CCARF Practice Question

Paper 3 · Question 24

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 gives subagents rigid step-by-step procedures (“run these exact five queries in this order”). Subagents fail whenever a topic doesn't fit the script. How should coordinator prompts be designed instead?

• A.Make the procedures longer, covering more contingencies explicitly
• B.Remove all instructions and let subagents infer their tasks
• C.Specify research goals and quality criteria — what a complete answer looks like — and let the subagent adapt its approach to what it discovers
• D.Have subagents ask the human operator whenever the script fails

Show answer & explanations

Correct answer: C

A: is an arms race against topic variety that scripts always lose

B: removes the goal along with the script

C: Goal-and-criteria prompts preserve subagent adaptability: the coordinator defines success, the subagent chooses the path — which is why the agent (not a fixed script) is there at all.

D: reintroduces a human into a loop designed to run autonomously

Related Agentic Architecture & Orchestration questions

More: Paper 3 · All practice questions