LawyerAILawyerAIIndependent Reviews
  • Search
  • Categories
  • Tag
  • Collection
  • Blog
  • Compare
  • Glossary
  • Solutions
  • Pricing
  • Submit
LawyerAILawyerAI
  1. Home
  2. ›
  3. Glossary
  4. ›
  5. Discovery AI

Discovery AI

Discovery AI is software that applies machine learning and natural language processing to litigation discovery, automating document review, relevance classification, and issue identification across large document collections.

Last reviewed: 2026/05/19

Definition

Why It Matters for Lawyers

How AI Tools Handle It

Frequently Asked Questions

Q1: Have courts approved AI-assisted document review?
Yes. Multiple federal courts have approved predictive coding and technology-assisted review methodologies in discovery protocols, starting with Da Silva Moore v. Publicis Groupe in 2012. Courts generally require transparency about the methodology, validation testing, and the opponent's opportunity to challenge the process. The specific protocol should be disclosed to opposing counsel and approved in the discovery order where possible.
Q2: What is the difference between predictive coding and generative AI in discovery?
Predictive coding uses supervised machine learning trained on attorney-reviewed examples to classify documents by relevance. Generative AI in discovery applies large language models to tasks like summarizing documents, extracting key facts, or answering questions about the document collection. Both can be used in the same matter, but they address different review tasks.
Q3: What happens if relevant documents are missed in AI-assisted review?
Missing relevant documents in discovery can have serious consequences, including adverse inference instructions, sanctions, or dismissal of claims or defenses. Quality control procedures — including random sampling of the AI-excluded population to check for missed relevant documents — are a critical safeguard. A defensible TAR process includes documented quality metrics showing the model's recall rate. --- *Last reviewed: 2026-05-19 by LawyerAI Editorial Team.*

Related Concepts

Capability

E-Discovery

E-discovery (electronic discovery) is the process of identifying, preserving, collecting, reviewing, and producing electronically stored information in response to litigation, investigations, or regulatory demands.

Capability

Privilege Review

Privilege review is the process of examining documents in an e-discovery collection to identify and withhold materials protected by attorney-client privilege, work product doctrine, or other applicable privileges before production to opposing parties.

Legal Practice

Document Production

Document production is the process of delivering to opposing parties in litigation or investigation the set of documents that are responsive to discovery requests, non-privileged, and within the scope of the applicable discovery order or agreement.

Related Tools

  • Everlaw

    Cloud eDiscovery with AI predictive coding and document summarization.

  • Supio

    AI document analysis purpose-built for personal injury case preparation.

  • Filevine

    Case management with AIFields for personal injury and plaintiff practice.

  • Luminance

    Enterprise AI for portfolio-level contract analysis and institutional memory.

Related Comparisons

  • Everlaw vs Filevine: eDiscovery vs Case Management

Related Reading

  • How We Score Legal AI Tools: The 5-Dimension Methodology

Last reviewed: 2026/05/19. Definitions are written by the LawyerAI Editorial team. We do not accept affiliate commissions; Featured placement is clearly labeled and does not influence editorial content.

← All glossary terms
LawyerAILawyerAI

Independent Reviews

The independent directory of AI tools for lawyers — reviewed by methodology, not by ad budget.

X (Twitter)
Tools
  • Search
  • Categories
  • Tag
  • Collection
Resources
  • Blog
  • Compare
  • Glossary
  • Solutions
  • Pricing
  • Submit
  • Suggest a Tool
  • Newsletter
Company
  • About Us
  • Studio
Legal
  • Privacy Policy
  • Terms of Service
  • Cookie Policy
  • Refund Policy
  • Editorial Independence
  • Sitemap
Editorially independent. Methodology open and versioned.
© 2026LawyerAI Editorial

Discovery AI is software that applies machine learning and natural language processing to litigation discovery, automating document review, relevance classification, and issue identification across large document collections.

Commercial litigation frequently involves document collections numbering in the millions. A single custodian's email archive can contain hundreds of thousands of documents, only a fraction of which are relevant to the litigation issues. Manual review of these volumes is prohibitively expensive and introduces inconsistency — different reviewers applying the same standard may classify the same document differently.

AI-assisted review addresses both cost and consistency. Predictive coding and technology-assisted review (TAR) train a model on a set of attorney-reviewed seed documents, then apply that classification to the broader collection. Documents above a relevance threshold are prioritized for human review; those below can be set aside subject to quality control sampling. Courts have accepted TAR in numerous discovery protocols, recognizing it as an accepted methodology when properly implemented.

For a litigator defending a major class action, deploying discovery AI can reduce review costs from millions of dollars to hundreds of thousands. For smaller commercial disputes, even modest AI assistance can make proportionate discovery feasible where exhaustive manual review would not be.

Lawyers supervising AI-assisted review retain professional responsibility for the reasonableness of the process and the adequacy of the production. Quality control protocols, sampling procedures, and attorney oversight are required components of a defensible AI-assisted review workflow.

Discovery AI tools range from broad e-discovery platforms to specialized analysis tools. Relativity AI integrates AI layers into the Relativity platform's existing document review workflows, offering conceptual search, email threading, near-duplicate detection, and predictive coding within a single environment. Everlaw takes a similar full-platform approach with AI features embedded throughout the review workflow.

More specialized tools focus on specific discovery tasks: Supio, for instance, focuses on personal injury and mass tort matters, using AI to extract and organize medical records and other structured data from large document sets.

Most enterprise discovery platforms now include some form of AI-assisted classification. The differentiators are model transparency, the workflow for training and validating the model, integration with existing document review processes, and the quality control tools for auditing results before production.

Lawyers should evaluate any discovery AI tool against the proportionality requirements of the applicable jurisdiction's discovery rules and document the methodology used in case it must be disclosed or defended.