Skip to main content

Multi-document table

Generate a table of answers across multiple documents. Compare and analyse responses from many files in one view.

Written by Alina
Updated over a week ago

In this article:


Overview

The Multi-document table feature lets you ask multiple questions across multiple documents at the same time.

It returns the results in a structured table, with answers for each question and each document, making it easy to compare and review information across many files. The table can be exported to Excel or Microsoft Word for further analysis or reporting.


✅ When you should use this feature

  • To compare documents at scale
    Quickly analyse many documents at once without manual effort.

  • To review grouped document sets
    Examine related documents—such as a main agreement and its annexes—together to get consolidated answers.

  • To extract data and support reporting
    Export results to Excel or Word for easy sharing, reporting, and further analysis.

❌ When you shouldn’t use it

  • For small reviews or simple questions
    If you’re working with only a few documents, manual review or single questions may be faster.

  • When drafting or negotiating documents
    This tool is designed for analysis and comparison, not document creation or editing.


Step 1: Upload (a group of) documents

The first step is to upload the documents you want to use for your questions. LawVu Draft will treat these documents as separate.

However, instead of uploading individual PDF or DOCX files, you can upload groups of documents. This is useful when a contract or deal is not contained in one physical document, but spread across several related documents. Common examples include:

  • A main agreement with one or more schedules or annexes

  • An original agreement with multiple amendments signed over time

When these documents are uploaded as a group, the AI engine considers all of them together and finds answers across the entire set.

PDF files are automatically converted to DOCX format so LawVu Draft can read them. Depending on the length and complexity of the document, this conversion may take a few seconds or up to a minute.

To create a group, click the “…” button to the left of the regular upload area.

You can then upload one or more documents by dragging them into the popup upload area or selecting them from your computer, just like with the regular upload process.

You can also fetch the documents directly from LawVu:

<SCREENSHOT>

It’s recommended to rename the group from the default name (for example, Group 1), as this name will be shown later in the questions grid.

Step 2: Submit your questions

In this step, you define all the questions you want to ask across the selected documents.

You can either load an existing question set or create your own.

Configuring questions

When you click Create your own set…

  • Add as many questions as needed by clicking the green + Question button.

  • For each question, choose the type of answer you expect (for example, text, number, date, currency, or yes/no).

  • For each question, you can add additional instructions that LawVu Draft will take into account when formulating an answer to that question.

  • Multiple choice option can be useful whenever you already know what the possible answers can be.

  • Just as you can add additional instructions for a specific question, you can also do so for the entire set of questions

While Text usually works as a question type, choosing the most appropriate type is recommended - especially if you plan to export results to Excel. Correct question types ensure that dates, numbers, currencies, and yes/no answers are formatted properly in Excel, allowing calculations and sorting.

If you don’t plan to export to Excel, Text is a good default choice.

Save a question set

If you plan to reuse the same questions, you can save them for future use.

  1. Click the Save button at the top.

  2. Enter a clear name and an optional description for the question set.

If you loaded an existing question set and want to save your changes under a new name, click Save as new. Clicking the blue Save button instead will overwrite the existing question set.

3. By default, the question set is only visible to you. To share it with colleagues, select the appropriate access rights from the dropdown.

If you don’t see the access-rights dropdown, the permission Publish Multi-document Chat Questions is not enabled for your account by your LawVu Draft administrator.


Step 3: Results

In the final step, click the Process documents button to start generating results.


If multiple AI models (LLMs) are available in your account, you can select a specific one from the dropdown before processing.

LawVu Draft will then analyse each selected document and answer each of your questions. As processing runs, results will appear progressively in the table.


Notes

  • Depending on your screen size and number of selected documents, at some point horizontal scrolling with the scrollbars at the bottom may become necessary.

  • You can click on the button in the upper left corner to "rotate" the table, i.e. to switch the position of the questions (left-side by default) and filenames (top-row by default).

  • You can hover over the answer itself (other than the number) to get a short explanation on the reasoning behind the answer.

  • You can hover over a number to get a popup-window with the relevant paragraph that was used by the AI-engine to formulate its answer.

  • You can click on a number to navigate to the relevant part of the document.

  • You can click on MS Word (DOCX) or MS Excel (XLSX) to export the results to Word or Excel.

    • Because MS Word is limited by paper size, each document's questions are answered in a separate table.

    • The Excel-file will follow the currently selected "rotation" of the table.

  • If you like, you can go back to Step 2 and add additional answers, or even go back to Step 1 and add additional documents.

Usage considerations

Bear in mind that the Multi-document Chat eats up a lot of "tokens" from the LLM, particularly when the document is long and/or you are asking many questions.

Did this answer your question?