AWS Bedrock: End-to-End (Foundations to AgentCore)
Course Curriculum
21 modules designed to master the subject.
Module 1: Introduction to AWS Bedrock
Foundations of Bedrock and the diverse model landscape.
Module 1 Lesson 1: What is AWS Bedrock?
Understanding the foundations of AWS Bedrock, the managed service for foundation models.
Module 1 Wrap-up: Foundations and Model Selection
Hands-on: Analyzing model suitability and understanding the serverless AI paradigm.
Module 9 Wrap-up: The Safe Assistant
Hands-on: Implement a Bedrock Guardrail and verify your grounding instructions.
Module 2: AWS Setup and Permissions
Configuring IAM, access, and security best practices.
Module 2 Lesson 1: IAM for Bedrock
Mastering Identity and Access Management for AI. Creating policies that allow your apps to talk to Bedrock securely.
Module 2 Lesson 2: Enabling Model Access
The 'Edit Model Access' step. How to manually request access to foundation models in the AWS Console.
Module 2 Wrap-up: Getting Ready for Code
Hands-on: Verify your AWS configuration and enable your first foundation models.
Module 3: Bedrock APIs Fundamentals
InvokeModel, Converse API, and response handling.
Module 3 Lesson 1: The InvokeModel API
Going Raw. How to use InvokeModel to send model-specific JSON payloads to Bedrock.
Module 3 Lesson 2: The Converse API
Unified AI. How to use AWS Bedrock's standard interface to write model-agnostic code.
Module 3 Wrap-up: Your First AI Call
Hands-on: Write a script that compares the outputs of two different models using the same prompt.
Module 4: Prompt Engineering in Bedrock
System prompts, guardrails, and cost-aware design.
Module 4 Lesson 1: System Prompts in Bedrock
Defining the Persona. How to use the 'System' role in Bedrock to control AI behavior and safety.
Module 4 Lesson 2: Cost-Aware Prompting
Saving Money by Design. How to optimize your prompts to use fewer tokens and reduce your AWS bill.
Module 4 Wrap-up: Engineering the Instruction
Hands-on: Robust prompt engineering to reduce hallucinations and maximize cost-efficiency.
Module 5: Streaming and Performance
Optimizing for latency and streaming user experiences.
Module 5 Lesson 1: Streaming Responses
The Typing Effect. How to use converse_stream to send tokens to your UI as they are generated.
Module 5 Lesson 2: Latency and Throttling
Handling the Load. Understanding Bedrock's rate limits and how to optimize for the fastest response times.
Module 5 Wrap-up: Real-time Performance
Hands-on: Build a streaming CLI chat application that handles tokens as they arrive.
Module 6: Building APIs with Bedrock
Integrating with FastAPI and production patterns.
Module 6 Lesson 1: FastAPI + Bedrock
Creating the Backend. How to wrap your Bedrock logic in a high-performance REST API.
Module 6 Lesson 2: Managing Chat State
Memory in the Cloud. How to maintain conversation context across multiple API requests.
Module 6 Wrap-up: Shipping the API
Hands-on: Build a functional REST API with FastAPI that exposes multiple Bedrock models.
Module 7: Knowledge Bases Foundations
RAG architecture, embeddings, and vector stores on AWS.
Module 7 Lesson 1: What is a Knowledge Base?
Foundations of RAG. Why Knowledge Bases are the secret to building AI that 'knows' your private business data.
Module 7 Lesson 2: Chunking and Embeddings
Slicing the Data. Understanding how Bedrock breaks docs into 'Chunks' and turns them into 'Vectors' of meaning.
Module 7 Wrap-up: Designing the Library
Hands-on: Design your first Knowledge Base and select your chunking strategy.
Module 8: Knowledge Base Retrieval and RAG
Grounded responses and source attribution.
Module 8 Lesson 1: Retrieve and Generate
The RAG APIs. Understanding the difference between raw retrieval and the fully managed 'Answer' API.
Module 8 Lesson 2: Source Attribution
Proving the Answer. How to extract citations and references to show users exactly where the AI found its information.
Module 8 Wrap-up: Real-World RAG
Hands-on: Build a Python script that answers questions about your S3 documents and prints the citations.
Module 9: Knowledge Base Validation and Safety
Content filtering and enforcment of retrieved context.
Module 9 Lesson 1: Bedrock Guardrails
Setting the Safety Net. How to use AWS Bedrock Guardrails to filter sensitive content and block inappropriate prompts.
Module 9 Lesson 2: Verification and Grounding
Fighting the Hallucination. Advanced techniques to ensure the AI stays strictly within the retrieved documentation.
Module 10: Bedrock Agents Introduction
Architecture, instructions, and the agent lifecycle.
Module 10 Lesson 1: What are Bedrock Agents?
The Autonomous Brain. Understanding how Bedrock Agents use reasoning to solve multi-step problems.
Module 10 Lesson 2: Agent Instructions
Defining the Mission. How to write effective 'Agent Instructions' that guide an autonomous AI through complex workflows.
Module 10 Wrap-up: Designing your Agent
Hands-on: Design the mission statement and tool-set for your first Bedrock Agent.
Module 11: Action Groups and Tooling
Lambda-backed tools and API schema definitions.
Module 11 Lesson 1: Action Groups and Schemas
Defining the Capability. How to describe your APIs to a Bedrock Agent using OpenAPI schemas.
Module 11 Lesson 2: Lambda-Backed Tools
Connecting to Code. How to use AWS Lambda to execute the actual logic behind your agent's action groups.
Module 11 Wrap-up: Giving your Agent Skills
Hands-on: Write a Lambda function and a schema for an agent that can track package deliveries.
Module 12: Agent Reasoning and Orchestration
Planning, execution, and error recovery.
Module 12 Lesson 1: The Reasoning Loop
How Agents Think. Understanding the ReAct (Reason + Act) cycle that powers Bedrock's autonomous decisions.
Module 12 Lesson 2: Handling Agent Failures
Resilient Autonomy. How to design agents that can recover from API errors and tool failures gracefully.
Module 12 Wrap-up: The Master Planner
Hands-on: Trace the execution of a multi-step agent and identify reasoning bottlenecks.
Module 13: Multi-Agent Patterns
Planner-Executor and Supervisor patterns.
Module 13 Lesson 1: The Planner-Executor Pattern
Division of Labor. How to split 'Thinking' and 'Doing' between two different agents for higher reliability.
Module 13 Lesson 2: Supervisor Agents
The AI Manager. How to build a supervisor agent that routes user queries to the correct specialized sub-agent.
Module 13 Wrap-up: The Team Lead
Hands-on: Design the architecture for a multi-agent system that handles a complex business workflow.
Module 14: Human-in-the-Loop
Approval flows and feedback delegation.
Module 14 Lesson 1: Agent Approval Flows
Safe Autonomy. How to implement 'Pause and Approve' patterns to ensure humans sign off on high-stakes AI actions.
Module 14 Lesson 2: Escalation Strategies
Knowing your Limits. How to design agents that realize they are stuck and hand over the conversation to a human expert.
Module 14 Wrap-up: The Collaborative AI
Hands-on: Design a human-in-the-loop workflow for a high-value financial transaction agent.
Module 15: Observability and Monitoring
CloudWatch, tracing, and cost tracking.
Module 15 Lesson 1: Logging and Tracing
Sseeing the Thoughts. How to use CloudWatch and Tracing to debug your Bedrock Agents and see their step-by-step logic.
Module 15 Lesson 2: Cost Monitoring
Protecting the Wallet. How to track token usage and set up alerts to prevent unexpected AWS bills from your GenAI apps.
Module 15 Wrap-up: The Observability Suite
Hands-on: Create a CloudWatch dashboard that tracks your agent's success rate and token spend.
Module 16: Security and Governance
Secrets, prompt injection, and compliance.
Module 16 Lesson 1: Hardening the Agent
Locking Down the AI. How to use IAM roles and AWS Secrets Manager to ensure your agent can only access exactly what it needs.
Module 16 Lesson 2: Defending the Prompt
Prompt Injection Defense. Advanced strategies for preventing users from tricking your agent into tool misuse.
Module 16 Wrap-up: The Security Audit
Hands-on: Design a secure architecture that involves IAM, Secrets Manager, and Guardrails.
Module 17: Scaling and Production Readiness
Rate limits, concurrency, and versioning.
Module 17 Lesson 1: Versioning and Aliases
Safe Deployments. How to use Bedrock Agent Versions and Aliases to update your AI without breaking your production app.
Module 17 Lesson 2: Scaling and Retries
Handling the Peak. Advanced strategies for dealing with Bedrock's rate limits using exponential backoff and request queuing.
Module 17 Wrap-up: Ready for Production
Hands-on: Design a deployment strategy for a mission-critical AI agent.
Module 18: Introduction to AgentCore
Why AgentCore and enterprise use cases.
Module 18 Lesson 1: Introducing AgentCore
The Enterprise Orchestrator. Understanding why AgentCore exists and how it brings deterministic control to AI workflows.
Module 18 Lesson 2: AgentCore vs Basic Agents
Choosing the Right Tool. Comparing the strengths of autonomous Bedrock Agents and controlled AgentCore workflows.
Module 18 Wrap-up: The Enterprise Mindset
Hands-on: Identify a business workflow that requires the control and state management of AgentCore.
Module 19: AgentCore Architecture
Deterministic flows and state management.
Module 19 Lesson 1: AgentCore Nodes and Flow
The Blueprint. Understanding how AgentCore uses 'Nodes' and 'Edges' to create complex, manageable AI graphs.
Module 19 Lesson 2: Persistence and Recovery
AI with Memory. How AgentCore preserves state across days or weeks, allowing workflows to survive crashes and wait for human input.
Module 19 Wrap-up: Mapping the Logic
Hands-on: Design a multi-node AgentCore graph that includes AI reasoning and data validation.
Module 20: AgentCore with Knowledge Bases
Multi-stage RAG and verification.
Module 20 Lesson 1: Controlled RAG
High-Fidelity Search. How to use AgentCore to make your RAG systems more reliable by adding pre-search and post-search nodes.
Module 20 Lesson 2: Multi-Stage Reasoning
Chain of Thought Orchestrated. How to build complex reasoning pipelines where multiple AI models check each other's work.
Module 20 Wrap-up: The High-Fidelity Assistant
Hands-on: Design an AgentCore workflow that uses a critic node to verify RAG output.
Module 21: Capstone Project
Final enterprise assistant deployment.
Course Overview
Format
Self-paced reading
Duration
Approx 6-8 hours
Found this course useful? Support the creator to help keep it free for everyone.
Support the Creator