Model Online / On-Site
Duration
Modules 5 modules

Course Objective & Scope

Running an agent prototype on a laptop is straightforward, but taking it to production for thousands of users with strict session isolation, persistent memory, enterprise OAuth/IAM delegation and sandboxed code or browser execution demands heavy infrastructure work. This training teaches how to deploy and operate production agents using the modular services of Amazon Bedrock AgentCore.

Session-isolated serverless execution on AgentCore Runtime, short- and long-term state in AgentCore Memory, user-delegated auth with AgentCore Identity, turning existing APIs and Lambdas into MCP servers via AgentCore Gateway, built-in Code Interpreter/Browser sandboxes and OpenTelemetry-powered AgentCore Observability are practiced hands-on.

Who Should Attend?

  • AI and platform engineers deploying agentic applications on AWS
  • Cloud architects responsible for enterprise security, identity and API integration
  • Developers running Strands, LangGraph or custom agents on managed infrastructure
  • Prerequisite: Python programming and basic familiarity with AWS (IAM, Lambda, Bedrock) and containers

Key Takeaways

  • Deploy agents written in Strands, LangGraph or custom Python onto session-isolated AgentCore Runtime
  • Expose internal REST APIs and AWS Lambda functions as governed MCP servers through AgentCore Gateway
  • Manage inbound user authentication and outbound OAuth/IAM tool delegation with AgentCore Identity
  • Configure short-term conversational state and long-term semantic memory with AgentCore Memory
  • Use managed Code Interpreter/Browser sandboxes and trace every step in AgentCore Observability

Curriculum

Amazon Bedrock AgentCore Architecture and AgentCore Runtime
  • Framework-agnostic modular services and micro-VM session isolation
  • Packaging, deploying and scaling synchronous and long-running asynchronous agents
AgentCore Gateway: Turning Enterprise APIs into MCP Tools
  • Exposing OpenAPI/REST services and Lambda functions as managed MCP endpoints
  • Semantic tool discovery across large tool catalogs and rate-limit enforcement
AgentCore Identity and Delegated Authorization
  • Integrating enterprise IdPs (Okta, Entra ID, Cognito) and on-behalf-of user permissions
  • Managed token vaults and least-privilege access to internal and SaaS tools
AgentCore Memory and Sandboxed Tools (Code Interpreter & Browser)
  • Combining short-term session state with extracted long-term user and episodic memory
  • Executing Python data analysis and headless web interactions in isolated sandboxes
AgentCore Observability and Operational Governance
  • OpenTelemetry-compatible traces, step latency breakdowns, token accounting and error triage
  • VPC networking, KMS encryption, versioning and production deployment checklists

Other Courses in This Category

  • Developing Production AI Agents with AWS Strands Agents SDK

    Building model-driven agents with the open-source AWS Strands Agents SDK: @tool decorators, native MCP integration, multi-provider model support, multi-agent patterns and OpenTelemetry tracing.

    Enterprise AI Platforms & Agent Cloud Ecosystem Corporate
    Live Course
    5 modules
    View
  • Amazon Bedrock Knowledge Bases and Guardrails

    Managed enterprise RAG with Amazon Bedrock Knowledge Bases (advanced parsing, chunking, hybrid search, reranking) and safety enforcement with Bedrock Guardrails (PII, grounding, content filters).

    Enterprise AI Platforms & Agent Cloud Ecosystem Corporate
    Live Course
    5 modules
    View
  • Amazon SageMaker AI and Enterprise ML Platform Services

    Training, deploying and governing classical ML models and open-weight LLMs on AWS using Amazon SageMaker AI: Unified Studio, JumpStart, Training, Pipelines, Model Registry and Endpoints.

    Enterprise AI Platforms & Agent Cloud Ecosystem Corporate
    Live Course
    5 modules
    View
  • Google Cloud Vertex AI and Gemini Enterprise Agent Platform

    Enterprise AI and agent development on Google Cloud Vertex AI with Gemini models: Google Gen AI SDK, grounding with Vertex AI Search, context caching, safety controls and deployment.

    Enterprise AI Platforms & Agent Cloud Ecosystem Corporate
    Live Course
    5 modules
    View
  • Building Multi-Agent Applications with Google Agent Development Kit (ADK)

    Developing modular multi-agent systems with Google's open-source Agent Development Kit (ADK): LlmAgent, Sequential/Parallel/Loop workflow agents, MCP tools, local evaluation and deployment.

    Enterprise AI Platforms & Agent Cloud Ecosystem Corporate
    Live Course
    5 modules
    View
  • Enterprise Agent Development with Google Cloud Vertex AI Agent Engine

    Learn hands-on how to design, deploy, and operate scalable, secure, and managed enterprise agent architectures using Google Cloud Vertex AI Agent Engine and Agent Development Kit (ADK).

    Enterprise AI Platforms & Agent Cloud Ecosystem Corporate
    Live Course
    4 modules
    View

Get in touch