Domain 1 · 27% of the exam
Agentic Architecture & Orchestration
Domain 1 measures whether you can design systems in which Claude — not a hard-coded script — decides what to do next, and whether you can put the right structure around that autonomy: agentic loops driven by
stop_reason, coordinator/subagent topologies, explicit context passing, programmatic enforcement of critical orderings, hooks for deterministic guarantees, task decomposition strategies, and session state management. It is the largest domain (27%) because every other domain plugs into it: tools are only useful inside a loop, prompts only steer an agent that has somewhere to go, and context management only matters once an agent runs long enough to accumulate history. It is also the domain where the tempting answers are most often wrong — the exam repeatedly contrasts model-driven decision-making against pre-configured pipelines, and deterministic enforcement against prompt-based persuasion. Expect scenario-based items from the Customer Support Resolution Agent (Scenario 1), the Multi-Agent Research System (Scenario 3) and Developer Productivity (Scenario 4). 7 statements 22 examples 12 diagrams ~18 min
Take the quiz Study map
Choose a task statement
Each statement is a focused page. Your progress and quiz links still connect through the domain.
- 1.1 1 of 7
Design and implement agentic loops for autonomous task execution
stop_reason drives termination. The guide tests two values: "tool_use" iterates, "end_turn" exits. ~2 min · 3 examples · 1 diagrams - 1.2 2 of 7
Orchestrate multi-agent systems with coordinator-subagent patterns
Hub-and-spoke: the coordinator mediates every subagent interaction, so there are no direct subagent-to-subagent edges. ~2 min · 3 examples · 2 diagrams - 1.3 3 of 7
Configure subagent invocation, context passing, and spawning
allowedTools on the coordinator must include "Task" — without it the coordinator physically cannot spawn subagents. ~4 min · 4 examples · 1 diagrams - 1.4 4 of 7
Implement multi-step workflows with enforcement and handoff patterns
Prompt instructions and few-shot examples give probabilistic compliance; hooks and prerequisite gates give deterministic compliance. ~2 min · 3 examples · 2 diagrams - 1.5 5 of 7
Apply Agent SDK hooks for tool call interception and data normalization
PostToolUse hooks intercept tool results and transform them before the model processes them — the right place for data normalization. ~2 min · 3 examples · 2 diagrams - 1.6 6 of 7
Design task decomposition strategies for complex workflows
Prompt chaining (fixed sequential steps) fits predictable multi-aspect work; dynamic decomposition fits open-ended investigation. ~2 min · 3 examples · 2 diagrams - 1.7 7 of 7
Manage session state, resumption, and forking
Use --resume <session-name with meaningful names to continue a specific named investigation across work sessions. ~3 min · 3 examples · 2 diagrams