Skip to main content
All CollectionsHow-To Guides
Vault
Vault

Discover how to use Vault for rapid document analysis with Harvey's AI.

Updated yesterday

Overview

Vault is a powerful tool that enables you to upload hundreds of documents to a project and conduct advanced analysis using Harvey’s AI models. It’s especially valuable for workflows that involve reviewing large document sets.

Vault Tab

To see a list of projects, or create a new one, click into the 'Vault' section in the left sidebar of Harvey.

Create a Project

  1. Click the 'New Project' button in the top right corner of the Vault page.

  2. Enter a Project Name.

  3. Select documents you wish to upload.

  4. Click 'Create Project' in the bottom right corner.

Use a Project

  1. Select the Project you wish to use in your Vault tab.

  2. Click on the 'Review query' dropdown menu.

  3. Select 'Review query' or 'Ask query'.

    1. Review Query: Get answers from each document separately in a table.

    2. Ask Query: Get one answer based on collective information across all documents.

Ask Query

Harvey will analyze the attached document(s) and load a response. On this page, you have a few additional options:

  • View Original Query: Located under the results header in the top left.

  • New Query: In the top right corner, this option allows you to edit your original query and generate new results.

  • Export: Export current results with or without citations.

Review Query

Harvey will fill each column in the table based on the prompt you entered, applying it to each document. On this page, you also have a few additional options:

  • Short vs Long Answer Filtering: you can see and filter short vs long answers - short answers are 1 word or sentence answers. Long answers are multiple sentences and extracting.

  • Export: you can export the whole table or sub-selected rows into an Excel sheet.

  • Document View: if you click a document, you can view each answer and relevant sources.

Example Queries

Litigation (1000 Discovery Emails)

  • Ask Query: "Who accepted the open international energy coordinator position?"

  • Review Query: "For each email, tell me the participants and a summary of what they discussed."

Capital Markets (1000 10-Ks)

  • Ask Query: "Explain the effective interest rate of the Company's Term Loan B, and whether the Company made any disclosures related to the LIBOR transition."

  • Review Query: "For each of these 10-Ks, provide the name of the company, the year it was filed, and a summary of what ESG disclosures were made."

M&A (1000 MSAs)

  • Ask Query: "Do any of these agreements contain an acceleration clause that would take effect in the event of a change of control or assignment?"

  • Review Query: "Show me every contract that has change of control provisions and, for those that do, tell me if the contract allows for termination on a change of control."

Delete or Rename a Project

From the Vault tab:

  1. Hover over the project you wish to change.

  2. Click on the ellipsis menu in the top right corner of the project.

  3. You will have the option to either Rename project or Delete the project.

    1. If you choose to delete your project, you will be prompted again to confirm this decision as this action will permanently delete the project and all associated sub-folders and files. Once a project is deleted, it cannot be recovered.

Data Security & Privacy

Data Storage Buckets

Vault projects and data adhere to the specific workspace and territory-level data storage buckets assigned by Admins. For example, if data is saved in an EU storage bucket, Vault files will also be stored there.

Data Retention Periods

There are two types of data retention periods related to Vault: query retention and projects & data retention.

  • Query Retention: The default retention period for Vault queries is 48 hours, unless your firm's retention period is longer. This ensures that users can access and export their review queries, which can take 20-40 minutes to run, before they are deleted.

  • Projects & Data Retention: Vault projects and data remain stored until the user deletes them, independent of workspace or territory-level retention policies.

Important Note: Once Vault projects, queries, files, or data are deleted, they cannot be recovered by Harvey or the customer.

FAQ

Q: Why don't I see Vault in my navigation pane?
A: This is likely because Vault is not part of your workspace configuration or plan. Please contact your Harvey Admin to explore how you can gain access.
​

Q: Does a user's uploaded documents in Vault help "train" Harvey's AI for other customers?

A: No, all data uploaded to Harvey only helps improve outputs for the user who uploaded it. Harvey does not retain data to train its AI models.

Q: How does Vault differ from using Assistant DocQA with a large number of documents?

A: When a user uploads 5 or more documents in Assistant, Harvey has to understand the content of the documents 'on the fly.' While we've improved this process over time, using Assistant DocQA limits the number of files to 50 and constrains deep analysis.

Vault, on the other hand, allows Harvey to store and proactively process a user's documents, leading to:

  • Querying sub-folders and files

  • Document-type AI routing (e.g., NDAs, Leases)

  • Improved performance on 'needle-in-the-haystack' problems, such as finding a single name across 1,000 documents

Q: What are the review evaluation benchmark's for Vault?

A: We’ve evaluated Vault on a variety of use cases and datasets across transactional diligence, litigation, deal term/precedent tracking, IP and other practice areas.

Datasets evaluated include:

  • Patents

  • Emails

  • Transactional agreements

  • Case summaries

  • Commercial contracts

  • Miscellaneous documents — Government documents, regulatory filings, etc.

Vault performs between 94%-99% accuracy on objective Review tasks with 10-50 questions. (An “objective task” refers to a query that can be verified as true or not.)

For further assistance, please contact [email protected]

Did this answer your question?