CCARF Practice Question

Paper 3 · Question 21

D1 Agentic Architecture & Orchestration · Paper 3

[Scenario 3: Multi-Agent Research System] A coordinator agent built on the Claude Agent SDK delegates to specialized subagents — web search, document analysis, synthesis, and report generation — to research topics and produce comprehensive, cited reports. Your coordinator's system prompt tells it to delegate research to subagents, but at runtime it never spawns any — it attempts all the research itself. Its configuration restricts it to research-planning tools. What is the most likely cause?

• A.The coordinator model tier is too small to understand delegation
• B.Subagents must be started manually before the coordinator runs
• C.The system prompt needs the word “delegate” in capital letters
• D.The coordinator's allowedTools does not include “Task” — the Task tool is the mechanism for spawning subagents, so without it no delegation can occur

Show answer & explanations

Correct answer: D

A: and C look for the failure in comprehension or emphasis when the tool inventory makes delegation impossible

B: describes a startup model that does not exist — subagents are spawned on demand

C: This option does not best satisfy the scenario requirements.

D: Subagent spawning happens through the Task tool. A coordinator whose allowedTools omits “Task” has no mechanism to delegate, no matter how clearly its prompt describes the intention — capability configuration trumps instruction.

Related Agentic Architecture & Orchestration questions

More: Paper 3 · All practice questions