---
title: "Impossible Questions: asking across many documents at once"
seo_title: "Impossible Questions: asking across many documents at once | SazAI"
description: "Questions that need many documents read together, answered with the document and the element each finding rests on."
tags: [marketing]
---

> For the person who has to answer a question about the whole library, not about one file.

**Here, an impossible question is one that is impractical to answer by reading the documents one after another, at the scale and in the time available. It is the name of a way of asking, not a promise.**

<div class="chap">

<h2 id="thesis">Questions that appear when documents are read together</h2>

<h3 class="sub">Answered with an address you can check</h3>

Some questions are not about any single file. Which of forty proposals still carry a hidden slide? Between two versions of a deck, which numbers in the text changed? Which contracts in a folder still hold comments, and what do they say? SazAI Corpus reads each document once, element by element, and keeps the record: what each file holds, which file SazAI Corpus produced from which, and the comparisons already run. [The assistant you use](interfaces) asks over that record, and each finding can come with the document and the element it rests on, so you can open it and check.

</div>

<div class="chap">

<h2 id="gate">What makes a question impossible</h2>

<h3 class="sub">It needs at least one of three things</h3>

**All of them, with the count.** "Of all the proposals, which…", "none of them", "which has the most". A search that returns the closest passages cannot say "all". A query can be paged through to the end of the scope you set, and the answer says, beside it, what was not read. Example: of the forty proposals in this folder, which carry a hidden slide?

**The library's memory.** The versions SazAI Corpus produced from a file, and the comparisons it ran between two files. These records come from Corpus itself, not from the files. Example: which versions were produced from the same source file, and which pairs have already been compared?

**The layer under the text.** Formulas, hidden slides, comments, image descriptions, signature fields. A tool that keeps the text alone drops this layer before anyone asks. Example: which contracts still hold comments, and what do they say? Signature fields are read as they are declared: SazAI Corpus does not verify a signature.

A question that needs none of the three is an ordinary question, and it gets an ordinary answer.

</div>

<div class="chap">

<h2 id="method">How to read a finding</h2>

<h3 class="sub">What a finding in this mode should carry</h3>

- **The bridge.** Two documents, or two versions of one, and the element that links them: a formula, a version, a sheet that lines up, a shared term. No bridge, no finding.
- **Two explanations at least.** Such as a shared source, a common template, or chance, and the item that tells them apart. Evidence that fits every explanation decides nothing.
- **The coverage.** How many documents were covered, which were left out, and what was not read.
- **The address.** The document, and the slide, page, paragraph or cell.
- **The next check.** The one whose opposite result would most change the conclusion.

An inconclusive result is a result. Ask for these points in your question; a finding that lacks one of them is a lead, not a finding.

</div>

<div class="chap">

<h2 id="scenes">What SazAI Corpus does here</h2>

<h3 class="sub">Scenes scored in a run</h3>

No question in this mode has been scored in a run yet. Scenes appear here when one is.

</div>

<div class="chap">

<h2 id="does-not">What SazAI Corpus does not do</h2>

<h3 class="sub">In this mode, today</h3>

Corpus does not:

- promise that something will be found;
- say whether there was fraud, intent, or a breach of a rule;
- read a missing link as proof that two documents are unrelated, or two similar texts as proof that one was copied from the other;
- read an order in time as a cause.

Corpus reads and records; your AI reasons over it; you decide. The fields where this applies: [Audit](audit), [Compliance](compliance), [Financial services](financial-services), [Legal](legal), [Life sciences](life-sciences) and [Real estate](real-estate). To talk to us: [contact](contact).

</div>

<div class="chap">

<h2 id="reading">Reading list</h2>

<h3 class="sub">The basis of the method</h3>

The method is built on this published work. Citing it does not mean its authors endorse SazAI.

- Swanson, D. R. (1986). Undiscovered Public Knowledge. *The Library Quarterly* 56(2), 103 to 118.
- Pirolli, P., Card, S. (2005). The Sensemaking Process and Leverage Points for Analyst Technology. International Conference on Intelligence Analysis.
- Heuer, R. J. (1999). *Psychology of Intelligence Analysis*, chapter 8, Analysis of Competing Hypotheses.
- Buneman, P., Khanna, S., Tan, W. C. (2001). Why and Where: A Characterization of Data Provenance. ICDT 2001.
- Howard, R. A. (1966). Information Value Theory. *IEEE Transactions on Systems Science and Cybernetics* 2(1), 22 to 26.
- Kastrin, A., Cestnik, B., Lavrač, N. (2025), and Alkan, A. K. et al. (2025): surveys of literature based discovery and of hypothesis generation.

</div>