Replacing a document is harder than uploading one
The file list can look current while search, preview, and extracts still answer from yesterday.
Paris Perlegkas
27/08/2026
Building layout-assisted field extraction
Reuse the layout map already stored at index time, match each extracted value back to a page region, and return boxes the preview can paint.
Paris Perlegkas
20/08/2026
Make AI answers auditable
A valid extract still isn’t enough if nobody can open the page and see where each field came from.
Paris Perlegkas
10/08/2026
Building schema-first extraction with validators
Strict JSON Schema at the model boundary, optional business rules after it, and an audit trail that survives the handoff.
Paris Perlegkas
06/08/2026
Mostly-right data extraction isn’t operational data
Soft JSON from document extraction passes the demo; operational data needs a declared shape and rules you can fail.
Paris Perlegkas
02/08/2026
Building registry-based extraction for any document type
Two-level discovery and a tenant allowlist in front of lookup are how a new document type, or a new field set of an old type, lands without touching the engine.
Paris Perlegkas
23/07/2026