aiR for Privilege

aiR for Privilege is an AI-powered solution that uses generative AI, large language models, natural language processing, machine learning, and social network graphs to analyze documents and predict whether they are privileged or not and provide a draft privilege log description. This streamlines privilege review, improves the accuracy of your final privilege calls, and reduces overhead when creating a privilege log.

aiR for Privilege retains an understanding of privilege specific to an organization to drive greater consistency in privilege calls across matters and speed up the pace of privilege review.

Note: aiR for Privilege locates attorney-client privileged communications and documents subject to the attorney work-product doctrine, as understood under US standards and laws. It is up to the user of aiR for Privilege to decide whether this criteria and the results meet applicable requirements.

Note: Azure OpenAI does not retain any data from the documents being analyzed. Data you submit for processing by Azure OpenAI is not retained beyond your organization’s instance, nor is it used to train any other generative AI models from Relativity, Microsoft, or any other third party. For more information, see the white paper A Focus on Security and Privacy in Relativity’s Approach to Generative AI.

Note: For European Economic Area (EEA) customers, aiR for Privilege data may be processed elsewhere in the EU, but it will always be processed in compliance with applicable laws. For more information, please contact your account manager.

Conceptual workflow

The table below illustrates the high-level workflow and the role that should be performing each step for aiR for Privilege:

Role Step Workflow Step
Project Manager 1 Create a saved search of documents that you want to analyze for privilege
2 Create an aiR for Privilege project
3 Upload any lists of Known Attorneys and Known Law Firms to jump-start the AI’s understanding
4 Run each aiR for Privilege pipeline step
Annotator 5 Confirm AI Predictions through Annotations during each pipeline step
Case SME 6 Finalize which Law Firms and Attorneys are Privilege Conferring, Privilege Neutral, or Privilege Breaking
Project Manager 7 Generate Privilege Predictions and Draft Privilege Log Descriptions
Case SME 8 Finalize privilege decisions and log descriptions through targeted quality check (QC)
9 Produce with confidence

For more information about the different aiR for Privilege roles see Roles and security permissions.

Requirements

Following are requirements for using aiR for Privilege:

  • You must complete aiR for Privilege contracting to use it in your RelativityOne instances.
    See Billing for more details. Contact your Relativity Sales Representative for contracting.
  • Relativity must install the aiR for Privilege application to your instance.
  • You must install the aiR for Privilege application to your workspace.
    See Installation and configuration for more details.
  • You should install the Import/Export application to your workspace as it can be helpful in accelerating the addition of Known Items and performing the Confirm Privilege Status step.

Considerations

Following are limitations to consider when using aiR for Privilege:

  • aiR for Privilege is available in RelativityOne instances hosted in the following regions:
    • United States
    • United Kingdom
    • Canada
    • Australia
    • France
    • Germany
    • Ireland
    • Netherlands
    • Switzerland
  • There are limitations on both what types of documents and the number of documents that can be included in an aiR for Privilege project as specified in Saved search requirements.
  • Only a single aiR for Privilege project within a workspace can be In Progress at any given time.
  • We tested the performance of aiR for Privilege on primarily English language documents. Use of aiR for Privilege with non-English language documents may result in unexpected or unverifiable results. Consider using Language Identification to better understand the language distribution across your data set.
    Note: aiR for Privilege only analyzes emails that have email headers in the following languages: English, Chinese, Dutch, French, German, Japanese, Korean, Portuguese, Spanish.
  • aiR for Privilege locates attorney-client privileged communications and documents subject to the attorney work-product doctrine, as understood under US standards and laws.
  • aiR for Privilege supports analyzing emails, attachments, and standalone documents. It does not currently support the analysis of RSMF documents.
    Note: RSMF documents that are included in a project will by default be analyzed as standalone documents. If the extracted text for an RSMF document contains valid email headers (from, to, date, subject, etc.) and has a Record Type of email it will be analyzed as if it is an email with it's senders and recipients considered.
  • aiR for Privilege supports email header formats as described in Supported email header formats.
  • In progress aiR for Privilege projects will be abandoned when the workspace is deleted, regardless of Recycling Bin, archived (ARM), or put in Cold Storage.
  • aiR for Privilege cannot be used or installed within Repository Workspace. You must uninstall Repository Workspace before installing aiR for Privilege.
  • aiR for Privilege only works in Review workspaces.
  • aiR for Privilege supports CMK instances.
  • aiR for Privilege is not offered in RelativityGov or Relativity Server.

Billing

aiR for Privilege is a usage-based product, meaning you pay-per-use. Charges are per Document Unit. A Document Unit is equal to one Relativity document.

After clicking the Run button on the Prepare Project pipeline step, Relativity estimates the number of Document Units you’ll use for this project. You can then decide to continue or cancel the step.

After completing the Prepare Project pipeline step Relativity will charge you for the number of Document Units. The price per Document Unit may vary. Your RelativityOne contract defines the price.

Note: You may have included aiR for Privilege Document Units to trial the product without any cost. After you use your Included aiR for Privilege Document Units, Relativity will charge per Document Unit.

Brain

The Brain stores past Annotator Decisions made on Disclaimers, Spammers, Domains, Equivalent Domains, and Entities and applies them to new projects. This accelerates annotation time and ensures consistency across the final document predictions that the AI makes.

The Brain contains three levels:

  • The Universal Brain contains items that are public knowledge that will be applied to every project.
  • The Client Brain contains client-specific decision that can be applied to different projects within the same client object.
  • The Matter Brain contains workspace-specific items that can be applied to different projects for the same matter.

Universal Brain

The Universal Brain includes data that Relativity has gathered from publicly available source (e.g. the domain lawfirm.com is a Law Firm domain as found on an AMLAW 100 list). No user data is stored in the Universal Brain.

Client Brain

Upon the completion of a project, aiR for Privilege will store Annotator Decisions made on Disclaimers, Spammers, Domains, Equivalent Domains, and Entities from that project in a Client Brain. The Client Brain is associated with the Client object linked to the workspace. Any future project, in a workspace associated with that Client object, will have the opportunity to use annotator decisions stored in that Client Brain to be automatically applied when those same items (Disclaimers, Spammers, etc.) are identified, resulting in fewer required annotations and greater consistency in final document predictions between matters.

Note: The Client Brain does not store Final Privilege Status decisions made on Domains and Entities (“Privilege Conferring”, “Privilege Neutral”, “Privilege Breaking".)

When an Annotator Decision stored in the Client Brain is applied to an item in a new workspace, that item will receive a Source field value of Client Brain. This will give you transparency that the Client Brain was used for that item, while still allowing you to have the control to overturn that prior Annotator Decision locally within this workspace.

Example scenario

In Workspace 1 which is connected to Client Object 1 a user annotates the John Doe entity as Legal Role. When John Doe is found in Workspace 2 which is also connected to Client Object 1, John Doe will be pre-populated with the Legal Role Annotator Decision and given a Source value of Client Brain.

See General settings in a workspace for more details on enabling the Client Brain and selecting which Client Brain you would like to apply to a project.

Matter Brain

The Matter Brain will store not only Annotator Decisions made on Disclaimers, Spammers, Domains, Equivalent Domains, and Entities, but also Final Privilege Status decisions (“Privilege Conferring”, “Privilege Neutral”, “Privilege Breaking”) on Domains and Entities for a project and apply those decisions to new projects in the same workspace. When a new project locates an item (Disclaimer, Spammer, etc.) that was already identified in a prior project in that same workspace it will not create a new item, but rather link the new project to that existing item (on the Privilege Project field) and take that item’s Annotator Decision and Final Privilege Status as truth for analysis. This eliminates repetitive annotation and drives consistency across final document decisions within the matter.

Example scenario

In Project 1 a user annotates the John Doe entity as Legal Role and Privilege Conferring. When John Doe is found in Project 2 in the same workspace that same John Doe object will be linked to Project 2 on the Privilege Project field and the existing Legal Role and Privilege Conferring decisions will be used for making final Document predictions.

The Matter Brain is always enabled and cannot be disabled.