Official launch partners
All courses

The Practical Legal AI Handbook

How AI works, when to trust it, and what the rules allow

Cover of The Practical Legal AI Handbook
Contents
9 chapters · 44 lessons
Author
Lawve AI
Updated
October 2026
Start reading

Contents

Chapter 0

Introduction

 0/3
  1. 0.1 Who this guide is for and how to read it
  2. 0.2 The eight questions every lawyer asks And where each one is answered in this guide.
  3. 0.3 Survival glossary One plain-language paragraph per term, each with a concrete example: LLM, token, prompt, context window, hallucination, RAG, skill, MCP, agent, API and more.
Chapter 1

How can AI help my practice and day-to-day work?

 0/5
  1. 1.1 What is AI really? How a language model works, in plain words.
  2. 1.2 Chat vs. agent Asking a question vs. delegating a task.
  3. 1.3 Where skills, MCP and plugins fit in The short version.
  4. 1.4 What lawyers are actually using AI for right now What lawyers give to AI, how they check it, and what surveys do not show.
  5. 1.5 Does it really save time? What studies measure, where the time goes, and why the setup matters more than the tool.
Chapter 2

Can I trust it?

 0/5
  1. 2.1 Hallucinations Why models still invent things, and why the errors are now subtler.
  2. 2.2 What is the answer based on? Memory vs. documents vs. live search.
  3. 2.3 When the model tells you what you want to hear Why it agrees with your view and gives way when you push back.
  4. 2.4 What a benchmark score really tells you How AI is tested, and how to read a vendor's accuracy claim.
  5. 2.5 Test it on your own matters Building a small test set that reflects your actual work.
Chapter 3

Am I allowed to use it?

 0/7
  1. 3.1 The three questions behind the question Confidentiality, competence, disclosure.
  2. 3.2 What happens to the documents I upload? Consumer vs. business plans, training on your data, retention, memory.
  3. 3.3 Who can access, store or reuse my data? Providers, sub-processors, hosting location, US access to data.
  4. 3.4 Anonymisation and pseudonymisation When it helps, when it isn't enough, when it isn't needed.
  5. 3.5 Professional rules by jurisdiction France, the European Union, the United States, the United Kingdom and others in brief.
  6. 3.6 Sovereignty and compliance Open-source vs. closed, cloud vs. EU cloud vs. on-prem, European providers: a simple decision grid.
  7. 3.7 Other risks Prompt injection, IP, over-reliance, insurance.
Chapter 4

How do I choose the best tools?

 0/6
  1. 4.1 Same brain, different bodies Why one model behaves differently in different products.
  2. 4.2 Subscription vs. API access What an API is, what you pay for, and when it makes sense without being a developer.
  3. 4.3 Legal AI tool or general-purpose assistant? What each gives you, what each costs you.
  4. 4.4 Open-source vs. closed, from the buyer's seat What open weights decide, what they do not, and the questions that replace them.
  5. 4.5 Panorama of tools A map of about 100 tools, and five questions that place any tool on it.
  6. 4.6 Questions to ask before choosing a legal AI tool A template of questions to send each vendor and compare their answers.
Chapter 5

How do we make it work across the firm or legal team?

 0/7
  1. 5.1 Why one enthusiast is not an adoption strategy
  2. 5.2 Choosing a first pilot Criteria, candidates, scope, success and kill criteria.
  3. 5.3 Training the team Who needs what, formats that work, training juniors without deskilling them.
  4. 5.4 Measuring time saved and quality Baselines for time saved, and what partners and associates actually report.
  5. 5.5 Who maintains the tools and the shared know-how? Roles, a shared library of prompts and skills, and a new role: the legal engineer.
  6. 5.6 Change management Incentives, resistance, the billable-hour tension, talking to clients.
  7. 5.7 Working with IT, security and procurement
Chapter 6

How do I get better results?

 0/3
  1. 6.1 Give it better context Explaining the task, choosing documents and examples, and showing your own work as the standard.
  2. 6.2 Turning your methods into reusable instructions From repeated prompts to custom skills.
  3. 6.3 Watch out for AI slop
Chapter 7

What does this mean for my career and my firm?

 0/4
  1. 7.1 Which skills should lawyers develop? What gains value, what new literacies are needed, and whether to learn to code.
  2. 7.2 What does a legal engineer do? Role, where they sit, how to become one.
  3. 7.3 How AI may change fees, staffing and client expectations The billable hour, the leverage pyramid, training juniors, and “did you use AI?”
  4. 7.4 What an AI-native firm might look like
Chapter 8

Where and how do I start now?

 0/4
  1. 8.1 Starter kits by profile Solo, small firm, large-firm associate, partner, in-house, student.
  2. 8.2 Classic mistakes to avoid
  3. 8.3 Section 1 recap The eight questions answered in one page.
  4. 8.4 Staying current without drowning