Written by a practising lawyer · Updated November 2026
AI agents for lawyers, explained by one who uses them every day.
150+ practical, independent guides to using AI and AI agents in legal practice — what works, what fails, what the rules say, and how to build your own workflows. No hype, no vendor spin.
By Dr. Niklas Schmidt, partner at Wolf Theiss · 1,000+ lawyers trained · rated 4.7/5 from 381 ratings
Browse by topic
Everything a lawyer needs to know about AI agents
Guides
18Foundational 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.
Use Cases
16How lawyers use AI agents for contract review, due diligence, legal research, litigation, drafting, e-discovery, compliance and client work — with real examples and results.
Practice Areas
17AI and AI agents for specific practice areas — M&A, tax, litigation, employment, IP, real estate, compliance, private clients and more.
Tools
18Independent overviews of the AI tools lawyers actually use: Claude, ChatGPT, Gemini, Copilot, Harvey, CoCounsel, Legora, Spellbook and more.
Comparisons
10Head-to-head comparisons of AI tools and approaches for legal work: Claude vs ChatGPT, Harvey vs CoCounsel, agents vs assistants, build vs buy.
Regulation & Ethics
18AI regulation and professional ethics for lawyers: the EU AI Act, ABA Formal Opinion 512, bar guidance, court orders, GDPR, confidentiality and privilege.
Playbooks
16Step-by-step playbooks for building and running AI agents in a law firm: prompts, projects, automations, no-code apps and verification workflows.
Questions
14Straight 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?
Glossary
23A plain-language glossary of AI terms for lawyers: agents, LLMs, tokens, context windows, RAG, MCP, hallucinations, fine-tuning and more.
Editor's picks
Start with these
Guides
AI Hallucinations in Legal Practice: Why They Happen and How to Catch Them
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.
9 min read
Guides
Prompt Engineering for Lawyers: Techniques That Actually Work
Prompt engineering for lawyers as a method: six elements, six complete legal prompts (NDA review, research memo, clause redraft, client email) and iteration.
8 min read
Guides
What Are AI Agents? A Practical Guide for Lawyers
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.
10 min read
Guides
Which AI Tools Train on Your Data? A Confidentiality Checklist for 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.
11 min read
Use Cases
AI Contract Review: How Agents Redline Against a Playbook
AI contract review works when an agent applies your playbook of positions, fallbacks and escalations. Tools, accuracy numbers, setup and failure modes for 2026.
8 min read
Use Cases
AI Due Diligence: From Twenty Associate Hours to Two
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.
10 min read
Why this site exists
Most writing about AI in law is by vendors, or by people who don't practise.
I am a tax partner at Wolf Theiss in Vienna. I run AI agents in my own practice every day — for research, drafting, due diligence, business development and the administrative work no lawyer enjoys. I have also taught more than a thousand lawyers from over fifty firms how to do the same.
This site is the written companion to that teaching. Every page is meant to be useful on its own: specific tools, specific prompts, specific rules, specific failure modes. Where something is genuinely uncertain — and much is — the page says so.
If you would rather learn it live, in four evenings, with homework and a community of other lawyers, that is what the AI Lab for Lawyers course is for.
Recently updated
- Human-in-the-Loop — Definition for Lawyers3 min · updated 2026-11-15
- Prompt Injection — Definition for Lawyers3 min · updated 2026-11-15
- Skills and Plugins (AI) — Definition for Lawyers3 min · updated 2026-11-15
- Token (AI) — Definition for Lawyers3 min · updated 2026-11-15
- Vector Database — Definition for Lawyers3 min · updated 2026-11-15
- Vibe Coding — Definition for Lawyers3 min · updated 2026-11-15
Live cohort course · new cohorts run regularly
AI Lab for Lawyers
Eight hours of live, hands-on training: prompting, legal research and drafting, document analysis, custom assistants, agents and automation, no-code apps — and the risks and rules that come with them. Taught by Dr. Niklas Schmidt, partner at Wolf Theiss.
- 1,000+
- lawyers trained
- 50+
- law firms represented
- 4 × 2h
- live sessions, recorded
- 300+
- practical slides
Questions people ask about this site
What is an AI agent, in plain terms?
An AI agent is a language model that can take actions, not just write text: it can read your documents, search, call tools, fill in forms and run multi-step tasks with limited supervision. For lawyers that means moving from 'draft me a clause' to 'review these 40 NDAs against our playbook and flag deviations'.
Is this site independent?
Yes. It is written by a practising lawyer, not a vendor. Tools are discussed on their merits, including their weaknesses. The only thing promoted here is the author's own course, AI Lab for Lawyers.
Do I need technical skills to use AI agents?
No. Everything covered here uses browser-based tools. Where a playbook involves automation platforms such as n8n, Make or Zapier, it is explained step by step for non-programmers.
Is the content up to date?
Every page carries an 'updated' date. The site was researched and written in September 2026 and is reviewed as models, tools and regulation change — which, in this field, is monthly.