CCARF Practice Question

Paper 3 · Question 9

D5 Context Management & Reliability · 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. A customer's first message is: “I want to speak to a human. Do not try to fix this yourself.” The issue looks like a routine replacement the agent could resolve. What should the agent do?

• A.Attempt resolution first, escalating only if the attempt fails
• B.Run sentiment analysis and escalate only if frustration exceeds a threshold
• C.Escalate immediately — an explicit customer request for a human is honored without first attempting investigation
• D.Ask the customer three clarifying questions before deciding

Show answer & explanations

Correct answer: C

A: and D do exactly what the customer forbade

B: substitutes an unreliable proxy (sentiment) for a signal that could not be clearer — the customer already said the words

C: Explicit customer demands for a human are a first-class escalation trigger, honored immediately. Overriding a stated preference to demonstrate capability damages trust regardless of how resolvable the issue looks.

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

Related Context Management & Reliability questions

More: Paper 3 · All practice questions