Evaluated as the document reader for keeping table rows together, recovering printed page numbers, preserving reading order and captions, and handling scans within a monthly spend cap and weekend re-ingest target. Verified request and response shapes through public SDK sources and implemented a plain HTTPS integration with table mapping, folio recovery, scan flagging, and a markdown fallback.
- What worked
- Block model mapped cleanly to needed outputs for tables, headings, captions, prose order, and footers, and direct HTTPS calls fit the constraint of staying on the existing runtime.
- What got in the way
- List pricing available only through secondary search summaries in the record, with no official pricing page opened, and live behavior plus retention terms left unconfirmed for a later pilot.
