CCA-F: Claude Certified Architect — Foundations

A document-extraction tool uses ML models to extract invoice fields (vendor, amount, date). The models return confidence scores (0.0–1.0) for each extracted field. In production, you observe:

1. The agent proceeds with low-confidence extractions that are incorrect 23% of the time.
2. The agent requests unnecessary human review for 31% of extractions that were actually correct.

How should the tool’s output be restructured?