AI in Law · a single-credit, 16-hour course
Use AI well in your legal work. Know where it breaks.
For law students. Brief a model, build a research assistant over a bundle of judgments in ten minutes, split work across agents when it pays, and know which model is worth paying for. Then verify every claim, because you sign what it produces, and know where Indian law stands. Every lab runs on a free account.
- contact hours
- 16 h
- sessions × 90 min
- 8
- lab in each session
- 30 min
- academic credit
- 1
Step 1 of 3: a random anchor.
Quick gut check.
Is the share of UN member states that are African more or less than 10%?
(That number was handed to you at random. Hold that thought.)
Half taught, half practised
60 minutes teach one technique and run it live on a real tool; a 30-minute lab demonstrates it end to end on a realistic student task. Students repeat it on their own work after the session.
- Live on the class, or built along
- Real tools, free tier, on screen
The premise
AI is already in your legal work. Using it well is a craft.
The tools read faster than you can and draft a first pass in seconds. They also invent judgments with perfect confidence, and a High Court has already ordered costs for citing one. What separates the two outcomes is what you put in front of the model, how you ask, and what you check.
The course teaches that craft and drills the habit that makes the output usable in practice: trace every claim to source and keep the trail.
The stakes
Since July 2026, citing unverified AI-generated authority has been professional misconduct in India. The course trains you to be the person who checks.
“'Summarise this judgment' asks for luck. A specification with an output contract is a brief a junior could execute, and unlike the junior, the machine never comes back to ask what you meant.”
How every session runs
Something happens live. You leave with a named skill.
When the room needs to feel an effect first, the session is a mirror: an experiment runs on the class, then on the model. When it teaches craft, it is a build-along: the class builds the prompt, the workspace or the pipeline with the presenter. The last 30 minutes are always yours, on your own laptop.
- 01SOMETHING HAPPENS LIVE
An experiment on the class, or a build-along
The room commits an answer on their phones and sees itself fooled, or builds the prompt, the workspace or the pipeline live with the presenter.
- 02THE MECHANISM
Why the machine does that
The effect explained from how a language model works, so it can be predicted next time rather than memorised.
- 03ON A REAL TOOL
Shown on a real tool
Proved live on a free-tier account, with designated moments where the same task runs on a stronger model beside it.
- 04A NAMED SKILL
One thing to do on Monday
A practical technique, demonstrated in the lab and repeated by students on their own work.
The course · 16 contact hours
From briefing a model to a work product you can sign
Eight core sessions in four phases of two: direct the machine, then decode it; engineer the context; orchestrate, then verify; the law, and the work product. Each phase builds on the last, from the first prompt to a work product the student would sign.
01 · Sessions 1–2
Direct the machine, decode it
Prompts that work (specification, worked examples, the output contract), then how a language model actually works and why it must sometimes fail, taught once, properly.
02 · Sessions 3–4
Engineer the context
What goes into the window and why: supply the judgment, structure long documents, keep the conversation clean. Then a grounded workspace over a bundle of authorities, built in ten minutes.
03 · Sessions 5–6
Orchestrate, then verify
Work split across a drafter, a fresh-context critic and a verifier, with model and reasoning effort chosen per task. Then the four-step authority check and the trail, practised in the labs.
04 · Sessions 7–8
The law, and the work product
Where the law stands, India first (evidence, professional duty, data protection, privilege), and the whole pipeline run end to end into a work product the student can sign.
The closing four hours
Two Conversations with Experts, then the evaluation.
Two 90-minute Conversations with Experts test the course's frameworks against real practice: in each, the instructors lead a structured conversation with a practitioner who uses AI seriously in their own work.
Conversation 01 · 90 min
Inside the firm — what AI actually does to legal work
What they use, and for what; what they refuse to use it for, and why; what is checked before anything leaves the building, and by whom; how juniors are supervised when drafts are machine-fast; and what they would want a first-year associate to do on day one.
Speaker: Ms. Aastha, Partner, Argus Partners (Solicitors & Advocates); a law-firm practitioner
Builds on Sessions 1, 3 and 6
Conversation 02 · 90 min
Building with AI in-house — harnesses, tooling, workflows
What they have built: the workspaces, pipelines and guardrails behind an in-house function; how reliability is evaluated before roll-out; data governance when the data is the company's and the clients'; buy versus build; and the in-house privilege gap the Supreme Court confirmed in 2025, as they live with it.
Speaker: Ms. Suman Mishra, Head of Commercial Contracts, Kotak Mahindra Bank; an in-house banking and technology lawyer
Builds on Sessions 4–5 and 7
Evaluation · 60 min
A 60-minute evaluation session closes the course, taken in class.
Two parts, taken on the course platform. An applied audit: a fresh extract seeded with the three classes of authority failure (one fabricated, one that says something materially different, one no longer good law), verified against supplied sources, with the trail. And short applied questions: an authentication note on a described digital artefact; a ceiling diagnosis on a described failure; and scenario questions on the legal position, marked for register: a holding is not an observation, and a draft is not a rule. The paper rewards demonstrated verification and judgment over recall.
Learning outcomes
What a student can do at the end
Every outcome is practised in a lab before it is assessed.
- 01
Explain what a language model does, predict from the mechanism where it will fail on a legal task (fabrication, sycophancy, variance, anchoring), and place any confident output on the Ladder of Misinference before relying on it.
- 02
Brief a model like a junior: a specification that says everything once, an output contract that forces uncertainty into the open, and worked examples where form must match. Iterate one change at a time, starting fresh when a conversation degrades.
- 03
Engineer the context: supply the source instead of asking from recall, structure long documents for the window, demand and verify paragraph pinpoints, and manage what does not fit by excerpting, chunking or re-supplying, knowing what each choice loses.
- 04
Build and run a grounded research workspace over a real bundle of authorities (instruction set, pinpoint citations, trap-tested) and state its limits: retrieval is not verification, and a bundle is only as current as its date.
- 05
Split work across a drafter, a fresh-context critic and a verifier when independence or breadth pays, and choose the model and reasoning-effort level per task, diagnosing whether a failure is the prompt's ceiling, the context's, the tool's, or the model's.
- 06
Run the four-step authority check (exists, says that, still good law, and the step everyone skips), classify failures into the three classes, and keep a verification trail another person could repeat.
- 07
State where Indian law stands on AI use, by register: authentication under BSA s.63 and its case law, the synthetic-media rules, the judiciary's instruments from White Paper to draft Regulations, professional duty after the 2026 misconduct holding, data protection, and privilege. Apply it, including the academic-integrity rules that bind a student today.
- 08
Ship a verified work product: a real deliverable through the full pipeline, every claim verified to source, with the trail and an AI-use disclosure that would survive a judge, a partner or an examiner.
Who it's for
Purpose-built for law students.
Purpose-built for law students: every technique arrives on a task from the student's own year (a moot memorial, an internship research note, a judgment brief, a seminar paper, journal cite-checking), and the legal session covers their own regulatory position. No quantitative background or prior AI knowledge is assumed; the course builds on the legal training students already have.
What it needs
A laptop, a phone, and a connection that carries video.
- Live over video conference, never pre-recorded. The experiments need a room that is present.
- Your laptop runs the labs on free accounts (ChatGPT, Claude or Gemini; NotebookLM; Indian Kanoon). Your phone is the clicker.
- Weekly (one 90-minute session) or a four-day intensive; the two expert conversations and the evaluation are scheduled into either.
For law schools
A single-credit, 16-hour course your academic council can approve as a value-added elective. Syllabus, session plan and assessment scheme on request.
Also from Computational Thinking
A live, in-school course for grades 8–12.
Four standalone 60-minute sessions with live clicker experiments, pitched for teenagers.
How do I know this is true?
Eight sessions build the craft and the check, two Conversations with Experts show how firms and in-house teams use it, and the evaluation asks you to do the whole job once. Start with Session 1.