Analect Proof

Compare answer quality and token use on the same questions

Access arranged as part of a pilot

Analect Proof is the measurement workflow in the Analect platform. It takes a document and its decomposition, asks the same questions of both against a model you choose, and totals the tokens each route consumed. It reports three things separately: whether the answers agreed with each other, whether they were correct against ground truth you supply, and whether they were complete.

Why measurement leads

Why proof comes first

Most claims about AI retrieval are made in a deck and tested nowhere. Proof exists so that the first conversation with your finance team is about numbers from your own documents rather than numbers from ours — including the questions where the fragment route did no better.

How it works

Three steps to a number

Step 1

Pick the data and the baseline

A document from your library or a fresh upload, and the baseline to compare against: the model reading it whole, your current retrieval workflow, or both.

Step 2

Pick the model and supply ground truth

Any model from the catalog, and the known-correct answers to score against where you have them. Without ground truth the test can only report agreement, not correctness.

Step 3

Run the test

The same questions go to each route. The report gives agreement, correctness where ground truth exists, completeness, and the token totals per category. It exports.

What Proof reports

Four measures, never conflated

Agreement, correctness and completeness answer different questions, and a tool that reports one of them as all three is not measuring anything useful.

Baseline agreement

Did the fragment answer say the same thing as the same model's whole-document answer? This is what our published test measured, on nine direct factual questions, and it matched on eight of them.

Factual correctness

Was the answer true, judged against known ground truth? An error shared by both routes counts as agreement but not as correctness. We have not published this separately.

Completeness

Did the answer contain everything a complete answer needed? An answer can agree with the baseline, be factually correct, and still omit a material fact that both routes dropped.

Citation support

Can every statement in an answer be traced to the assertion it came from? Fragments carry a link to their source sentence by construction, which is a property of the design rather than a benchmark result.

The evidence

What we found on our own material

On nine direct factual questions across two documents, fragment answers agreed with the same model's whole-document answers on eight, using 70 to 77 percent fewer retrieved context tokens. Agreement is not correctness: we have not published factual correctness or completeness as separate measures, and the ninth question is not yet published with its reason.

Retrieved context tokens used to answer one direct factual question, whole document against fragments, on ETT's own two-document sample. Excludes the cost of decomposing the documents, and does not report total billed tokens separately.

The full method record, including what is not yet published

Honest scope

The zeroes are part of the report

Proof reports the zeroes as well as the wins. Whole-document workloads cost more on fragments, and the report says so. That is the point: a result you can take to a CFO has to be a result that could have gone the other way. Where a question came back worse on fragments, the report shows the question, both answers and the reason.

The output

What a scored question contains

One row per question, per route. The report is only worth anything if a row can come back negative, so every field below is reported whichever way it goes.

FieldWhat it contains
The questionAs asked, chosen before anyone saw the fragments.
Answer, per routeWhat each route returned: the whole-document baseline, your existing retrieval workflow where you have one, and the fragment route.
AgreementDid the fragment answer say the same thing as the baseline? Agreement only. It says nothing about either answer being right.
CorrectnessScored against ground truth you supply. Without ground truth this field is empty, and the report says so rather than substituting agreement for it.
CompletenessDid the answer contain everything a complete answer needed? An answer can agree, be correct, and still omit a material fact both routes dropped.
CitationsWhich fragments were used, and the source sentence each came from, so a reviewer can check rather than trust.
Tokens, by categoryRetrieved context, total input, output. Reported separately, because a percentage without its category is meaningless.
VerdictIncluding “no better” and “worse”. These rows stay in the report.

This is the shape of the report, not a result. The figures in yours come from your own documents.

Established on your material

What we will not claim in advance

These are answered by running this on your own documents, not by a specification sheet. They are the things most likely to decide whether the approach works for you, which is exactly why guessing at them would be unhelpful.

  • Which baselines to compare against — the whole-document read, your current retrieval workflow, or both
  • Whether you have ground truth for the questions, and if not, who will mark the answers
  • How many questions and documents constitute a sample you would actually believe

Run the test on your documents.

A pilot runs the same questions against your documents and their fragments, marks the answers and totals the tokens, so the evidence is yours rather than ours.

Region & currency

Changes spelling, terminology, the data-protection regime named in our notices, and the currency used in indicative figures. It does not change where we are or quote you a price in your currency. ETT is headquartered in Dallas, with offices in London and Vancouver.