Release notes June 28, 2024: Everlaw AI Assistant Beta updates and more!

Expected AU release:  June 26, 2024 ACT

Expected release for all other: June 28, 2024 PT

Knowledge Base updates: June 28, 2024 PT

With this release, we’ve added Everlaw AI Assistant Beta updates and more — read on for more information about the features coming out this month! If you would like to learn more about the features in this release, join us for a live training session.

User-facing features in this release:

Everlaw AI Assistant Beta Updates


We’re getting ready to launch the general availability of the Everlaw AI Assistant later this year! In preparation, all users will see disabled UI elements corresponding to the Everlaw AI Assistant feature set in their projects. This does not mean that Everlaw AI Assistant has been automatically enabled for the database. 

Learn more about enabling Everlaw AI Assistant on one or more of your databases, or sign up today to try Everlaw AI Assistant for free for a limited time.

Batch generate and search on generated topics

Everlaw AI Assistant-generated topics give users at-a-glance insight into the content and sentiment of a document. Users of Everlaw’s AI Assistant Beta can now:

  • Batch generate document topics from the results table, by selecting Batch > Topics
  • View and export topic information from the results table
  • Search documents based on Everlaw AI Assistant generated topics and associated sentiment

To learn more about Everlaw AI Assistant-generated topics, visit Document summaries, topic analysis, and Q&A.

Writing Assistant prompt templates

Users of Everlaw’s AI Assistant Beta can now compose tasks using custom and pre-defined Everlaw templates when configuring their Writing Assistant prompts in Depositions and Drafts. 

Everlaw’s pre-defined templates are a great way to better understand the various ways task types can be configured. They can be used as-is or as the base for creating custom templates. 

There are three pre-defined Everlaw templates: 

  • Factual Background: A memo template that analyzes the factual events and context of the selected evidence
  • Misconduct Analysis: An outline template that analyzes any misconduct committed by the parties found in the selected evidence  
  • Theme List: A list template that indexes and describes distinct themes present in the selected evidence

Project Admins can also pin any custom or Everlaw template, which will make that template visible and usable in the Pinned templates section by all users in the project who are able to use the Writing Assistant. 

To learn more about Writing assistant prompt templates, visit Storybuilder and Writing Assistant (Everlaw AI Assistant Beta).

New ways to unitize documents

Bookmarks and additional selection options in the review window

Three new ways to unitize documents let you quickly break apart large documents at predetermined points. 

You can now unitize documents using the following Split by methods: 

  • [New] Bookmarks: Allows you to add breakpoints based on existing bookmarks. Everlaw automatically detects bookmarks and lists the pages on which they appear in the unitization panel.
  • Custom selection: Allows you to scroll through the document and select the page at which you want to split the document. Each selected page will add a breakpoint to the list
  • [New] Manual input: Allows users to type in individual page numbers, separated by commas
  • [New] Number of pages: Allows you to split the document every N pages

Screenshot 2024-06-24 162956.png  

Batch unitization in the results table

You can now batch unitize documents from the results table by selecting Batch > Unitize

If some documents fail the unitization process — because they have already been unitized, because the document is not long enough to unitize, or for any other reason — all other documents in the batch will still be unitized. You will see a task card on the homepage displaying the results of the unitization. To see which documents were not unitized and why, click See details.

To learn more about Unitization, visit Unitization Tool.

Allow word order specification in proximity searches

You can now specify word order in proximity content searches by using a double tilde (~~).

For example, “Sacramento California”~~3 searches for instances where “Sacramento” appears before “California” and has no more than 3 words between them in a document. 

Prior to this release, you could only use a single tilde  (~), followed by a word distance, to perform a proximity search between two words. This behavior is still available. 

In addition, you will be prompted to convert dtSearch patterns such as Sacramento pre/3 California to the proximity search “Sacramento California”~~3.

To learn more about proximity searches, visit Advanced Content Searches - Proximity searches.

Improve single folder packaging for productions

Prior to this release, if a user chose to produce both images and natives in the same produced folder, both the image file and a native file could be given the same file name.  

Now, if a native has an extension that might conflict with image or text files, Everlaw will include ".native" in the filename.

Example: PREFIX.BOX.FOLDER.PAGE.native.[txt/pdf]

Visual improvements

  • New buttons are now used for creating persistent hits for search terms and copying to clipboard.
    • The persistent hits button was updated to differentiate it from the general text highlighting.
    • The copy to clipboard button was updated to differentiate it from duplicating an object.
  Before After
Persistent hits
Copy to clipboard
  • During login to Everlaw when the page is still loading, the Login button will show a disabled loading state.

    For users that sign in using a password, the cursor will now auto-focus in the password field after they enter their email and click Next.
  • The Projects table on the Organization Admin page now displays each project’s ID under Project ID.


Do you have feedback about:


Have more questions? Submit a request


Article is closed for comments.