CCA-F: Claude Certified Architect — Foundations

By Anthropic · Question Mode

QuestionQ113

Prompt Engineering & Structured Output

You are developing a structured-data extraction system using Claude. The system extracts information from unstructured documents, validates its output with JavaScript Object Notation (JSON) schemas, and maintains high accuracy. It must gracefully handle edge cases and integrate with downstream systems.

After you implement tool use with strict schema definitions, JSON syntax errors are eliminated, but 5% of extractions still produce valid JSON containing empty arrays or null values for required fields such as citations and methodology. Spot checks show that the source documents contain this information, but in varied forms—inline citations versus bibliographies, and methodology sections versus details embedded in introductions.

What is the most effective way to address these failures?

Explanation

Few-shot examples that cover multiple document structures teach the model to recognize citations and methodology when the same information appears in different formats or sections. This addresses the semantic extraction gap while retaining strict schema validation for complete, reliably structured downstream data.

Community Discussion

No comments yet. Be the first to start the discussion!