AI for Legal Capstone Exercise
Deliberate Academy Editorial Team
Reviewed for accuracy and professional relevance
You're 10 lessons in — don't lose your progress.
Sign up free to save where you are and earn a verified certificate when you pass.
- Apply skills from across this course in a single realistic professional scenario
- Produce a concrete, role-relevant deliverable using AI tools
- Self-assess your output against professional quality criteria
This course has covered AI across legal practice: document review, contract analysis, legal research, drafting, confidentiality and data governance, professional ethics, litigation support, legal operations, and matter management. The capstone brings those skills together in a scenario that a junior solicitor encounters regularly: time pressure, a senior partner waiting, and a client who needs a plain-English update before close of business.
The exercise is designed to test not just whether you can produce the outputs, but whether you can identify the verification gaps an AI will not flag itself. In legal work, an unverified AI output that reaches a client or a partner is a professional risk. The goal is to move fast without moving recklessly.
Capstone Exercise
Contract Dispute: Research, Case Summary, and Client Update
Context
You are a junior solicitor at a mid-sized commercial law firm. At 10am, a senior partner drops a new matter on you. The client is a logistics company that entered a three-year software supply agreement. The supplier has stopped providing updates and claims the contract does not require them to do so beyond year one. The client wants to know whether they have a breach of contract claim and what their options are. The partner needs a structured case summary memo by 3pm. The client needs a plain-English update letter by 4pm before a team meeting. You have the contract, which you will describe to the AI in structured terms for this exercise.
Your Task
Draft a four-step prompt sequence for an AI assistant (Claude, ChatGPT, or Perplexity) to support this workflow. Step 1: a prompt to summarise the scenario in structured legal terms, covering parties, contract type, key obligation in dispute, and the client's position. Step 2: a prompt to identify the key legal issues, specifying the jurisdiction as England and Wales. Step 3: a prompt to produce a structured case summary memo with three sections: Facts, Key Legal Issues, and Preliminary View. Step 4: a prompt to draft a client update letter in plain English, explaining the position clearly without legal jargon, covering what the issue is, what the options are, and what the next step is. For each of the four steps, add a verification annotation: a specific description of what a competent solicitor must check before relying on or sending that output. At the end, write a one-paragraph professional reflection (100 to 150 words) on the limits of AI in this workflow and where solicitor judgment is not substitutable.
Your notes (optional)
Deliverable
A four-step prompt sequence with sample outputs described, a verification annotation for each step naming the specific professional risk and the check required, and a one-paragraph professional reflection of 100 to 150 words on the limits of AI in this legal workflow.
The partner memo and the client letter both rest on the same preliminary analysis. What does this capstone say must not happen when that analysis is translated into the client letter?
Select one answer.
- Legal AI output is a research and drafting accelerator, not a substitute for legal judgment: every output that reaches a partner, a client, or a court filing must pass through the solicitor's professional verification standard before it leaves the firm
- Jurisdiction, register, and audience are three brief parameters that dramatically change the quality and reliability of AI legal output: specifying all three before generating is a minimum professional standard for AI-assisted legal drafting
- Verification annotations are not bureaucratic overhead: they are the record of where professional judgment was applied, which matters both for quality assurance and for professional indemnity purposes
- The limit of AI in legal work is not capability but accountability: an AI can draft a client letter in seconds, but the solicitor who sends it takes professional responsibility for its accuracy, and that responsibility cannot be delegated to the model
Complete all lessons to take the free exam
Pass the exam to earn your AI for Legal — Certified AI Practitioner — a verifiable certificate you can share on LinkedIn.