QA rendered content for extraction errors

Audit rendered content for source extraction artifacts

QA text content when you need to detect HTML/entities, page numbers, OCR gibberish, dropped words, truncation in rendered fields.

• · corpus domain (Bible verses, commentary, library chapters)

• · verified real issues + false-positive categorization + semantic findings (mis-mapping) + executive fix plan

• · Deterministic scanner (counts mechanical hits)
• · Grep (sampling)
• · reader agents (judgment)

Corpus must be rendered via React Native (no HTML/markdown interpretation); rendered fields must be identified.

Scanner over-counts false positives (years, alt numbering); reader misses semantic issues; files too large to sample effectively.