CCARF Practice Question

Paper 5 · Question 39

D4 Prompt Engineering & Structured Output · Paper 5

[Scenario: Customer Support Agent] Production logs show the agent sometimes chooses `get_customer` when `lookup_order` would be more appropriate, especially for ambiguous queries like “I need help with my recent purchase.” You decide to add few-shot examples to the system prompt to improve tool selection. Which approach most effectively addresses the problem? Which approach is most effective?

• A.Add explicit “use when” and “don’t use when” guidance in each tool description covering ambiguous cases.
• B.Add examples grouped by tool—all `get_customer` scenarios together, then all `lookup_order` scenarios.
• C.Add 4–6 examples targeted at ambiguous scenarios, each with rationale for why one tool was chosen over plausible alternatives.
• D.Add 10–15 examples of clear, unambiguous requests demonstrating correct tool choice for typical scenarios for each tool.

Show answer & explanations

Correct answer: C

A: Use-when and don't-use-when lines are another rule list. The failures are the ambiguous cases, which need a comparison.

B: Examples grouped by tool never show the choice between the two tools.

C: Targeting few-shot examples at the specific ambiguous scenarios where errors occur, with explicit rationale for why one tool is preferable to alternatives, teaches the model the comparative decision process needed for edge cases. This is more effective than generic examples or declarative rules.

D: Easy examples do not teach the "recent purchase" cases where the errors happen. More of them is not the gap.

Related Prompt Engineering & Structured Output questions

More: Paper 5 · All practice questions