Understand AI.
Put it into practice.
Plain explanations, worked legal examples, and the checks that keep AI-assisted work reliable.
Learn at the depth you need.
53 lessons in 9 chapters, with worked legal examples throughout.
Choose your next step
Read in sequence or jump inInside AI
How it works behind the scenes. For judges, lawyers, and curious newcomers: what a model does, what it can see, why a persuasive answer can be wrong, and what courts and regulators already expect. No code.
Use AI in your practice
Move from a clear assignment to source-linked work products, focused revision, and repeatable quality checks.
Build your own AI systems
Choose and test a local model, then build document workflows with Python, APIs, retrieval, and bounded agents. Finish with security, deployment, and maintenance. Local processing is not a privacy guarantee.
Explore a subject
All chaptersAI essentials
Understand what a model does, what it can see, and why a persuasive answer still needs support.
6 lessons Chapter 2Using AI effectively
Write a useful brief, preserve meaning, distinguish evidence from inference, and resume work reliably.
5 lessons Chapter 3AI in legal practice
Build source-linked chronologies, transcript work products, research tables, and drafting workflows.
5 lessons Chapter 4Tools and choosing between them
Compare tools on complete tasks, design review tables, and turn dictation into usable work.
3 lessons Chapter 5Agents, skills, and automation
Understand the components, design a first bounded agent, and make recurring work recoverable.
6 lessons Chapter 6Documents and knowledge systems
Prepare source material, understand retrieval and RAG, and create reusable precedent and matter knowledge.
4 lessons Chapter 7Local AI and building systems
Learn the hardware, run a model, write small utilities, connect an API, and preserve structured facts.
7 lessons Chapter 8Reliability and oversight
Evaluate results, verify support, recognize prompt injection, and map the full data journey.
7 lessons Chapter 9Local AI, in depth
Optional depth: run a model on hardware you control. Check memory, setup, data flows and results before using client files.
10 lessons