CCARF Practice Question

Paper 1 · Question 51

D4 Prompt Engineering & Structured Output · Paper 1

Your document processing pipeline chains three steps: (1) extract raw text, (2) classify document type, (3) extract structured fields based on type. Step 2 occasionally misclassifies invoices as purchase orders, causing step 3 to extract the wrong fields. The team proposes combining steps 2 and 3 into a single prompt to reduce errors. What is the better approach?

Show answer & explanations

Correct answer: B

Related Prompt Engineering & Structured Output questions

Paper 1 Q14A validation-retry loop still fails on the same documents after three attempts each. In which situations will further retries not help? (Sel…Paper 1 Q17Your data extraction pipeline uses tool_use with tool_choice set to 'auto'. You need guaranteed structured output for every request, but som…Paper 1 Q18Your extraction pipeline validates that line item amounts sum to the stated total. For Document A, the sum is £450 but the stated total is £…Paper 1 Q25The pipeline validates each tool_use extraction against a Pydantic model with model_validate(). Validation succeeds and every field has the …Paper 1 Q26An extraction pipeline uses `tool_use` with a 15-required-field schema. For some document types, only 8 of those fields ever appear in the s…

More: Paper 1 · All practice questions