Irys Learn Center
Guides, documentation, FAQs, and a comprehensive glossary — everything legal professionals need to understand and use AI effectively.
Platform Documentation
Complete platform documentation — setup guides, feature walkthroughs, and reference material.
Open DocumentationFeatured Guides
The Attorney's Guide to Billing AI-Assisted Work
How to bill under hourly, fixed fee, AFA, and value-based models. Includes invoice templates, client disclosure language, and ethics guidance from practicing attorneys.
Read the guideHow to Evaluate Legal AI Platforms: A Buyer's Checklist
Security, citation accuracy, context windows, pricing models, red flags, and the questions every firm should ask before signing.
Read the guideResearch
AI-Powered Legal Research: The Complete Guide (2026)
How AI is changing legal research, from semantic search to citation verification and best practices for modern workflows.
Read guideResearchHow to Verify AI-Generated Legal Citations
Understand the hallucination problem and learn practical methods for verifying every citation AI produces.
Read guideResearchAI Legal Research vs Westlaw vs Lexis: What Changed in 2026
How the legal research landscape shifted and why firms are adopting hybrid approaches.
Read guideDrafting
AI Contract Drafting: A Guide for Transactional Lawyers
How AI assists in contract creation, tracked changes, template-driven drafting, and quality control workflows.
Read guideDraftingHow to Use AI to Draft Motions and Briefs
AI-assisted brief writing that maintains your voice, integrates citations, and exports cleanly to Word.
Read guideDraftingAI-Assisted Redlining: How It Works and When to Use It
Tracked changes workflows, accept/reject mechanics, and best practices for AI-powered redlining.
Read guideDocument Analysis
Multi-Document AI Analysis for Litigation
Analyze large document sets with structured queries, confidence scores, and export-ready reporting.
Read guideDocument AnalysisAI for Due Diligence: A Practical Guide
How AI accelerates due diligence through document extraction, risk identification, and automated reporting.
Read guideBuying Guides
How to Evaluate Legal AI Platforms: A Buyer’s Checklist
What to look for in security, citations, context windows, and pricing. Red flags and questions for vendors.
Read guideEvaluation & PricingLegal AI Pricing Models Explained: Per-Seat vs Usage vs Enterprise
Understand how platforms price, hidden costs to watch for, and why transparent pricing matters.
Read guideGlossary
Clear definitions of the terms lawyers encounter when evaluating and using AI in legal practice.
AI Concepts
Legal Operating System
A legal operating system is a unified AI platform that consolidates research, drafting, document analysis, and knowledge management into a single interface. Rather than requiring lawyers to switch between multiple point solutions, it provides one environment where every legal workflow connects to the same underlying intelligence layer.
AI ConceptsAI Hallucination in Legal
An AI hallucination occurs when a language model generates text that appears authoritative but is factually incorrect, such as fabricating case citations, inventing statutes, or misrepresenting holdings. In legal practice, hallucinations carry professional responsibility implications because lawyers have a duty to verify the accuracy of every authority they cite.
AI ConceptsRetrieval-Augmented Generation (RAG)
Retrieval-augmented generation is an AI architecture that supplements a language model's response by first retrieving relevant documents from an external knowledge base and then using those documents as context for generating an answer. In legal applications, RAG grounds AI output in actual case law, statutes, and firm documents rather than relying solely on the model's training data.
AI ConceptsLarge Language Model (LLM)
A large language model is a neural network trained on vast text corpora that can understand and generate human language. LLMs power the natural language capabilities of legal AI tools, enabling them to read contracts, draft documents, answer research questions, and summarize complex legal materials in plain language.
AI ConceptsPrompt Engineering for Lawyers
Prompt engineering is the practice of structuring instructions to an AI system to elicit accurate, useful, and appropriately scoped responses. For lawyers, effective prompting includes specifying jurisdiction, defining the role the AI should assume, providing relevant context, and clearly articulating the desired output format.
AI ConceptsAI Context Window
The context window is the maximum amount of text an AI model can process in a single interaction, measured in tokens. A larger context window allows the model to consider more documents, longer contracts, or more extensive case histories simultaneously, which directly impacts the quality and completeness of its legal analysis.
AI ConceptsToken Limit
A token limit is the maximum number of tokens (word fragments or characters) that an AI model can process in a single request, encompassing both the input and the output. In legal applications, token limits determine how much source material the AI can analyze at once and how long its generated responses can be.
AI ConceptsAI Agent in Legal
An AI agent is an autonomous system that can plan and execute multi-step tasks on behalf of a user, making decisions about which tools to use and in what order. In legal applications, AI agents can conduct research across multiple databases, draft documents incorporating their findings, and verify citations, all from a single instruction.
AI ConceptsNatural Language Processing in Legal
Natural language processing (NLP) is the branch of AI that enables computers to understand, interpret, and generate human language. In legal applications, NLP powers everything from contract analysis and clause extraction to case law search and automated document summarization.
AI ConceptsSemantic Search in Legal
Semantic search is a search methodology that understands the meaning and intent behind a query rather than matching exact keywords. In legal research, semantic search allows lawyers to describe a legal issue in natural language and find relevant cases, statutes, and secondary sources even when they use different terminology than the query.
AI ConceptsFine-Tuning Legal AI
Fine-tuning is the process of further training a pre-trained language model on a specialized dataset to improve its performance in a specific domain. In legal AI, fine-tuning on legal corpora teaches the model legal reasoning patterns, citation formats, jurisdictional distinctions, and the precision that legal analysis demands.
AI ConceptsAI Wrapper
An AI wrapper is a product that adds a user interface and minimal customization on top of a third-party language model API without building substantial proprietary technology. In legal tech, AI wrappers often provide a chat interface to GPT or Claude with legal-themed prompts but lack the retrieval, verification, and security infrastructure that professional legal work requires.
Legal Tech
Legal AI Platform
A legal AI platform is a comprehensive software system purpose-built for law firms and legal departments that integrates AI capabilities across multiple legal workflows. Unlike general-purpose AI tools or single-function products, a legal AI platform provides research, drafting, document analysis, and knowledge management in a unified environment with enterprise-grade security.
Legal TechAI Drafting Assistant
An AI drafting assistant is a tool that helps lawyers create, edit, and refine legal documents using artificial intelligence. These systems can generate first drafts from instructions, suggest clause language, maintain consistent terminology, and adapt documents to specific jurisdictional requirements while preserving tracked changes for attorney review.
Legal TechAI Legal Research
AI legal research uses artificial intelligence to find, analyze, and synthesize legal authorities including case law, statutes, regulations, and secondary sources. Unlike traditional database searches that return ranked lists of documents, AI legal research can answer natural language questions, provide analytical summaries, and identify relevant authorities that keyword searches would miss.
Legal TechAI Redlining
AI redlining is the automated process of reviewing and marking up legal documents with suggested edits, using artificial intelligence to identify issues, propose alternative language, and flag provisions that deviate from standard terms or a firm's preferred positions. The output is typically presented as tracked changes that lawyers can accept, reject, or modify.
Legal TechAI Matter Management
AI matter management applies artificial intelligence to the organization, tracking, and analysis of legal matters. It uses AI to automate task management, surface relevant precedents from past matters, predict timelines and resource needs, and maintain institutional knowledge that would otherwise exist only in individual lawyers' memories.
Legal TechLegal Knowledge Management
Legal knowledge management is the systematic process of capturing, organizing, and making accessible the collective expertise and work product of a legal organization. AI-enhanced knowledge management goes beyond document storage to understand the substance of legal work, automatically categorize materials, and surface relevant precedents when lawyers need them.
Legal TechAI Document Comparison
AI document comparison uses artificial intelligence to identify and analyze differences between two or more versions of a legal document. Beyond simple text-diff tools, AI-powered comparison understands the legal significance of changes, categorizes modifications by type and risk level, and can summarize the substantive impact of revisions.
Legal TechAI Cite Check
AI cite check is an automated system that verifies the accuracy and validity of legal citations in a document. It confirms that cited cases exist, checks that quoted language matches the source, verifies that holdings are accurately represented, and flags authorities that have been overruled, reversed, or otherwise undermined.
Legal TechLegal Template Builder
A legal template builder is an AI-powered tool that creates reusable document templates with intelligent fields, conditional logic, and automated clause selection. Unlike static templates, AI-enhanced template builders can adapt output based on deal parameters, jurisdiction, and party-specific requirements while maintaining consistency with firm standards.
Legal TechAI Word Add-In
An AI Word add-in is a software extension that integrates AI capabilities directly into Microsoft Word, allowing lawyers to access research, drafting assistance, redlining, and cite checking without leaving their primary document editing environment. This integration eliminates the context-switching between AI tools and the word processor where legal work product is ultimately finalized.
Security
Zero Data Retention
Zero data retention is a security policy in which an AI platform does not store user queries, uploaded documents, or generated outputs on its servers after processing is complete. For law firms, this policy ensures that confidential client information is not retained in third-party systems where it could be exposed through data breaches or used to train AI models.
SecuritySOC 2 for Legal AI
SOC 2 (System and Organization Controls 2) is an auditing framework developed by the AICPA that evaluates a service provider's controls for security, availability, processing integrity, confidentiality, and privacy. For legal AI platforms, SOC 2 compliance demonstrates that the vendor has implemented and maintained the security controls necessary to protect sensitive legal data.
SecurityAttorney-Client Privilege and AI
Attorney-client privilege protects confidential communications between a lawyer and client made for the purpose of seeking or providing legal advice. When lawyers use AI tools, privilege concerns arise because sharing privileged information with a third-party technology provider could be construed as a waiver of the privilege if adequate confidentiality protections are not in place.
SecurityTenant Isolation
Tenant isolation is a security architecture in which each customer's data is logically or physically separated from every other customer's data within a multi-tenant platform. In legal AI, tenant isolation ensures that one firm's confidential information, work product, and AI interactions are completely inaccessible to other firms using the same platform.
SecurityEnd-to-End Encryption in Legal
End-to-end encryption is a security method in which data is encrypted on the sender's device and can only be decrypted by the intended recipient, remaining encrypted throughout transmission and storage. In legal AI, end-to-end encryption protects confidential client data, privileged communications, and work product at every stage of processing.
SecurityHIPAA Compliance for Legal AI
HIPAA (Health Insurance Portability and Accountability Act) compliance for legal AI refers to the set of safeguards and practices that ensure protected health information (PHI) is handled appropriately when lawyers use AI tools for healthcare-related legal matters. Firms handling medical malpractice, health care regulatory, or employee benefits matters must ensure their AI tools meet HIPAA requirements.
SecurityGDPR for Legal AI
GDPR (General Data Protection Regulation) compliance for legal AI refers to the requirements that AI platforms must meet when processing personal data of individuals in the European Economic Area. For law firms with international clients or matters involving EU data subjects, GDPR imposes strict rules on how personal data is collected, processed, stored, and transferred through AI systems.
SecurityData Residency
Data residency refers to the physical or geographic location where data is stored and processed. For law firms, data residency requirements may arise from client contracts, regulatory obligations, or firm policies that dictate that certain data must remain within specific geographic boundaries, such as within the United States or European Union.
Workflow
Matter Context
Matter context is the accumulated body of information relevant to a specific legal matter, including uploaded documents, prior research, communications, and case facts, that an AI system maintains and references across all interactions. It allows the AI to provide increasingly relevant assistance as the matter develops, without requiring lawyers to re-explain background each time.
WorkflowAI Tracked Changes
AI tracked changes is a feature that presents AI-generated edits to legal documents in the standard tracked changes format used in Microsoft Word and other word processors. Rather than generating a new version of a document, the AI produces its suggestions as insertions, deletions, and formatting changes that lawyers can individually accept, reject, or modify.
WorkflowDeep Research in Legal AI
Deep research is an AI capability that conducts comprehensive, multi-step legal research autonomously, searching across multiple sources, analyzing results, following citation trails, and synthesizing findings into a structured memorandum. Unlike single-query research, deep research mimics the iterative process a skilled research attorney would follow.
WorkflowMulti-Document Analysis
Multi-document analysis is the AI capability to simultaneously process, compare, and extract insights from multiple legal documents. This allows lawyers to ask questions across an entire set of contracts, depositions, or discovery documents, identifying patterns, inconsistencies, and key provisions without reading each document individually.
WorkflowAmplify Prompt
Amplify Prompt is a feature that automatically enriches a lawyer's query with relevant context before sending it to the AI model. It adds jurisdictional parameters, matter context, relevant document references, and structural framing to a simple question, transforming a brief query into a comprehensive, well-structured prompt that produces higher-quality results.
WorkflowLegal Playbook
A legal playbook is a codified set of a firm's or organization's preferred negotiating positions, standard terms, acceptable fallback positions, and red-line issues for specific types of transactions or matters. In AI-enabled workflows, playbooks are machine-readable, allowing the AI to automatically compare incoming documents against the organization's established standards.
WorkflowCase Law Search with AI
AI-powered case law search uses semantic understanding and natural language processing to find relevant judicial opinions based on the meaning of a legal query rather than just keyword matching. It can identify cases by legal concept, factual similarity, or analytical approach, even when the opinions use different terminology than the search query.
WorkflowDual Search
Dual search is a legal research methodology that combines AI-powered semantic search with traditional Boolean keyword search in a single interface. This approach gives lawyers the conceptual understanding of semantic search together with the precision and reproducibility of Boolean search, allowing them to leverage the strengths of both methods.
WorkflowKnowledge Graph in Legal
A legal knowledge graph is a structured representation of relationships between legal concepts, authorities, entities, and documents. It maps how cases cite each other, how statutes relate to regulations, how legal concepts connect across practice areas, and how a firm's work product relates to specific legal issues, enabling the AI to understand law as an interconnected system rather than isolated documents.
WorkflowLegal Workflow Automation
Legal workflow automation uses AI and technology to streamline repetitive legal processes, from document intake and initial review through research, drafting, and final production. It connects discrete tasks into end-to-end workflows that reduce manual handoffs, eliminate redundant work, and ensure consistent quality across routine matters.
Research
Boolean Search in Legal Research
Boolean search is a legal research technique that uses logical operators (AND, OR, NOT) and proximity connectors to construct precise queries against legal databases. While AI-powered semantic search is transforming legal research, Boolean search remains essential for tasks requiring exact phrase matching, comprehensive coverage verification, and reproducible search results.
ResearchCitation Verification
Citation verification is the process of independently confirming that legal citations in a document are accurate: that the cited authorities exist, that quoted language matches the source, that holdings are correctly represented, and that the authorities remain good law. In AI-assisted legal work, automated citation verification is essential to catch hallucinated or inaccurate references before they reach a court or client.
ResearchCourtListener
CourtListener is a free, open-source legal research platform operated by Free Law Project that provides access to millions of court opinions, oral arguments, and judicial records from federal and state courts. It serves as an important public legal data source that some AI legal research tools use as part of their retrieval infrastructure.
ResearchGood Law Check
A good law check is the process of verifying whether a cited legal authority remains valid and has not been overruled, reversed, superseded by statute, or otherwise undermined by subsequent legal developments. AI-powered good law checks automate the citator function traditionally performed by Shepard's Citations (Lexis) or KeyCite (Westlaw).
ResearchMemo-Quality Research
Memo-quality research refers to AI-generated legal research output that meets the standard expected of a well-drafted legal memorandum: thorough analysis of relevant authorities, proper citation format, balanced treatment of favorable and unfavorable authority, clear IRAC or similar analytical structure, and transparent identification of open questions or weaknesses in the analysis.
ResearchAI Legal Citations
AI legal citations are case references, statutory citations, and other legal authority references generated by AI systems in the course of legal research or drafting. The accuracy and verifiability of AI-generated citations is a central concern in legal AI because language models can produce citations that appear well-formed but reference non-existent authorities.
ResearchWestlaw Alternative
A Westlaw alternative is a legal research platform that provides comparable or complementary capabilities to Thomson Reuters' Westlaw service, often leveraging AI to offer different approaches to case law search, statutory research, and legal analysis. These alternatives may offer advantages in AI-powered features, pricing transparency, or integrated workflows while potentially trading off on the depth of editorial enhancements like headnotes and key numbers.
ResearchLegal Research AI Tools
Legal research AI tools are software applications that apply artificial intelligence to the process of finding, analyzing, and synthesizing legal authority. The category ranges from AI-enhanced search features within traditional databases to standalone platforms that reimagine the research workflow around natural language interaction, automated citation verification, and AI-generated analysis.
ResearchJurisdictional Search
Jurisdictional search is the capability to constrain legal research results to authorities from specific jurisdictions, including particular states, federal circuits, or court levels. Effective jurisdictional search ensures that research results prioritize binding authority from the relevant jurisdiction while appropriately weighting persuasive authority from related jurisdictions.
ResearchSecondary Source Research
Secondary source research involves searching treatises, law review articles, practice guides, restatements, and other scholarly or practice-oriented legal publications that analyze, explain, and synthesize primary law. AI-enhanced secondary source research can identify the most authoritative secondary sources on a topic, extract relevant analysis, and connect secondary source insights to primary authority.
Ready to put this knowledge into practice?
Irys One brings research, drafting, and document intelligence together in one platform. Try it free for 7 days.