Skip to main content

Agentic AI: 12 Building Blocks

A practical, hands-on series that walks you through the 12 core concepts behind every production AI agent. Each module focuses on one building block, explained through a document processing workflow that applies to any industry.

This series is the companion to our blog post: The 12 Building Blocks Behind Every AI Agent We Deploy.

The Use Case​

Throughout this series, we build a contract processing agent that:

  • Extracts key terms from incoming PDFs
  • Checks clauses against company policies
  • Flags compliance risks
  • Routes to legal for human review
  • Generates executive summaries

Every concept is taught through this single, real-world workflow.

The 12 Modules​

#ModuleWhat You'll Learn
1MCP (Model Context Protocol)How agents connect to external tools, APIs, and data sources through a unified standard
2Tool UseHow AI models call external functions and take action in the real world
3Prompt ChainingHow to break complex analysis into focused, debuggable steps
4OrchestrationHow to coordinate multiple agents working toward a shared goal
5SubagentsHow to design focused, single-purpose agents that work within a larger system
6RAG (Retrieval Augmented Generation)How to give agents access to your organization's knowledge at query time
7GroundingHow to connect agent outputs to verified data and prevent hallucinations
8GuardrailsHow to set boundaries that keep agents safe and compliant
9Human-in-the-LoopHow to design approval workflows where agents pause for human decisions
10MemoryHow agents retain and retrieve information across sessions
11ObservabilityHow to monitor, trace, and debug agent decisions in production
12EvaluationHow to measure whether your agent is actually getting better

Prerequisites​

  • Basic understanding of AWS services (Lambda, DynamoDB, S3)
  • Familiarity with Python
  • An AWS account with Bedrock access

Who This Is For​

  • Engineers building their first AI agent system
  • Architects evaluating agentic AI patterns for their organization
  • Technical leaders who need to understand what their teams are building