nofolder

Honesty page

How the index works — exactly

What runs on your documents

Deterministic rules. No AI model, no cloud processing. When you ingest a document, fixed pattern rules read its text layer and extract three kinds of facts. Every fact is stored with evidence: the exact text span and the rule ("cue") that fired. That is why quality here is a number and not an adjective.

FactHow it is extracted
DeadlinesA date counts as a deadline only when an obligation cue sits just before it in the text — due by, expires, no later than, must be completed by, deadline is, an obligation verb + by, and kin. Invoice dates, effective dates, "scheduled for", and past references are recorded as mentions, never deadlines.
PeopleNames in labeled positions (From:, Bill To:, Attendees:, Landlord:, technician:), salutations, "between … and …" contract parties, and signature blocks. Organization names are filtered out by suffix rules.
TagsDocument type by cue scoring (invoice / contract / letter / memo / note / receipt), plus topic tags from a published keyword map.

What it cannot do — printed on the box

The measured scores

Test corpus: 24 synthetic documents (invoices, contracts, letters, memos, notes, receipts, 2 text-layer PDFs, 2 images) generated for this product, scored against a written answer key. Latest run of the shipped engine:

FieldPrecisionRecallCounts
Deadlines (by date)1.001.0013 found / 13 expected / 0 invented
Deadline kindaccuracy 1.00 on matched13 / 13
People1.001.0026 / 26 / 0
Tags0.910.9651 right / 5 extra / 2 missed
Document typeaccuracy 0.9623 / 24

Known misses, kept in the open: the plant-rota note is typed as a plain document; a follow-up letter is not tagged client; two documents earn a topical tag (payment, legal) the answer key did not assign. The regression job replays this corpus on every engine change.

Your documents

The MVP retains the extracted text and the index facts so browsing and search work. It does not retain your original file bytes, it never trains anything on your documents, and no third-party AI service sees them — there is no AI service in the loop.