# AI Agents for Lawyers > Independent, practitioner-written guides to using AI and AI agents in legal practice: tools, workflows, regulation, ethics and hands-on playbooks for lawyers. Author: Dr. Niklas Schmidt, Partner, Wolf Theiss (Vienna) (https://www.wolftheiss.com/lawyer/niklas-schmidt/). Course: AI Lab for Lawyers — live cohort course (new cohorts run regularly), https://maven.com/niklas-schmidt/ai-lab-for-lawyers ## Key pages - [Start here](https://www.ai-agents-for-lawyers.com/start-here): reading path for lawyers new to AI agents - [About the author](https://www.ai-agents-for-lawyers.com/about) - [About the course](https://www.ai-agents-for-lawyers.com/course) - [Full text of every page](https://www.ai-agents-for-lawyers.com/llms-full.txt): all articles and pages in one plain-text file ## Guides Foundational guides to AI and AI agents for lawyers: how large language models work, what agents actually are, and how to use them safely in legal practice. - [Agent Security for Lawyers: Prompt Injection, Data Leaks and Guardrails](https://www.ai-agents-for-lawyers.com/guides/agent-security-for-lawyers): AI agent security for law firms: prompt injection via hostile documents, the Grok Build and Cowork incidents, and the allowlists and gates that contain them. - [AI Agents for In-House Legal Teams: A Practical Guide](https://www.ai-agents-for-lawyers.com/guides/ai-for-in-house-counsel): AI for in-house counsel in 2026: the agents legal departments run, how to govern a Copilot stack, how to win AI savings from law firms, and a 12-month roadmap. - [AI Agents vs Assistants vs Chatbots: The Difference for Legal Work](https://www.ai-agents-for-lawyers.com/guides/ai-agents-vs-assistants-vs-chatbots): AI agent vs chatbot vs assistant, explained for lawyers: a five-tier taxonomy with examples, risk profile and supervision needs, plus a checklist for spotting agent washing. - [AI and the Billable Hour: Who Keeps the AI Dividend?](https://www.ai-agents-for-lawyers.com/guides/ai-and-the-billable-hour): AI and the billable hour in 2026: associate rates at $798 and hours up 4.2% while Citi demands AI savings. What the ethics rules allow, three fee scenarios and a clear view. - [AI for Small Law Firms and Solo Practitioners: What to Use and What to Skip](https://www.ai-agents-for-lawyers.com/guides/ai-for-small-law-firms): AI for small law firms in 2026 means a business-tier model, one legal tool and simple automation for under €200 a month, plus the policy and privacy settings most solos skip. - [AI Hallucinations in Legal Practice: Why They Happen and How to Catch Them](https://www.ai-agents-for-lawyers.com/guides/ai-hallucinations-legal-practice): AI hallucinations in legal practice: why models invent cases, what 2,041 court decisions and the HAQQ benchmark show, and a verification routine that holds. - [AI Literacy for Law Firms: What to Teach and What Article 4 Expects](https://www.ai-agents-for-lawyers.com/guides/ai-literacy-for-law-firms): AI literacy for law firms under Article 4 of the EU AI Act: an obligation of effort, no certificates, keep a record. A curriculum by role and a training record. - [Build or Buy Legal AI? Latham's GPUs, Harvey's Seats and the Firms in Between](https://www.ai-agents-for-lawyers.com/guides/build-vs-buy-legal-ai): Build vs buy legal AI in 2026: rent Harvey or Legora, assemble on Claude or Astra with MCP, or build like Latham on own GPUs. Costs, control, decision tree. - [Deep Research Tools for Lawyers: Claude, ChatGPT, Gemini and Perplexity Compared](https://www.ai-agents-for-lawyers.com/guides/deep-research-for-lawyers): Deep research AI for lawyers compared: what Claude, ChatGPT, Gemini and Perplexity research modes do, where they fail on law, and a verification table. - [How Large Language Models Work, Explained for Lawyers](https://www.ai-agents-for-lawyers.com/guides/how-large-language-models-work): How LLMs work, explained for lawyers: tokens, prediction, training versus inference, context windows, knowledge cutoffs, reasoning modes and the September 2026 model line-up. - [How to Choose an AI Tool for Your Law Firm: A Decision Framework](https://www.ai-agents-for-lawyers.com/guides/how-to-choose-legal-ai-tool): How to choose legal AI for your law firm: four routes, six vendor questions, a weighted scoring matrix and a six-week pilot, with September 2026 prices. - [Junior Lawyers and AI: Training, Hiring and the Missing Rung](https://www.ai-agents-for-lawyers.com/guides/junior-lawyers-and-ai): Junior lawyers and AI in 2026: Big Law hired 538 fewer graduates, 2% of UK juniors say AI helps them learn, and firms are rebuilding training with AI seats. - [Legal AI Benchmarks Explained: Vals, BigLaw Bench, LAB, HAQQ and LegalBench](https://www.ai-agents-for-lawyers.com/guides/legal-ai-benchmarks-explained): Legal AI benchmarks explained: what Vals, BigLaw Bench, Harvey LAB, HAQQ and LegalBench measure, the September 2026 leaders, and how to run your own evaluation. - [Prompt Engineering for Lawyers: Techniques That Actually Work](https://www.ai-agents-for-lawyers.com/guides/prompt-engineering-for-lawyers): Prompt engineering for lawyers as a method: six elements, six complete legal prompts (NDA review, research memo, clause redraft, client email) and iteration. - [The State of AI in Legal Practice in 2026: Every Number That Matters](https://www.ai-agents-for-lawyers.com/guides/state-of-ai-in-legal-practice-2026): Legal AI statistics for 2026, dated and sourced: adoption, client pressure, funding, prices, juniors, burnout, hallucination cases and regulation, with caveats. - [What Are AI Agents? A Practical Guide for Lawyers](https://www.ai-agents-for-lawyers.com/guides/what-are-ai-agents): AI agents for lawyers explained in plain terms: a model plus tools, a loop and a goal. How legal agents review NDAs, where they fail and what to expect in 2026. - [What Legal AI Really Costs in 2026: Harvey, Legora, CoCounsel, Claude and ChatGPT](https://www.ai-agents-for-lawyers.com/guides/legal-ai-pricing-guide-2026): Legal AI cost as of September 2026, from €39 to $1,200 per seat per month, with Harvey, Legora, CoCounsel, Claude and ChatGPT prices and worked budgets for 5 and 50 lawyers. - [Which AI Tools Train on Your Data? A Confidentiality Checklist for Lawyers](https://www.ai-agents-for-lawyers.com/guides/ai-confidentiality-checklist-lawyers): Which AI tools train on your data, plan by plan as of September 2026: ChatGPT, Claude, Gemini, Copilot, legal vendors, plus bar rules and a 10-point checklist. ## Use Cases How lawyers use AI agents for contract review, due diligence, legal research, litigation, drafting, e-discovery, compliance and client work — with real examples and results. - [AI Client Intake: Agents That Qualify, Conflict-Check and Onboard](https://www.ai-agents-for-lawyers.com/use-cases/ai-client-intake): AI client intake agents qualify leads, run conflict pre-checks, collect KYC documents and draft engagement letters. The flow, the fields and the guardrails. - [AI Contract Drafting: From First Draft to Negotiated Text](https://www.ai-agents-for-lawyers.com/use-cases/ai-contract-drafting): AI contract drafting works from your precedents, not a blank prompt. A drafting prompt, a worked SaaS example under Austrian law and the risks a redline hides. - [AI Contract Review: How Agents Redline Against a Playbook](https://www.ai-agents-for-lawyers.com/use-cases/ai-contract-review): AI contract review works when an agent applies your playbook of positions, fallbacks and escalations. Tools, accuracy numbers, setup and failure modes for 2026. - [AI Deposition and Transcript Summaries: A Litigator's Workflow](https://www.ai-agents-for-lawyers.com/use-cases/ai-deposition-and-transcript-summaries): AI deposition summaries work when every quotation is checked against the transcript, the tool runs on a business tier and output is anchored to page and line. - [AI Due Diligence: From Twenty Associate Hours to Two](https://www.ai-agents-for-lawyers.com/use-cases/ai-due-diligence): AI due diligence now runs as a tabular agent over the data room: 10,000 documents against 100 questions, every cell cited. Numbers, a question matrix, the junior gap. - [AI Email Triage for Lawyers: Agents That Sort, Summarise and Draft](https://www.ai-agents-for-lawyers.com/use-cases/ai-email-triage-for-lawyers): AI email triage for lawyers is safe when the agent classifies, summarises and drafts but never sends. A gated build, a prompt and the settings to switch on. - [AI for Legal Business Development: Pitches, Prospect Research and LinkedIn](https://www.ai-agents-for-lawyers.com/use-cases/ai-business-development-for-lawyers): AI business development for lawyers works at the research end: deep-research prospect briefs, pitches built on a client's own filings, posts that sound human. - [AI in E-Discovery: From TAR to Generative Review](https://www.ai-agents-for-lawyers.com/use-cases/ai-ediscovery-document-review): Generative AI review beats TAR on recall (87–88% vs 64% in Redgrave's 2026 study) but loses precision. Tools, privilege, defensibility and a sampling plan. - [AI Knowledge Management: Turning Precedents into a Firm Brain](https://www.ai-agents-for-lawyers.com/use-cases/ai-knowledge-management-law-firms): AI knowledge management for law firms has four layers: a DMS connection that copies nothing, curation, measured retrieval and permissions. With a 90-day plan. - [AI Legal Research in 2026: What Works, What Hallucinates](https://www.ai-agents-for-lawyers.com/use-cases/ai-legal-research): AI legal research now beats a lawyer baseline on accuracy yet misapplies law in 24% of answers. Which tools are grounded, where errors hide, a routine that holds. - [AI Legal Translation: Accuracy, Confidentiality and Workflow](https://www.ai-agents-for-lawyers.com/use-cases/ai-legal-translation): AI legal translation gives reliable working drafts of contracts and pleadings when a glossary, system prompt and bilingual review surround it. German-English example. - [AI Meeting Notes and Transcription for Lawyers: Consent, Privilege and Setup](https://www.ai-agents-for-lawyers.com/use-cases/ai-meeting-notes-for-lawyers): AI meeting notes are ethical for lawyers only with all-party consent, a no-training data path and a retention rule. Bar opinions, tools and a file-note prompt. - [AI Regulatory Monitoring: Agents That Track Law Changes for You](https://www.ai-agents-for-lawyers.com/use-cases/ai-regulatory-monitoring): AI regulatory monitoring works as a scheduled fetch, diff, classify and route workflow on official sources. How to build a weekly digest and cut false alarms. - [Drafting Briefs and Motions with AI Without Ending Up in Charlotin's Database](https://www.ai-agents-for-lawyers.com/use-cases/ai-brief-and-motion-drafting): AI brief drafting is safe only as a five-stage workflow: grounded research, outline, drafting from verified authorities, every case read, court rules checked. - [NDA Review at Scale with AI Agents: A Complete Workflow](https://www.ai-agents-for-lawyers.com/use-cases/ai-nda-review-at-scale): AI NDA review at scale works when an agent applies a ten-position playbook, routes exceptions to a named lawyer and logs every concession. Prompt and metrics. - [Writing Legal Memos with AI: A Method That Survives Partner Review](https://www.ai-agents-for-lawyers.com/use-cases/ai-legal-memos): An AI legal memo survives partner review when the model drafts only from sources you supply, every authority is checked three ways and the checks are logged. ## Practice Areas AI and AI agents for specific practice areas — M&A, tax, litigation, employment, IP, real estate, compliance, private clients and more. - [AI for Arbitration Practitioners: Submissions, Evidence and Tribunal Rules](https://www.ai-agents-for-lawyers.com/practice-areas/ai-for-arbitration-lawyers): AI for arbitration practitioners: what CIArb's 2025 guideline, tribunal procedural orders and disclosure rules mean for long records, witnesses and quantum. - [AI for Banking and Finance Lawyers: Facility Agreements, Regulation and Speed](https://www.ai-agents-for-lawyers.com/practice-areas/ai-for-banking-and-finance-lawyers): AI for banking and finance lawyers: covenant extraction from LMA-style facility agreements, compliance agents for DORA and MiCA, and bank-grade confidentiality. - [AI for Competition and Antitrust Lawyers: Merger Filings, Dawn Raids and Data](https://www.ai-agents-for-lawyers.com/practice-areas/ai-for-competition-lawyers): AI competition lawyers use review agents for merger-filing documents, dawn-raid triage and economic data. A filing-support workflow, the recall numbers and the sanction risk. - [AI for Corporate Lawyers: Governance, Board Papers and Company Secretarial Work](https://www.ai-agents-for-lawyers.com/practice-areas/ai-for-corporate-lawyers): AI corporate lawyers use models for board minutes, resolutions, entity compliance and shareholder documents, and scheduled agents for housekeeping. Design and gates. - [AI for Criminal Defence Lawyers: Disclosure Review, Evidence and Privilege](https://www.ai-agents-for-lawyers.com/practice-areas/ai-for-criminal-defence-lawyers): AI criminal defence tools review unused material, bodycam and transcripts and build timelines. The guardrails: privilege after Heppner, verified citations and deepfakes. - [AI for Crypto and Blockchain Lawyers: MiCA, Tax and On-Chain Evidence](https://www.ai-agents-for-lawyers.com/practice-areas/ai-for-crypto-lawyers): AI crypto lawyers use models for MiCA authorisation files, whitepaper gap checks, crypto-tax memos and on-chain evidence, plus agents that watch regulators. - [AI for Employment Lawyers: Advice, Investigations and the AI Act's HR Rules](https://www.ai-agents-for-lawyers.com/practice-areas/ai-for-employment-lawyers): AI for employment lawyers: advising on AI in hiring and monitoring after the AI Act's Annex III deferral to December 2027, plus investigations and policies. - [AI for Family Lawyers: Financial Disclosure, Drafting and Emotional Clients](https://www.ai-agents-for-lawyers.com/practice-areas/ai-for-family-lawyers): AI family lawyers get most from financial-disclosure analysis, chronologies and tone-controlled letters. Two 2026 divorce cases show why research and privilege need care. - [AI for Immigration Lawyers: Forms, Evidence Bundles and the Hallucination Risk](https://www.ai-agents-for-lawyers.com/practice-areas/ai-for-immigration-lawyers): AI immigration lawyers use models for forms, evidence bundles, translation drafts and multilingual client updates. Country research and case law still need verification. - [AI for IP Lawyers: Patents, Trademarks and the Copyright Cases](https://www.ai-agents-for-lawyers.com/practice-areas/ai-for-ip-lawyers): AI for IP lawyers: patent drafting and prior-art tools, trademark clearance agents, what NYT v OpenAI has decided so far, and which AI output is protectable. - [AI for Litigators: Research, Drafting, Discovery and the Sanctions Trap](https://www.ai-agents-for-lawyers.com/practice-areas/ai-for-litigators): AI for litigators pays off in chronologies, discovery and deposition prep; it costs $110,204 when a brief cites invented cases. Where to gain and the one rule. - [AI for M&A Lawyers: Diligence, Drafting and Deal Management](https://www.ai-agents-for-lawyers.com/practice-areas/ai-for-m-and-a-lawyers): AI for M&A lawyers now compresses diligence by 15–75%, drafts disclosure schedules and runs closing checklists. A deal-phase map of agent tasks, gates and fees. - [AI for Personal Injury Lawyers: Demand Letters, Medical Records and EvenUp](https://www.ai-agents-for-lawyers.com/practice-areas/ai-for-personal-injury-lawyers): AI personal injury lawyers use EvenUp, Supio and Eve for medical chronologies and demand packages. Wadsworth and Lacey show why a QC checklist still decides. - [AI for Privacy and Data Protection Lawyers: DSARs, DPIAs and Advising on AI](https://www.ai-agents-for-lawyers.com/practice-areas/ai-for-privacy-lawyers): AI for privacy lawyers: automating DSARs and DPIAs, reading vendor retention terms, and advising on LLM rollouts after EDPB Opinion 28/2024 and the Rome ruling. - [AI for Private Client and Estate Lawyers: Wills, Trusts and Family Offices](https://www.ai-agents-for-lawyers.com/practice-areas/ai-for-private-client-lawyers): AI private client lawyers draft from precedent, build asset schedules and explain plans to families; formalities, cross-border succession and tax stay with you. - [AI for Real Estate Lawyers: Leases, Title and Transaction Volume](https://www.ai-agents-for-lawyers.com/practice-areas/ai-for-real-estate-lawyers): AI for real estate lawyers: how to abstract 200 leases with an agent and a QA sample, what the platforms extract, land-register limits and template drafting. - [AI for Tax Lawyers and Tax Advisers: Research, Rulings and Returns](https://www.ai-agents-for-lawyers.com/practice-areas/ai-for-tax-lawyers): AI for tax lawyers works where sources are supplied and numbers are checked. What tax authorities, Big Four and Blue J do, plus a worked withholding example. ## Tools Independent overviews of the AI tools lawyers actually use: Claude, ChatGPT, Gemini, Copilot, Harvey, CoCounsel, Legora, Spellbook and more. - [Astra for Law: What OpenAI's Legal Offering Actually Includes](https://www.ai-agents-for-lawyers.com/tools/astra-for-law-openai): Astra for Law, announced 17 September 2026, pairs GPT-6 Astra with a 230-million-URL Legal Search Index, 26 partner plugins and a zero-retention API. - [ChatGPT for Lawyers: GPT-6 Astra, ChatGPT Work and What to Switch Off](https://www.ai-agents-for-lawyers.com/tools/chatgpt-for-lawyers): ChatGPT for lawyers as of September 2026. Which plans train on your chats, the 20-million-log discovery order, GPT-6 Astra, ChatGPT Work and a firm setup. - [Claude Code for Lawyers: Should Non-Programmers Use a Coding Agent?](https://www.ai-agents-for-lawyers.com/tools/claude-code-for-lawyers): Claude Code is a terminal coding agent. When lawyers should use it for bulk document work and small tools, two worked examples with guardrails, safer routes. - [Claude Cowork for Lawyers: Desktop Agents on Your Own Files](https://www.ai-agents-for-lawyers.com/tools/claude-cowork-for-lawyers): Claude Cowork lets Claude read, edit and create files in a folder you choose. What it does for lawyers, the February 2026 deletion incident and a safe setup. - [Claude for Lawyers: An Honest Review of Anthropic's Models for Legal Work](https://www.ai-agents-for-lawyers.com/tools/claude-for-lawyers): Claude for lawyers, reviewed as of September 2026: Fable 5.1, Opus 5 and Sonnet 5, plan prices, data retention by plan, legal plugins, benchmarks, weaknesses. - [Claude for Legal Plugins Explained: The 12 Practice-Area Plugins and 20+ Connectors](https://www.ai-agents-for-lawyers.com/tools/claude-for-legal-plugins): Claude for Legal gives paid Claude users 12 open-source practice-area plugins, 150+ skills and 20+ connectors to iManage, NetDocuments and CoCounsel. - [CoCounsel Legal (Thomson Reuters) Review: Westlaw-Grounded Agents](https://www.ai-agents-for-lawyers.com/tools/cocounsel-legal-review): CoCounsel Legal reviewed as of September 2026. The Claude-built rebuild, Brief Builder, Tabular Analysis, Deep Research Verify, $104 to $639 pricing and grounding. - [Gemini for Lawyers: Workspace Integration, Gemini Notebook and Data Caveats](https://www.ai-agents-for-lawyers.com/tools/gemini-for-lawyers): Gemini for lawyers as of September 2026. Why Workspace is the only safe door, what Gemini 3.1 Pro and Gemini Notebook do well, and where Google's terms bite. - [Gemini Notebook (NotebookLM) for Lawyers: A Grounded Case-File Assistant](https://www.ai-agents-for-lawyers.com/tools/gemini-notebook-notebooklm-for-lawyers): Gemini Notebook (ex-NotebookLM) for lawyers as of September 2026. How source-grounded answers work on a case file, three workflows, source caps and data terms. - [Harvey AI in 2026: What It Does, What It Costs and Who Uses It](https://www.ai-agents-for-lawyers.com/tools/harvey-ai-review): Harvey AI reviewed as of September 2026. The $15.5bn valuation, Harvey II, Tenet, 500-plus agents, who uses it, estimated seat prices and its own benchmark. - [Legora Review: The Agentic OS Challenging Harvey](https://www.ai-agents-for-lawyers.com/tools/legora-review): Legora reviewed as of September 2026. The $5.6bn Stockholm challenger to Harvey: aOS, Tabular Review, Wexler litigation facts, pricing, clients to Salesforce. - [Lexis+ with Protégé Review: Workflows, Vault and the Legal Intelligence Engine](https://www.ai-agents-for-lawyers.com/tools/lexis-protege-review): Lexis+ with Protégé replaced Lexis+ AI in February 2026 with 300+ workflows, Shepard's-grounded verification and an agentic engine. What it does, costs and still gets wrong. - [Microsoft 365 Copilot for Lawyers: Word, Outlook and the Legal Agent](https://www.ai-agents-for-lawyers.com/tools/microsoft-copilot-for-lawyers): Microsoft 365 Copilot for lawyers as of September 2026. Why 76 percent of firms use it, what $30 a seat buys, the Word Legal Agent, Agent 365 and its limits. - [Microsoft Word Legal Agent: Playbook Review and Redlines Inside Word](https://www.ai-agents-for-lawyers.com/tools/microsoft-word-legal-agent): Microsoft's Legal Agent for Word reviews contracts against your playbook and writes tracked-change redlines within the $30 Copilot add-on. What to check first. - [n8n for Law Firms: Building Legal Automations Without Code](https://www.ai-agents-for-lawyers.com/tools/n8n-for-law-firms): n8n is a self-hostable workflow builder with AI nodes. A German firm runs intake and deadlines on it for €20–30 a month; three law-firm workflows, node by node. - [Perplexity for Lawyers: Fast Sourced Research, With Limits](https://www.ai-agents-for-lawyers.com/tools/perplexity-for-lawyers): Perplexity for lawyers as of September 2026. What its cited web answers do well, what Enterprise and Computer for Counsel cost, and why it cannot verify law. - [Spellbook Review: Contract Drafting Inside Word for Smaller Teams](https://www.ai-agents-for-lawyers.com/tools/spellbook-review): Spellbook review for lawyers: the Word add-in at about $180 a month, 4,000 customers, grounded frontier models and an autonomous agent in early access. - [Zapier and Make for Law Firms: Quick Automations and AI Agents](https://www.ai-agents-for-lawyers.com/tools/zapier-and-make-for-law-firms): Zapier and Make automate intake, email triage and document assembly for law firms in an afternoon. What the AI agents add, two builds, costs and data caveats. ## Comparisons Head-to-head comparisons of AI tools and approaches for legal work: Claude vs ChatGPT, Harvey vs CoCounsel, agents vs assistants, build vs buy. - [AI Agents vs CLM Software: Replace, Layer or Ignore?](https://www.ai-agents-for-lawyers.com/comparisons/ai-agents-vs-clm-software): AI agents vs CLM software for in-house teams: what Ironclad-style CLMs do that agents cannot, where agents win, how MCP connects them, and three architectures. - [Claude for Legal vs Astra for Law: Anthropic and OpenAI Go Direct to Lawyers](https://www.ai-agents-for-lawyers.com/comparisons/claude-for-legal-vs-astra-for-law): Claude for Legal vs Astra for Law: open-source plugins and MCP connectors against a 230m-URL US law index with a ZDR API, data terms, prices, the European view. - [Claude vs ChatGPT for Lawyers (2026): Which Should You Use?](https://www.ai-agents-for-lawyers.com/comparisons/claude-vs-chatgpt-for-lawyers): Claude vs ChatGPT for lawyers in 2026, compared task by task: drafting, research, agents, data terms by plan, prices and benchmarks, plus a pick by firm type. - [Claude vs Gemini for Legal Work: Context, Workspace and Data Terms](https://www.ai-agents-for-lawyers.com/comparisons/claude-vs-gemini-for-legal-work): Claude vs Gemini for legal work: close on benchmarks, far apart on data terms. Workspace vs Microsoft fit, Gemini Notebook vs Claude Projects, EU residency. - [CoCounsel vs Lexis+ Protégé: The Research Incumbents' AI Compared](https://www.ai-agents-for-lawyers.com/comparisons/cocounsel-vs-lexis-protege): CoCounsel vs Lexis+ Protégé in 2026: KeyCite against Shepard's, a Claude Agent SDK rebuild against a multi-model harness, prices, jurisdictions, when to switch. - [Harvey vs CoCounsel: Platform Play vs Westlaw-Grounded Research](https://www.ai-agents-for-lawyers.com/comparisons/harvey-vs-cocounsel): Harvey vs CoCounsel for 2026: Westlaw and KeyCite grounding against firm-wide agents, published prices from $104 versus a 20-seat minimum, and a scenario table. - [Harvey vs Legora: The Two Legal AI Platforms Compared](https://www.ai-agents-for-lawyers.com/comparisons/harvey-vs-legora): Harvey vs Legora in September 2026: $15.5bn vs $5.6bn valuations, ARR, clients, Workflow Agents vs Agentic OS, models, pricing minimums, geography and who should pick which. - [Legal-Specific AI vs General-Purpose AI: Do Lawyers Need a Vertical Tool?](https://www.ai-agents-for-lawyers.com/comparisons/legal-ai-vs-general-purpose-ai): Legal-specific AI vs general-purpose AI: why legal tool use fell to 40%, what Harvey, CoCounsel and Legora add over Claude or ChatGPT, and a decision by task. - [Open-Weight vs Closed Models for Law Firms: Control, Cost and Confidentiality](https://www.ai-agents-for-lawyers.com/comparisons/open-weight-vs-closed-models-for-law-firms): Open-weight vs closed AI models for law firms: what Latham's own GPUs buy, Harvey Tenet, DeepSeek V4, Mistral, the legal benchmark gap, when self-hosting pays. - [Spellbook vs Harvey: Word Add-In vs Enterprise Platform](https://www.ai-agents-for-lawyers.com/comparisons/spellbook-vs-harvey): Spellbook vs Harvey for transactional work: about $180 a seat against a reported $1,000-plus with a 20-seat minimum, scope, grounding and a ten-lawyer decision. ## Regulation & Ethics AI regulation and professional ethics for lawyers: the EU AI Act, ABA Formal Opinion 512, bar guidance, court orders, GDPR, confidentiality and privilege. - [ABA Formal Opinion 512 Explained: What US Lawyers Must Do When Using AI](https://www.ai-agents-for-lawyers.com/regulation/aba-formal-opinion-512): ABA Formal Opinion 512 applies six Model Rules to generative AI: competence, confidentiality, communication, candour, supervision and fees. What each duty requires in 2026. - [AI Hallucination Sanctions: The Cases Every Lawyer Should Know (2023–2026)](https://www.ai-agents-for-lawyers.com/regulation/ai-hallucination-sanctions-cases): AI hallucination cases reached 2,041 in Charlotin's database by September 2026, 811 involving lawyers. Every sanction from Mata to Couvrette's $110,204, with lessons. - [AI Rules for Austrian and German Lawyers: ÖRAK, BRAK and CCBE Guidance](https://www.ai-agents-for-lawyers.com/regulation/austria-germany-bar-guidance-ai): ÖRAK's four AI rules and § 40 Abs 3 RL-BA bind Austrian lawyers; BRAK's § 43a BRAO line binds German ones; CCBE guides cover both. With a bilingual checklist. - [AI Vendor Due Diligence for Law Firms: The Questions to Ask Before You Sign](https://www.ai-agents-for-lawyers.com/regulation/ai-vendor-due-diligence-law-firms): AI vendor due diligence for law firms starts with the subprocessor chain, then training and retention terms, ZDR eligibility, data residency, audit logs and exit rights. - [Attorney–Client Privilege and AI: Heppner, Warner, the NYT Logs and Public Chatbots](https://www.ai-agents-for-lawyers.com/regulation/attorney-client-privilege-and-ai): Consumer chatbot memos are not privileged. US v. Heppner, Warner v. Gilbarco and the 20-million-log OpenAI order, plus rules that keep privilege intact. - [Ayinde v Haringey Explained: The UK's Leading AI Hallucination Judgment](https://www.ai-agents-for-lawyers.com/regulation/ayinde-v-haringey-explained): Ayinde v Haringey [2025] EWHC 1383 (Admin) explained: the fake cases, the Divisional Court's sanctions ladder, the duty on heads of chambers and how the SRA built on it. - [Billing Clients for AI: What You Can Charge and What You Cannot](https://www.ai-agents-for-lawyers.com/regulation/billing-clients-for-ai): Lawyers may bill actual time spent using and checking AI or a fixed fee agreed in advance, but not saved hours, subscriptions or marked-up AI costs. Worked numbers inside. - [Court Standing Orders on AI: Where You Must Disclose or Certify](https://www.ai-agents-for-lawyers.com/regulation/court-standing-orders-ai-disclosure): Court AI disclosure rules in 2026: over 30 of 94 US federal districts and 300+ judges require certification, two Ohio judges ban it, Illinois requires none. - [Do You Have to Tell Clients You Use AI? Disclosure Rules and Practice](https://www.ai-agents-for-lawyers.com/regulation/ai-disclosure-to-clients): When lawyers must disclose AI use to clients under ABA 512, California, CCBE and ÖRAK rules, when consent is required, and a sample engagement-letter clause. - [EU AI Act Article 4: The AI Literacy Duty for Law Firms, Explained](https://www.ai-agents-for-lawyers.com/regulation/eu-ai-act-article-4-ai-literacy): Article 4 of the AI Act requires every firm whose staff use AI to support their AI literacy. In force since 2 February 2025, supervised nationally since August 2026. - [GDPR and AI Tools for Lawyers: Lawful Basis, DPIAs and Vendor Terms](https://www.ai-agents-for-lawyers.com/regulation/gdpr-and-ai-tools-for-lawyers): How GDPR applies when law firms use Claude, ChatGPT or Copilot: controller and processor roles, lawful basis, DPIA triggers, transfers and vendor terms. - [How to Write a Law Firm AI Policy (With a Template Outline)](https://www.ai-agents-for-lawyers.com/regulation/law-firm-ai-policy): A law firm AI policy lists approved tools by tier, classifies data, makes verification personal, covers disclosure, billing and training, and limits agents. - [Mata v. Avianca, Three Years On: What the First AI Sanction Still Teaches](https://www.ai-agents-for-lawyers.com/regulation/mata-v-avianca-lessons): Mata v. Avianca (S.D.N.Y. 2023) cost two lawyers $5,000 for six fake ChatGPT cases. What went wrong, why asking AI to verify AI fails, and what changed since. - [The Digital Omnibus on AI: What Changed in the AI Act and What Did Not](https://www.ai-agents-for-lawyers.com/regulation/eu-ai-act-digital-omnibus): The Digital Omnibus AI Act amendment, Regulation (EU) 2026/1744, deferred high-risk duties to December 2027 but left transparency, literacy and the prohibitions in force. - [The EU AI Act for Lawyers and Law Firms: What Applies in 2026](https://www.ai-agents-for-lawyers.com/regulation/eu-ai-act-for-lawyers): The EU AI Act applies to law firms as deployers. Article 4 literacy and Article 50 transparency are live; high-risk duties are deferred to December 2027. - [The SRA's 2026 Warning Notice on AI Misuse: What UK Solicitors Must Know](https://www.ai-agents-for-lawyers.com/regulation/sra-ai-warning-notice-2026): The SRA AI warning notice of 17 August 2026 followed 42 misuse reports in a year. Solicitors must understand a tool well enough to review its output critically. - [UK Judiciary, Bar Council and Law Society AI Guidance: The 2026 Picture](https://www.ai-agents-for-lawyers.com/regulation/uk-judiciary-and-bar-ai-guidance): UK judiciary AI guidance (Oct 2025), Bar Council considerations (Nov 2025) and Law Society material share one rule: whoever signs is responsible for every word. - [US State Bar AI Ethics Opinions: A 2026 State-by-State Guide](https://www.ai-agents-for-lawyers.com/regulation/us-state-bar-ai-ethics-opinions): As of June 2026, 17 US jurisdictions plus the ABA have formal AI ethics opinions. None bans AI. They agree on verification, split on client consent and billing. ## Playbooks Step-by-step playbooks for building and running AI agents in a law firm: prompts, projects, automations, no-code apps and verification workflows. - [AI Privacy Settings for Lawyers: Step-by-Step in ChatGPT, Claude, Gemini, Copilot and Perplexity](https://www.ai-agents-for-lawyers.com/playbooks/ai-privacy-settings-step-by-step): Exact steps to turn off training and check retention in ChatGPT, Claude, Gemini, Copilot and Perplexity as of September 2026, plus admin settings and a log. - [Automate Contract Review with a Playbook: Positions, Fallbacks and Escalations](https://www.ai-agents-for-lawyers.com/playbooks/automate-contract-review-with-a-playbook): A contract review playbook an AI agent can apply: ten sample rows, encoding for Claude, Spellbook and Word's Legal Agent, plus a 20-contract calibration method. - [Build a Client Intake Workflow in n8n: From Web Form to Matter Opening](https://www.ai-agents-for-lawyers.com/playbooks/n8n-client-intake-workflow): Build an n8n client intake workflow node by node: form trigger, AI classification, conflict pre-check, engagement letter, lawyer approval, DMS entry and tests. - [Build a Firm Knowledge Base for AI: Curation, Retrieval and Permissions](https://www.ai-agents-for-lawyers.com/playbooks/build-a-firm-knowledge-base): A playbook for a law firm knowledge base AI can retrieve from: curating precedents, metadata, permission mapping, platform choice and a 30-question test. - [Build a Legal Decision-Tree App for Clients Without Code](https://www.ai-agents-for-lawyers.com/playbooks/build-a-legal-decision-tree-app): Build a legal decision-tree app for clients without code in a day: write the logic as a node table, generate it with Claude or Lovable, and test the edge cases. - [Build a Prompt Library for Your Practice: Structure, Governance and 12 Starter Prompts](https://www.ai-agents-for-lawyers.com/playbooks/build-a-prompt-library-for-your-practice): Build a law firm prompt library lawyers will use: folder structure, a header for every prompt, a review cadence for model changes and 12 tested starter prompts. - [Build Your First Legal AI Agent in an Afternoon (No Code Required)](https://www.ai-agents-for-lawyers.com/playbooks/build-your-first-legal-ai-agent): Build a legal AI agent in one afternoon without code: pick NDA triage, write a one-page playbook, set up a Claude Project, add verification and test on ten documents. - [Connect Claude to iManage or NetDocuments with MCP: A Setup Guide](https://www.ai-agents-for-lawyers.com/playbooks/connect-claude-to-your-dms-with-mcp): Connect Claude to iManage or NetDocuments with MCP in six admin steps, test on a read-only matter, enable audit logging and scope permissions before rollout. - [Create a Custom GPT for Your Practice: A Lawyer's Walkthrough](https://www.ai-agents-for-lawyers.com/playbooks/create-a-custom-gpt-for-your-practice): How to create a custom GPT for your practice: GPT vs Project vs ChatGPT Work, two full instruction sets, knowledge-file rules, data settings, sharing and tests. - [Extract Data from PDFs and Scans with AI: Contracts, Invoices and Court Files](https://www.ai-agents-for-lawyers.com/playbooks/extract-data-from-pdfs-with-ai): How lawyers extract data from PDFs and scans with AI: OCR first, a fixed schema, a full lease-extraction prompt, batch runs in Cowork or n8n, and sampling. - [How to Verify AI Legal Research: A Citation-Checking Protocol](https://www.ai-agents-for-lawyers.com/playbooks/verify-ai-legal-research): Verify AI legal research with a five-check protocol: open every authority, match the quote, confirm holding and status, log it. Template, time budgets, tools. - [Red-Team Your Argument with AI: Adversarial Prompts for Litigators and Negotiators](https://www.ai-agents-for-lawyers.com/playbooks/red-team-your-argument-with-ai): Red-team your legal argument with AI in five rounds: prompts that make the model argue the other side, play a sceptical judge and score your case before filing. - [Run a Six-Week AI Pilot in Your Firm: Design, Metrics and the Go/No-Go](https://www.ai-agents-for-lawyers.com/playbooks/run-an-ai-pilot-in-your-firm): Run a law firm AI pilot in six weeks: three use cases, ten users, a 20-task evaluation set, baseline metrics, security sign-off and a go/no-go scorecard. - [Set Up Claude Projects for a Matter: Instructions, Files and Memory](https://www.ai-agents-for-lawyers.com/playbooks/set-up-claude-projects-for-a-matter): Set up a Claude Project for a legal matter in 30 minutes: sample instruction text, which files to upload, Skills, memory, Team sharing and three prompt flows. - [Vibe-Code a Client Intake App as a Lawyer (Lovable, Claude Artifacts, v0)](https://www.ai-agents-for-lawyers.com/playbooks/vibe-code-a-client-intake-app): Vibe-code a client intake app as a lawyer with Lovable, Claude Artifacts or v0: the spec, four exact prompts, a fee-band calculator and the IT handover. - [Write a Law Firm AI Policy in a Day: A Working Template](https://www.ai-agents-for-lawyers.com/playbooks/write-a-law-firm-ai-policy): A working law firm AI policy template with ten clauses, commentary on each, EU and US variants and an hour-by-hour rollout plan that gets it signed in one day. ## Questions Straight answers to the questions lawyers ask about AI: Can I use ChatGPT for client work? Will AI replace lawyers? Is it confidential? Do I have to disclose it? - [Can AI Do Legal Research Without Hallucinating? The Honest Answer](https://www.ai-agents-for-lawyers.com/questions/can-ai-do-legal-research-without-hallucinating): No AI legal research tool is hallucination-free as of September 2026. Measured rates, why grounding does not cure misreading, and the checks that protect you. - [Can AI Draft a Contract? What Works in 2026 and What Still Needs a Lawyer](https://www.ai-agents-for-lawyers.com/questions/can-ai-draft-a-contract): AI can draft a contract from a good precedent and clear instructions, but not sign one off. The 2026 evidence, the errors it makes and a six-step protocol. - [Can I Bill Clients for AI? Time, Subscriptions and Value Fees](https://www.ai-agents-for-lawyers.com/questions/can-i-bill-clients-for-ai): You can bill actual time spent using AI, not time it saved; subscriptions are overhead; value fees stay lawful. What ABA 512, Texas 705, Virginia 1901 and California say. - [Can Lawyers Use ChatGPT for Legal Work? Yes — With These Conditions](https://www.ai-agents-for-lawyers.com/questions/can-lawyers-use-chatgpt): Lawyers can use ChatGPT for legal work on a non-training plan if they verify every citation, tell clients and bill honestly. The rules as of September 2026. - [Do I Have to Tell the Court I Used AI? Disclosure Rules by Jurisdiction](https://www.ai-agents-for-lawyers.com/questions/do-i-have-to-tell-the-court-i-used-ai): Whether you must tell the court you used AI depends on the judge: 30+ US federal districts require it, Illinois does not, England has no duty. How to check. - [Does the EU AI Act Apply to Law Firms? A Direct Answer](https://www.ai-agents-for-lawyers.com/questions/does-the-eu-ai-act-apply-to-law-firms): Yes. An EU law firm whose staff use ChatGPT, Claude or Copilot is a deployer under the EU AI Act. Article 4 literacy applies now, Article 50 since August 2026. - [Does Using ChatGPT Waive Attorney–Client Privilege?](https://www.ai-agents-for-lawyers.com/questions/does-using-chatgpt-waive-privilege): Using ChatGPT rarely waives privilege in the technical sense; the courts' answer is worse. In Heppner, consumer-chatbot memos were never privileged at all. - [How Much Does Harvey AI Cost? Pricing, Minimums and Alternatives](https://www.ai-agents-for-lawyers.com/questions/how-much-does-harvey-ai-cost): Harvey AI costs an estimated $1,000–1,200 per seat per month with a 20-seat minimum as of September 2026. What you get, how to negotiate and cheaper options. - [Is ChatGPT GDPR-Compliant for Law Firms? A Practical Answer](https://www.ai-agents-for-lawyers.com/questions/is-chatgpt-gdpr-compliant-for-law-firms): ChatGPT can be used GDPR-compliantly by a law firm on Business, Enterprise or API terms with training off, a processor contract and a DPIA; consumer plans cannot. Seven steps. - [Is Harvey Worth It for a Small Law Firm?](https://www.ai-agents-for-lawyers.com/questions/is-harvey-worth-it-for-a-small-firm): Harvey is usually not worth it for a small law firm: a reported 20-seat minimum at about $1,000–1,200 a seat. When it is, and what six lawyers should buy instead in 2026. - [Is It Ethical for Lawyers to Use AI? The Rules in the US, UK and EU](https://www.ai-agents-for-lawyers.com/questions/is-it-ethical-for-lawyers-to-use-ai): Yes, every major bar permits lawyers to use AI. It becomes unethical when output is filed unverified or client data is exposed. US, UK and EU rules in 2026. - [What Percentage of Lawyers Use AI in 2026? The Survey Numbers](https://www.ai-agents-for-lawyers.com/questions/what-percentage-of-lawyers-use-ai): The percentage of lawyers using AI in 2026 runs from 74% to 94% depending on the survey; daily use is 21–44% and only about 40% use legal-specific tools. Every number, dated. - [Which AI Has the Lowest Hallucination Rate for Legal Work?](https://www.ai-agents-for-lawyers.com/questions/which-ai-has-the-lowest-hallucination-rate-for-law): The lowest hallucination rate AI for legal work as of September 2026: GPT-5.5 at 3% on HAQQ, Claude Opus 4.8 best overall, and why no model reaches the zero courts demand. - [Will AI Replace Lawyers? What the 2026 Evidence Actually Shows](https://www.ai-agents-for-lawyers.com/questions/will-ai-replace-lawyers): AI will not replace lawyers in 2026, it replaces tasks: Big Law hired 7.5% fewer graduates while demand for hours rose 4.2%. What the evidence shows. ## Glossary A plain-language glossary of AI terms for lawyers: agents, LLMs, tokens, context windows, RAG, MCP, hallucinations, fine-tuning and more. - [Agentic AI (Definition for Lawyers)](https://www.ai-agents-for-lawyers.com/glossary/agentic-ai): Agentic AI means software where a language model plans and carries out multi-step work with a degree of autonomy. A five-level autonomy ladder, legal examples and cautions. - [AI Agent (Definition for Lawyers)](https://www.ai-agents-for-lawyers.com/glossary/ai-agent): An AI agent is a language model with tools, a goal and permission to take several steps on its own. Definition for lawyers, an NDA triage example, failure data and four questions to ask. - [Computer Use / Browser Agent — Definition for Lawyers](https://www.ai-agents-for-lawyers.com/glossary/computer-use): Computer use lets an AI agent see a screen and click, type and browse for you. Definition, Claude for Chrome, ChatGPT Work, Perplexity Computer and the legal risks. - [Context Window — Definition for Lawyers](https://www.ai-agents-for-lawyers.com/glossary/context-window): A context window is the text an AI model can hold at once. As of September 2026 it is 1 million tokens on Claude, GPT-6 and Gemini, about 555,000 words. - [Contract Playbook — Definition for Lawyers](https://www.ai-agents-for-lawyers.com/glossary/contract-playbook): A contract playbook is a clause-by-clause table of preferred positions, fallbacks and escalation rules. How AI review tools consume it, with sample rows you can copy. - [Deployer (EU AI Act) — Definition for Lawyers](https://www.ai-agents-for-lawyers.com/glossary/deployer-eu-ai-act): A deployer under the EU AI Act is anyone using an AI system under its own authority for professional purposes. Law firms are deployers; here is what follows, and when. - [Fine-Tuning — Definition for Lawyers](https://www.ai-agents-for-lawyers.com/glossary/fine-tuning): Fine-tuning retrains an AI model's weights on your data. How it differs from RAG and prompting, why Latham and Harvey do it, why Spellbook refuses, and the client-data problem. - [General-Purpose AI Model (GPAI) — Definition for Lawyers](https://www.ai-agents-for-lawyers.com/glossary/general-purpose-ai-model): A general-purpose AI model under the EU AI Act is a model with significant generality, such as GPT-6 or Claude Opus 5. Definition, tiers, signatories, enforcement. - [Hallucination (AI) — Definition for Lawyers](https://www.ai-agents-for-lawyers.com/glossary/hallucination): An AI hallucination is fluent, confident, false output: an invented case, a misread holding or a fake quote. 2,041 court decisions now involve one. What to know. - [Human-in-the-Loop — Definition for Lawyers](https://www.ai-agents-for-lawyers.com/glossary/human-in-the-loop): Human-in-the-loop means an AI system pauses for a person to review or approve before it acts. Where the gate belongs in legal workflows and why regulators ask for it. - [Large Language Model (LLM) — Definition for Lawyers](https://www.ai-agents-for-lawyers.com/glossary/large-language-model): A large language model is a neural network trained to predict the next token, and it powers every legal AI tool. How LLMs are built, the models of September 2026 and what follows for reliability and confidentiality. - [Model Context Protocol (MCP) — Definition for Lawyers](https://www.ai-agents-for-lawyers.com/glossary/model-context-protocol): Model Context Protocol (MCP) is the open standard that lets Claude, ChatGPT and Copilot read your DMS or docket feed through one connector. What a server exposes and what to check. - [Open-Weight Model — Definition for Lawyers](https://www.ai-agents-for-lawyers.com/glossary/open-weight-model): An open-weight model publishes its trained weights for anyone to run. Open weights vs open source, DeepSeek, Mistral and Muse Glimmer licences, self-hosting and government bans. - [Prompt Injection — Definition for Lawyers](https://www.ai-agents-for-lawyers.com/glossary/prompt-injection): Prompt injection is an attack that hides instructions in text an AI model reads, such as a contract or email, so it obeys the attacker. Why agents raise the stakes. - [Reasoning Model — Definition for Lawyers](https://www.ai-agents-for-lawyers.com/glossary/reasoning-model): A reasoning model works through intermediate steps before it answers. What adaptive thinking and effort settings mean for legal analysis, cost, speed and hidden reasoning. - [Retrieval-Augmented Generation (RAG) — Definition for Lawyers](https://www.ai-agents-for-lawyers.com/glossary/retrieval-augmented-generation): Retrieval-augmented generation (RAG) searches a document set first and drafts from what it finds. Every grounded legal tool uses it; here is why errors still get through. - [Skills and Plugins (AI) — Definition for Lawyers](https://www.ai-agents-for-lawyers.com/glossary/skills-and-plugins): A skill is a packaged, reusable instruction an AI tool loads for one task; a plugin bundles skills with tools, connectors and automations. How they differ, and governance. - [System Prompt — Definition for Lawyers](https://www.ai-agents-for-lawyers.com/glossary/system-prompt): A system prompt is the standing instruction an AI model reads before your message. Where it lives in Claude, ChatGPT and Skills, a legal template, and its limits. - [Token (AI) — Definition for Lawyers](https://www.ai-agents-for-lawyers.com/glossary/token): A token is the unit of text a language model reads and writes, usually part of a word. Why limits, prices and speed are counted in tokens, not pages or words. - [Vector Database — Definition for Lawyers](https://www.ai-agents-for-lawyers.com/glossary/vector-database): A vector database stores text as numerical embeddings so an AI system can find passages by meaning, not keywords. Its role in RAG and knowledge management, and its limits. - [Vibe Coding — Definition for Lawyers](https://www.ai-agents-for-lawyers.com/glossary/vibe-coding): Vibe coding means building software by describing what you want to an AI tool in plain language and iterating on the result. What lawyers build with it, and its limits. - [Workflow Agent — Definition for Lawyers](https://www.ai-agents-for-lawyers.com/glossary/workflow-agent): A workflow agent is an AI agent that runs a fixed sequence of legal steps with approval gates. Definition, Harvey and Lexis examples, and five design rules. - [Zero Data Retention (ZDR) — Definition for Lawyers](https://www.ai-agents-for-lawyers.com/glossary/zero-data-retention): Zero data retention means the AI vendor stores nothing after replying. Which plans offer ZDR, the Covered Models exception, and why it matters for privilege and GDPR.