Building Agentic AI with Amazon Bedrock AgentCore
Field | Description |
Purpose | To provide developers with the technical expertise to architect and deploy production-grade, autonomous AI agents using the Amazon Bedrock AgentCore infrastructure platform. |
Audience | Intermediate software developers and AI engineering teams focused on moving beyond simple chatbots to complex, multi-agent autonomous systems. |
Role | AI Engineers, Software Architects, DevOps Engineers, and Backend Developers. |
Domain | Agentic AI / AI Orchestration / Cloud Infrastructure. |
Skill Level | Intermediate to Advanced. |
Style | Technical and implementation-heavy, covering the full agent lifecycle including runtime execution, identity management, tool integration (MCP), and production observability. |
Duration | 1-2 Days (estimated based on curriculum depth). |
Related Technologies | Amazon Bedrock AgentCore (Runtime, Identity, Policy, Gateway), Strands Agents SDK, Model Context Protocol (MCP), Amazon CloudWatch. |
Course Description
Building Agentic AI with Amazon Bedrock AgentCore is an intensive technical course designed for developers seeking to master the implementation of autonomous, goal-driven AI systems. Unlike traditional conversational AI, Agentic AI requires robust infrastructure for memory, security, and tool orchestration. This course dives deep into Amazon Bedrock AgentCore, the enterprise-grade platform for running custom agents at scale. You will learn how to use the Strands Agents SDK to build agent loops and leverage AgentCore’s serverless runtime for isolated, secure execution. From configuring identity providers like Cognito to implementing the Model Context Protocol (MCP) for extensible tool capabilities, this course provides the blueprint for production-ready AI agents.
Who is this course for
This course is intended for:
Software Developers looking to transition from basic LLM prompts to building complex, autonomous workflows.
Technical Professionals tasked with ensuring AI agents meet enterprise security and compliance standards.
Development Teams building multi-agent systems that require persistent memory and sophisticated tool integration.
Course Objectives
Architecture Foundations: Differentiate agentic AI from traditional systems and identify core interactions between agent components.
Secure Execution: Deploy agents using AgentCore Runtime with session isolation, serverless execution, and identity delegation.
Governance & Security: Implement AgentCore Policy for natural-language boundary setting and secure tool access via AgentCore Gateway.
Advanced Tooling: Design and deploy Model Context Protocol (MCP) servers to extend agent capabilities without custom code.
Production Readiness: Configure AgentCore Memory for context-aware agents and utilize AgentCore Observability and Evaluations for continuous monitoring.
Prerequisites
Foundational Knowledge: Completion of Agentic AI Foundations.
Technical Background: Familiarity with Python, AWS IAM, and basic Large Language Model (LLM) concepts.
Course outline
Section 1: Foundations of Agentic AI Patterns
Agent building blocks
Amazon Bedrock AgentCore introduction
Section 2: AgentCore Runtime and Framework Integration
Supported frameworks and implementation
AgentCore Runtime overview
Infrastructure and deployment
Section 3: Security and Identity Management
Security and identity management
Securing your agents with AgentCore Identity
Section 4: Tool Integration and AgentCore Gateway
Amazon Bedrock AgentCore Policy
Built-in tools and custom integration
Model Context Protocol (MCP)
AgentCore Gateway
Implementing AgentCore Gateway
Amazon Bedrock AgentCore Policy
Section 5: Agentic Memory Implementation
Agentic memory core concepts
AgentCore Memory
Securing AgentCore Memory
Hands-on Lab: Enhance and Scale Agents with Amazon Bedrock AgentCore
Section 6: Production Monitoring and Observability
Monitoring agents with AgentCore Observability
Verifying agent performance with AgentCore Evaluation