Interactive demo · pre-computed model outputs · 100% synthetic data

Two reads.
Seven gates.

A verification pattern for AI document extraction: consensus finds the doubt, deterministic gates decide the output.

Two independent model reads of the same document are diffed against each other — any disagreement is treated as a signal, not an error to average away. What actually ships is then decided by seven deterministic checks that run as plain code, every time.

01 Pick a document

02 The document

03 Two independent reads pre-computed

Model read A

Model read B

04 Consensus diff runs live

FieldRead ARead BStatus

05 Seven deterministic gates runs live

    06 Why this shape

    A single model read fails silently: an ambiguous date, a hallucinated field, a faithfully-copied typo all come back looking equally confident. Running the same document through two independent reads and diffing the results turns silent failure into a visible disagreement — cheap to compute, impossible to ignore.

    But agreement is not correctness (try the third document). So no model output ships on consensus alone: a layer of deterministic gates — checksums, format rules, date arithmetic, required-field checks — makes the final call in plain code. Models propose; gates dispose. This demo mirrors a pattern running in a document-extraction engine in production for a client, rebuilt here with fully synthetic data and pre-computed model outputs so it can run anywhere, for free, with no API keys.