Build, secure, and monitor production AI agents with Amazon Bedrock AgentCore, covering Runtime, Identity, Policy, Gateway, MCP, Memory, and Observability. 1-day official AWS course.

👥 132 Enrolled ⏱️ 1 Day 💼 Intermediate Level ⭐ 5 ( 5 ) Reviews

500+Courses

10+ YrsExperience

95K+Global Learners

Live Online (Public Batch)

Instructor-led group class, fixed schedule

USD 649

Private Group

Train your whole team, on your dates

Custom Quote

For Teams

Proceed to Buy Request Info

📄 Download Course PDF

100% Satisfaction Guarantee · Guaranteed to Run · Secure Payment

Course Overview

Building an agent that works is not the hard part anymore. Building one your security team will approve, your compliance officer will sign off on, and your operations team can actually monitor is where most projects stall. This course is about that gap.

Over one day you will learn to design, secure, and deploy enterprise-ready agentic AI systems using Amazon Bedrock AgentCore. It starts with foundations, what makes a system agentic rather than merely generative, the core agent components, and how AgentCore's services fit together. From there you move into AgentCore Runtime: deploying agents through supported frameworks, serverless execution with session isolation, and the infrastructure decisions behind a real deployment.

Security runs through the middle of the course. You will configure AgentCore Identity for enterprise requirements, write policies that constrain agent tool calls with AgentCore Policy, implement secure token management and permission delegation, and address data governance and audit obligations. Tool integration follows, covering built-in and protocol-based tools, designing and deploying Model Context Protocol servers and clients, common authentication patterns, and configuring AgentCore Gateway for authorized tool access.

The final sections deal with what agents remember and how you watch them. You will implement agentic memory patterns, configure AgentCore Memory for context-aware behaviour, secure it, and optimize its performance. The course closes with AgentCore Observability, CloudWatch integration and specialized tracing, and AgentCore Evaluation for validating agent performance before and after production release.

Mode of Training

🏫 Classroom 💻 Live Online 🧪 Blended 👨‍👩‍👧‍👦 Private Group

Upcoming Schedules

Start Date	Time	Duration	Mode	Price
Aug 28, 2026	9:00 am - 5:00 pm	1 Day	online	$649	GTR
Sep 11, 2026	9:00 am - 5:00 pm	1 Day	online	$649	GTR
Sep 25, 2026	9:00 am - 5:00 pm	1 Day	online	$649	GTR
Oct 09, 2026	9:00 am - 5:00 pm	1 Day	online	$649	GTR
Oct 23, 2026	9:00 am - 5:00 pm	1 Day	online	$649	GTR
Nov 06, 2026	9:00 am - 5:00 pm	1 Day	online	$649	GTR

+ View more schedules

What you will learn

Define agentic AI characteristics and distinguish agentic systems from traditional AI applications
Identify core agent components and how they interact
Deploy agents through supported frameworks using AgentCore Runtime
Configure serverless execution with session isolation
Configure AgentCore Identity to meet enterprise security requirements
Create policies that secure agent tool calls with AgentCore Policy
Implement secure token management and permission delegation
Meet data governance and audit requirements
Implement built-in and protocol-based tool integration patterns
Design and deploy Model Context Protocol (MCP) servers and clients for extensible agent capabilities
Configure AgentCore Gateway components for secure, authorized tool access
Implement agentic memory patterns and configure AgentCore Memory for context-aware behaviour
Secure AgentCore Memory and optimize memory performance for production workloads
Configure AgentCore Observability, with CloudWatch integration and specialized tracing
Use AgentCore Evaluation to validate agent performance
Integrate agentic systems with production APIs and design deployment strategies
Assess production readiness and establish continuous improvement processes

Who Should Attend This Course?

AI engineers and machine learning engineers building agent systems
Software developers moving from generative AI applications into agentic ones
Cloud and AI architects designing agent infrastructure
Security and governance professionals responsible for approving AI deployments
Enterprise technology teams moving agentic AI from pilot into production

Prerequisites

AWS recommends completing Agentic AI Foundations before attending, or having equivalent practical knowledge of agentic AI concepts.

You should also be comfortable with AWS fundamentals and have development experience. This is a build-and-configure course, not a conceptual overview.

📞 Talk to a Learning Advisor

📘 Building Agentic AI with Amazon Bedrock AgentCore Outline

Agent building blocks
Introduction to Amazon Bedrock AgentCore

Supported frameworks and implementation
AgentCore Runtime overview
Infrastructure and deployment

Security and identity management for agents
Securing your agents with AgentCore Identity

Amazon Bedrock AgentCore Policy
Built-in tools and custom integration
Model Context Protocol (MCP)
AgentCore Gateway and its implementation

Agentic memory core concepts
AgentCore Memory
Securing AgentCore Memory

Monitoring agents with AgentCore Observability
Verifying agent performance with AgentCore Evaluation

Course summary
Next steps and additional resources

❓ Frequently Asked Questions

A managed capability within Amazon Bedrock for building, operating, and scaling production AI agents. Rather than a single feature, it is a set of components: Runtime for execution, Identity and Policy for security, Gateway for tool access, Memory for persistent context, and Observability and Evaluation for monitoring and validation. This course covers each of them.

Most generative AI training teaches prompting and chatbot-style applications built on foundation models. This course is about autonomous, goal-directed agents that call tools, hold context across interactions, and act on their own within boundaries you define. That shift changes what matters: identity, policy enforcement, memory security, and observability become central rather than optional.

Because an agent that can call tools and act autonomously is a different risk profile from a model that only produces text. Three of the eight modules deal with identity, policy, secure tool access, and memory protection, which is why the course suits security and governance stakeholders as well as engineers.

MCP is the standard for connecting agents to external tools and services. In this course you design and deploy MCP servers and clients, then route that access through AgentCore Gateway so tool calls stay authorized and policy-aligned rather than open-ended.

Agentic AI Foundations comes first and introduces agentic concepts and the AWS tooling landscape. This course is the AgentCore deep dive: building, securing, and operating a single agent system properly. Building Advanced Agentic Systems on AWS comes after, covering multi-agent architectures, communication patterns, and context engineering across several agents.

Yes, and it works well as a cross-functional session. The identity, policy, and governance content benefits from having engineers and security stakeholders in the room together, since those are exactly the decisions that stall agent projects when the two groups are misaligned.

Still have questions?

Reach out to our learning advisors for personalized guidance on choosing the right course, group training, or enterprise packages.

📞 Talk to an Advisor

What You Get with Microtek Learning

Instructor-Led Excellence

✓ Certified Instructor-led Training
✓ Top Industry Trainers
✓ Official Student Handbooks

Measurable Learning Outcomes

✓ Pre- & Post-Training Assessments
✓ Practice Tests
✓ Exam-Oriented Curriculum

Real-World Skill Building

✓ Hands-on Activities & Scenarios
✓ Interactive Online Courses
✓ Peer Collaboration (Not in self-paced)

Full Support & Perks

✓ Exam Scheduling Support ^*
✓ Learn & Earn Program ^*
✓ Support from Certified Experts
✓ Gov. & Private Pricing ^*

Our Clients

For over 10 years, Microtek Learning has helped organizations, leaders, students and professionals to reach their maximum potential. We have led the path by addressing their challenges and advancing their performances.