AI Skill Certs
Domain 1·14.7% of exam·7 concepts

Agents and Workflows

Decide between workflows and agents, construct Claude agents with the Agent SDK and custom harnesses, and apply core agent patterns and frameworks.

Official prep for this domain

Anthropic's own free prep module for this part of the syllabus, on the official prep course. Free with an Anthropic Academy sign-in.

1.1

Agent Architecture (4.5%): Principles, patterns, and tradeoffs of agent and workflow architecture, including the decision criteria for using a workflow versus an agent, the structure of manager/supervisor hierarchies, and the role of subagents in improving task execution.

1.2

Agent Construction with Claude (5.3%): Methods, tools, and platforms for constructing Claude agents, including the Claude Agent SDK, custom agent loops and harnesses, managed agent deployment models (self-hosted vs. Anthropic-hosted), and hooks for deterministic actions.

1.3

Agent Patterns and Frameworks (4.9%): Common agent design patterns (tool-use loops, sub-agents, memory, context-window management) and agentic abstraction frameworks (e.g., Strands, LangGraph, PydanticAI) for building agents and workflows for multi-step tasks.

Other exam domains

Domain 2 · 33.1%Applications and IntegrationDomain 3 · 3.1%Claude CodeDomain 4 · 2.6%Eval, Testing, and DebuggingDomain 5 · 16.8%Model Selection and OptimizationDomain 6 · 11%Prompt and Context EngineeringDomain 7 · 8.1%Security and SafetyDomain 8 · 10.6%Tools and MCPs
Back to all concepts