What this instrument rests on, and what it cannot do.
The prices are assumed, and the page labels them as such. The small and large tiers use assumed per-call
rates. The generative tiers use their measured latency against an assumed machine cost. The
human tier uses an assumed pace and salary. Change the assumptions and the dollars move.
The accuracies do not.
The human column is the one exception, an assumption until you measure it.
We assume 85% on each field, which the tool declares in its own source. Each other accuracy shown here was measured. npm run measure:humans -- --cases=your-file.csv
grades your own reviewers: accuracy per field with intervals, agreement between reviewers,
seconds per record. Pass the sealed result to optimise with --humans
and the optimizer reads your measurement instead of the assumption.
Your documents never touch this page, because nothing is uploaded and nothing is
fetched: the browser's own security rules refuse each network call.
These are our readings. Now test them against yours. Write to us: the free test measures up to
100 labeled pages of one document type with the tool, and the one-page report comes back by email within
48 hours of the measured record, at no charge. No document comes to us.