end trace for latency, token use, tool activity, memory activity, and errors
  • Relate production controls to the AWS Well-Architected Agentic AI Lens, OWASP Top 10 for Agentic Applications 2026, and NIST AI RMF

By the end: You can deploy a governed agent on AgentCore and explain which production controls remain your responsibility.

What You'll Receive

  • Hands-on lab exercises and a sample code repository to keep
  • Course slides and reference guides for every module
  • Session recordings for review after class
  • Certificate of completion
  • A post-course support window for follow-up questions

Delivery Options

Online Classes

Live, interactive sessions from anywhere. Small batches for personalized attention.

1-to-1 Coaching

Personalized mentorship with flexible scheduling tailored to your goals.

Enterprise Training

Customized programs for teams, delivered online or on-site, scoped to your stack.

Learn More

Your Instructor

Taught by a practicing engineer with hands-on experience building and scaling test automation, CI/CD, and AI-assisted tooling across enterprise teams. Every session is delivered by the instructor - no recordings-only courses, no junior stand-ins - with real-world examples drawn from production projects.

Frequently Asked Questions

This course is pitched at Intermediate level - you should be comfortable with Python, the AWS CLI, and core AWS concepts such as IAM. We can advise on readiness during a free consultation.

Both. We deliver live online classes, 1-to-1 coaching, and on-site or remote enterprise sessions for teams.

Yes. For enterprise engagements we tailor examples, exercises, and the detailed outline to your application, tools, and timeline.

Yes - a certificate of completion is provided at the end of the course.

Working knowledge of Python and the AWS CLI; Familiarity with core AWS concepts such as IAM roles and policies; Basic understanding of LLM-based agents and tool calling.

Related Courses

AI & Dev

Build AI Agents with GitHub Copilot

Move from assistive, suggestion-by-suggestion use of GitHub Copilot toward standardized, repository-level agentic workflows.
AI & Dev

Build AI Agents with Claude Agent SDK

Move from chatbots to autonomous systems with the Claude Agent SDK: tools, skills, subagents, MCP, and safety guardrails.
AI & Dev

MCP with AI Agents

Learn how to configure existing MCP servers within tools like Claude Code and GitHub Copilot to expand your local development capabilities.

Ready to get started?

Request the detailed day-by-day outline or book a free consultation to find the right level for you.

Request Detailed Outline Book a Free Consultation

Request Your Detailed Outline

Tell us a little about your goals and we'll send the full outline tailored to your level and context.