Lab PDF data extraction, handover documentation, imaging governance, WCAG evidence packs. Schema first. No hallucinated cells.
They are structured badly. A Certificate of Analysis has columns; they just have no borders. A vendor data book for an oil and gas handover has a contents list, data sheets, and certificates of conformity that do not share a filename convention. A DICOM governance pack cares about study instance UIDs, retention, and who could export a series — not a pretty gallery. A WCAG conformance evidence pack is a trail: pages tested, criteria (1.4.3 Contrast, 2.4.1 Bypass Blocks), artefacts, residual risk.
Generic “document AI” products optimise for a paragraph summary. That is the wrong artefact. You need rows that survive an audit.
Lock a schema with the people who sign the report. Collect a gold set. Try the cheap parsers; they usually fail on borderless tables — we documented that on SI Report Analyser. Then cluster text positions, dual-parse, and emit exceptions. Humans resolve exceptions. The model, if we use one at all, proposes a mapping; it does not write a concentration.
The same pattern applies to funder data import sheets: the destination columns are the schema. Extraction is successful only if the sheet validates.
See also geotechnical CoA screening and funder impact reporting.
Structured capture of sample IDs, determinands, units, results and methods from laboratory PDFs so they can be screened or loaded into a schedule. It is not a generic 'ask the PDF' chatbot. Unreadable cells are flagged, not invented.
Oil and gas handover packs and vendor data books, DICOM and medical imaging governance records, WCAG conformance evidence packs, Ofsted safeguarding files, and funder data import sheets. Each family gets its own schema.
Worked example: extracting AGS data from lab PDFs, and the SI Report Analyser case study.