> For the complete documentation index, see [llms.txt](https://help.jurisphere.ai/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://help.jurisphere.ai/parallel-review/overview-of-the-parallel-review-tool.md).

# Overview of the Parallel Review tool

The **Parallel Review tool** is a powerful feature designed to extract and organize multiple pieces of information from multiple documents into a structured, easily consumable table format. It is particularly useful when you need to answer several questions across a **large collection of documents**, providing a clear and concise overview of the data.

## Key Features

<details>

<summary>Intelligent Query Expansion</summary>

Jurisphere's intelligence expands your initial broad query into a set of precise, legally relevant questions, mimicking the review process of a well-trained lawyer. Your initial query will be a question that, once submitted, will be automatically expanded into robust and specific questions to query across your documents.

<figure><img src="/files/T01bZoj7yZJnJbjM66KB" alt=""><figcaption></figcaption></figure>

</details>

<details>

<summary>Customizable Questions</summary>

While the tool intelligently expands your query, you have complete control to add, modify, or delete any of the generated questions to perfectly align with your specific research needs.

</details>

<details>

<summary>Structured Output</summary>

All responses in the Parallel Review tool are generated in a tabular format. Each row is dedicated to a separate document from your selection, and your questions (or information points) become the column headers. The cells contain the extracted answers from each respective document.

</details>

## When to use the Parallel Review tool vs the Document Review tool.

| Parallel Review                                                                                                                                                                            | Document Review                                                                                                                                                                                                                                                       |
| ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------ | --------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
| Suitable for tasks requiring the extraction of the <mark style="color:green;">**same set of information across a large volume of documents**</mark>.                                       | Best suited when you have <mark style="color:green;">**one specific question**</mark> (or trail of questions) whose answer is expected from a small set of documents.                                                                                                 |
| Answers will be distinct for each document - the tool will not compare two different documents, or analyze documents in bunch. <mark style="color:orange;">**No shared context**</mark>.   | Answers will always be consolidated from the set of selected documents, and context from all documents will be considered. <mark style="color:orange;">**May not examine each document separately**</mark>.                                                           |
| Can simultaneously process <mark style="color:green;">**up to 50 questions**</mark> across <mark style="color:green;">**over 1000 documents**</mark> (up to 5GB of data) in a single task. | Optimal maximum usage is <mark style="color:green;">**between 20-50 documents**</mark> in a single task, and only one question at a time.                                                                                                                             |
| <p>Recommended for:</p><ul><li>Vendor due diligence</li><li>Mass review of case laws</li><li>Review of trademark applications</li></ul>                                                    | <p>Recommended for:</p><ul><li><a href="/pages/nhSdG6f1Kgenc2Q8i6mT">Contract review</a></li><li><a href="/pages/xihH5rG8cmXTg1wZdu35">Drafting pleadings and notes</a></li><li><a href="/pages/nhSdG6f1Kgenc2Q8i6mT">Interactive analysis and drafting</a></li></ul> |


---

# Agent Instructions
This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com.

## Querying This Documentation
If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question.

Perform an HTTP GET request on the current page URL with the `ask` query parameter, and the optional `goal` query parameter:

```
GET https://help.jurisphere.ai/parallel-review/overview-of-the-parallel-review-tool.md?ask=<question>&goal=<endgoal>
```

`ask` is the immediate question: it should be specific, self-contained, and written in natural language.
`goal` is optional and describes the broader end goal you are ultimately trying to accomplish on behalf of the user. GitBook uses it to tailor the answer towards what is most useful for that goal.

The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.