CCARF Practice Question

Paper 3 · Question 51

D4 Prompt Engineering & Structured Output · Paper 3

[Scenario 6: Structured Data Extraction] You are building a structured data extraction system: pulling information from unstructured documents, validating output against JSON schemas, handling edge cases gracefully, and integrating with downstream systems. Your current pipeline asks Claude to “respond with JSON” in plain text; downstream parsing breaks on markdown fences, trailing commentary, and occasional malformed syntax. What is the most reliable structural fix?

• A.Strengthen the prompt: “respond ONLY with valid JSON, no exceptions”
• B.Post-process the text with regexes that strip fences and repair syntax
• C.Define the extraction as a tool whose input schema is your JSON schema, and read the structured data from the tool_use block — guaranteeing schema-compliant output and eliminating JSON syntax errors
• D.Switch to XML output, which models format more carefully

Show answer & explanations

Correct answer: C

A: improves the odds within a fundamentally text-shaped channel

B: patches symptoms with fragile repairs

C: Tool use with JSON schemas is the reliability mechanism for structured output: the model's extraction arrives as schema-conformant tool input, not as prose that happens to contain JSON — syntax errors are eliminated by construction.

D: relocates the same free-text problem to a different syntax

Related Prompt Engineering & Structured Output questions

More: Paper 3 · All practice questions