Comparison

Retrieval, re-reading, and retention

Three ways to put a long document in front of a model. The figures below come from our controlled study on the standard legal RAG benchmark; the full methodology is published.

RAG (retrieval)Whole-document re-readingRetention (Revyzor)
What the model seesFragments chosen by a search engine before the model ever reads themThe whole document, read section by section on every questionThe whole document, read once; the working state is retained
Exact clause accuracyBaseline. On the longest agreements in our study: 0 of 313x baseline; 10x on merger agreementsSame accuracy as the structured read: it is the same read, retained
Cost per follow-up questionOne retrieval round trip, but against the wrong evidenceA full re-read: ~5.7x the wall-clock of a single-shot answer, every timeAbout 2.6 MB appended per follow-up, and a reload at roughly 7x less GPU time than the re-read; the read is never repeated
When the answer is challengedNo record of what the model considered; the chunks are goneA prompt log at best; the working state was discardedThe retained working state, cryptographically signed, reloadable for inspection
Session continuityNone: every question starts from scratchNone: every question starts from scratchSuspend Friday, resume Monday from the exact same state

The pattern: whole-document reading is the best clause-finder in the study, and its only real cost is the repeated read. Retention keeps the accuracy and removes the repetition. The retained state then does double duty as the compliance record: signed at capture, reloadable for inspection, held under an explicit retention policy.

How does this compare to Harvey or Legora?

It doesn’t compete with them; it sits underneath that kind of tool. Harvey, Legora, and most legal AI products are applications: a legal workflow and interface built on top of frontier models running in a US cloud, with retrieval deciding which fragments of your documents the model sees. Revyzor is infrastructure: a plug-in for the engine that runs an open-weights model on your own servers, in your own jurisdiction, under your own keys.

The practical difference: with an application, your client documents travel to someone else’s cloud and the model answers from retrieved fragments. With a Revyzor-backed stack, the documents never leave your infrastructure, the model reads them whole, and every read is retained as a signed, inspectable record. A Harvey-style application could, in principle, be built on top of it.