PLAYBOOK ATLASPlaybook Atlas

Legal

AI in legal: explore 26 applications.

Turn legal documents and authorities into source-linked work for professional review.

Explore legal research, clause extraction, contract review, drafting and obligation tracking for legal teams.

Book a 30-minute call See the 26 applications

Where the 26 applications sit

Explore the domains
  1. 11Document and Contract Management
  2. 9Legal Knowledge Management
  3. 8Legal Operations
  4. 4Justice System Integration
  5. 4Risk Management

01Why AI now

Why legal is moving on AI, in three figures.

Each figure links to its source.

  1. Average lawyer rate: $341/hour in 2024

    Attorney at Work's summary of the Clio Legal Billable Hour Index reports an average lawyer hourly rate of $341 in 2024.

    Source: Attorney at Work

  2. 83% of legal departments expect demand to rise

    A survey of 186 organizations found that 83% of legal departments expect demand for their services to increase.

    Source: Corporate Legal Operations Consortium (CLOC)

  3. 63% cite workload and bandwidth as top challenge

    Nearly two-thirds of surveyed legal departments identified workload and limited resource bandwidth as their leading challenge.

    Source: Corporate Legal Operations Consortium (CLOC)

How to evaluate a first project

Define the jurisdiction, document set and legal task. Check every material quotation, citation and proposed change against its source, including conflicting or missing authority. Evaluate the resulting issue list, redline or research packet with a qualified reviewer and preserve responsibility for advice, filing and client decisions.

02Capability map

Where legal puts AI to work, domain by domain.

Pick a domain to see its applications. Each one opens a full report.

Inside Document and Contract Management

Applications in Document and Contract Management

What the use cases ask AI to do

Share of the legal use cases, by the kind of work the AI does.

  1. Reasoning

    Analyzes, predicts and decides: scoring, forecasting, classifying.

    65%

  2. Generation

    Creates: text, images, code and other content.

    34%

  3. Agentic

    Acts: plans, uses tools and completes multi-step tasks.

    1%

Under 1% each: perception and optimization.

03Workflow ideas

Ways AI could change the work, in legal.

Atlas groups these applications by the changes they propose to a workflow. These preliminary classifications help you explore ideas; each application still needs a review of its sources and operating requirements.

Workflow categories in this catalog

Share of the 22 applications assigned a category.

How to evaluate an application

  1. Start with a bounded task

    Identify the inputs, the person responsible, and the decision or output the workflow must produce.

  2. Check the support for each method

    Look for source-backed details about the specific implementation, including its limits and human review.

  3. Measure the pilot

    Record the current baseline, agree on acceptance criteria, and test on representative cases before expanding.

Explore applications

04What gets built

The approaches legal uses most, and when to skip them.

Knowing when not to use one matters as much as knowing when to.

  1. 01 · 13 applications

    Generative AI

    Models that learn data distributions to generate new text, images, code, and media.

    Use it when

    • When you need to generate natural language, code, or media that would be expensive or slow for humans to produce manually.
    • When tasks involve ambiguity, open-ended questions, or creative exploration rather than strict right-or-wrong answers.
    • When you can ground the model on reliable internal or external data sources to improve factuality.

    Skip it when

    • When the task requires strict determinism, formal guarantees, or regulatory-grade traceability (e.g., certain financial calculations, safety-critical control systems) without a robust verification layer.
    • When you lack access to high-quality, authoritative data or subject-matter expertise to validate outputs in a high-risk domain.
    • When a simple rules engine, search, or template-based system can solve the problem more reliably and cheaply.
    Generative AI, in depth

  2. 02 · 2 applications

    Document Review Intelligence

    LLM/NLP document review and playbook-grounded analysis systems.

    Document Review Intelligence, in depth

  3. 03 · 2 applications

    RAG-Standard

    LLM + retrieval layer that injects relevant documents into the prompt at query time.

    Use it when

    • You need an LLM to answer questions based on proprietary or private documents that are not part of its pretraining data.
    • Your knowledge changes frequently (e.g., policies, product docs, pricing) and you want updates to be reflected without re-training the model.
    • You have a large corpus of unstructured or semi-structured text (wikis, PDFs, tickets, emails, manuals) that users struggle to search effectively.

    Skip it when

    • Your task is primarily structured data querying or analytics (e.g., reporting over a relational database) where SQL or BI tools are more accurate and efficient.
    • You have very small, static knowledge (e.g., a short FAQ) that can fit directly into a prompt or be encoded as rules without a retrieval layer.
    • You require strict, deterministic behavior with no tolerance for probabilistic errors (e.g., certain financial calculations, safety-critical controls).
    RAG-Standard, in depth

05The applications

26 legal applications, each with a full report.

The widest first, by the number of use cases each covers. Every report shows what changed, how it works, who has done it and what can go wrong.

  1. Legal Research and Summarization HubAI Legal Research & Summarization ingests case law, contracts, and filings to automatically extract key facts, holdings, precedents, and issues, then generates concise, citation-rich summaries. It accelerates legal research, enhances drafting quality, and reduces time spent reviewing lengthy documents, enabling law firms and legal departments to handle more matters with greater consistency and lower cost.Expert → AI23 use cases
  2. Legal Workflow Automation and Optimization HubThis AI solution applies AI to streamline legal workflows end-to-end, from research, drafting, and contract review to due diligence and operations management. By automating routine legal tasks and surfacing insights faster, it increases lawyer productivity, shortens turnaround times, and enables firms and legal departments to handle more matters with the same resources.Human Creative → Augmented12 use cases
  3. Legal AI Fairness GovernanceThis AI solution uses AI to evaluate, benchmark, and monitor fairness, bias, and legal risk across AI systems used in courts, law firms, and justice institutions. It standardizes assessments of algorithmic liability, professional legal reasoning, and access-to-justice impacts, providing evidence-based guidance for procurement, deployment, and oversight. By systematizing fairness and risk evaluation, it helps legal organizations comply with regulations, enhance trust, and reduce exposure to AI-related litigation and reputational damage.Opaque → Trans8 use cases
  4. Criminal Justice Decision Risk AnalyzerThis AI solution uses AI to model crime risk, assess defendants, and analyze policing patterns while embedding fairness, due process, and governance constraints. It helps courts, law firms, and justice agencies improve decision quality and consistency, reduce bias and rights violations, and manage legal and reputational risk when deploying predictive and generative tools in criminal justice workflows.Expert → AI7 use cases
  5. Legal Document Generation HubAI Legal Document Generation tools automatically draft state-specific contracts, pleadings, and other legal documents from templates, clauses, and client inputs. They speed up first-draft creation, reduce manual editing, and help standardize language and compliance across matters, freeing lawyers to focus on higher‑value analysis and strategy.Human Creative → Augmented6 use cases
  6. eDiscovery Document Review HubeDiscovery document review is the process of identifying, organizing, and assessing electronically stored information—such as emails, chats, documents, and files—for litigation, investigations, and regulatory matters. At scale, this traditionally requires large teams of lawyers and reviewers to manually sift through millions of items to determine relevance, privilege, and risk, which is slow, extremely costly, and prone to human error. Modern systems apply advanced automation to prioritize, classify, and filter documents so that humans review a much smaller, higher‑value subset. These tools rank likely‑relevant materials, flag potentially privileged or risky content, and expose patterns or connections across vast datasets, while preserving audit trails and defensibility for courts and regulators. This dramatically reduces review time and spend, helps avoid missed evidence, and enables litigation and investigations teams to respond faster and more confidently under tight deadlines.Expert → AI6 use cases
All 26 applications, A to Z

Work with us · Legal operations

The catalog shows what is possible. A sprint decides what you should fund.

Reading every report still leaves the hardest question open: which move is worth funding first, here, given your constraints. That is the sprint: two weeks, fixed scope, and a candid answer either way.

Book a 30-minute callHow the sprint works

Two weeks Fixed scope A candid fit-or-no-fit answer

  1. 01

    Three ranked opportunities

    A decision-ready shortlist scored against value, feasibility, evidence, risk, and time to proof.

  2. 02

    One pilot-ready workflow

    A bounded operating design with actors, handoffs, data needs, controls, and success measures.

  3. 03

    A defensible 90-day plan

    Build-versus-buy guidance, ROI assumptions, risk treatment, sequencing, and executive decisions.

06Rules & standards

Rules and standards to check, with their scope and sources.

Selected US and EU references for these workflows. Applicability depends on jurisdiction, organization, data and intended use. The planning notes are Atlas editorial guidance; they are not official implementation-time estimates or an exhaustive list of obligations.

  1. ABA Formal Opinion 512 · generative AI

    Professional guidance

    United States · professional guidance, subject to local rules

    The opinion addresses competence, confidentiality, communication, supervision and fees when lawyers use generative AI. Binding duties come from the relevant jurisdiction’s professional rules and court requirements.

    ABA: Formal Opinion 512

    Source checked

    Project planning note

    Define source verification, confidentiality, supervision and client-communication steps for the specific legal workflow.

  2. GDPR · personal data and automated decisions

    Law or regulation

    European Union / EEA · processing within GDPR scope

    Personal-data processing needs an applicable lawful basis and safeguards. Article 9 adds conditions for special-category data; Article 22 addresses certain solely automated decisions with legal or similarly significant effects. Consent is not the only lawful basis.

    EUR-Lex: GDPR, Articles 3, 6, 9, 22 and 35

    Source checked

    Project planning note

    Review the lawful basis, access and transfer arrangements for client and third-party personal data.

Your next step

Find your first move in legal.

Bring us the decision you are weighing. In 30 minutes we look at it against these 26 applications and your constraints, and tell you plainly whether a two-week sprint fits.

Book a 30-minute call

Rather work it through yourself? Plan it in the workspace