CCARF Practice Question

Paper 3 · Question 1

D1 Agentic Architecture & Orchestration · Paper 3

[Scenario 1: Customer Support Resolution Agent] You are building a customer support resolution agent with the Claude Agent SDK. It handles high-ambiguity requests (returns, billing disputes, account issues) via custom MCP tools — get_customer, lookup_order, process_refund, escalate_to_human — targeting 80%+ first-contact resolution while knowing when to escalate. You are implementing the agent's core loop. Which control flow correctly determines when to keep executing tools and when to present the final response?

• A.Continue looping until the assistant's text contains a phrase like “I have resolved the issue”, then stop
• B.Inspect stop_reason on each response: while it is “tool_use”, execute the requested tools and return results for the next iteration; when it is “end_turn”, present the final response
• C.Run exactly five iterations, since support cases rarely need more tool calls than that
• D.Stop as soon as any response contains text content, since text indicates completion

Show answer & explanations

Correct answer: B

A: parses natural language for a completion signal — a documented anti-pattern

B: The agentic loop keys off stop_reason: “tool_use” means the model has requested tools and expects their results back; “end_turn” means it has finished reasoning and produced its answer. That signal is the designed termination mechanism.

C: makes an arbitrary iteration cap the primary stopping mechanism

D: fails because responses can contain both text and tool_use blocks mid-task

Related Agentic Architecture & Orchestration questions

More: Paper 3 · All practice questions