CCARF Practice Question

Paper 5 · Question 34

D4 Prompt Engineering & Structured Output · Paper 5

[Scenario: Customer Support Agent] Your agent handles single-issue requests with 94% accuracy (e.g., “I need a refund for order #1234”). But when customers include multiple issues in one message (e.g., “I need a refund for order #1234 and also want to update the shipping address for order #5678”), tool selection accuracy drops to 58%. The agent usually solves only one issue or mixes parameters across requests. What approach most effectively improves reliability for multi-issue requests? What approach is most effective?

• A.Implement a preprocessing layer that uses a separate model call to decompose multi-issue messages into separate requests, handle each independently, and merge results.
• B.Combine related tools into fewer universal tools.
• C.Add few-shot examples to the prompt demonstrating correct reasoning and tool sequencing for multi-issue requests.
• D.Implement response validation that detects incomplete answers and automatically reprompts the agent to resolve missed issues.

Show answer & explanations

Correct answer: C

A: A separate model to split the message adds a call and a merge before the agent has been shown how to handle two issues in one turn.

B: Fewer, broader tools make it easier to mix parameters across issues.

C: Few-shot examples that demonstrate correct reasoning and tool sequencing for multi-issue requests are most effective because the agent already performs well on single issues—what it needs is guidance on the pattern for decomposing and routing multiple issues and keeping parameters separated.

D: A reprompt catches a miss after the answer is already incomplete. It does not teach the sequencing.

Related Prompt Engineering & Structured Output questions

More: Paper 5 · All practice questions