Complete AI Training
Sign inGet my AI kit

Your job's AI kit

Get your AI kit

Tell us who you are and what you do. We show you your kit right away and email you the link: skills, prompts, AI agents, MCP servers and courses for your job.

500+ jobs ready, and we make a kit for any other job. No payment needed to look.

Share

AI agent for law students

Exam Practice Loop Agent

Students improve issue spotting through repeated practice

Exam Practice Loop Agent: what goes in, what the agent does and what you get

What it does

Law students learn exam technique by practice, but they rarely get fast, specific feedback on what they missed. Before exams, this agent runs a practice loop. It draws on the student's outline to build a hypothetical fact pattern and asks the student to write an answer. It scores the answer against an issue checklist built from the outline and shows missed issues, weak rule statements and missing application. It tracks weak topics and builds the next fact pattern around them. A topic missed twice becomes the focus. It repeats until the student reaches the target, by default 80% of issues spotted. The student decides when to stop. Edge case: the student keeps missing a defense, so the agent adds more patterns that turn on that defense.

How it works

Follow the arrows from top to bottom. The orange dashed arrow is the loop: when a check fails, the agent goes back and tries again.

Start and resultWhat it doesA check on its own workWaits for your OKGoes back and retries
Yes, continueApprovedNo 1 STARTS WHEN Practice session 2 USES A TOOL Build fact pattern from outline 3 DOES Student writes answer 4 DOES Score against issue checklist 5 CHECKS THE RESULT Did the student meet the target score? If not: build a new pattern on weak topics. Back to step2. 6 YOU APPROVE Student decides to stop or continue 7 RESULT Progress log
Read the steps as a list
  1. Practice session
  2. Build fact pattern from outline
  3. Student writes answer
  4. Score against issue checklist
  5. Did the student meet the target score?If not: build a new pattern on weak topics. Back to step 2.
  6. Student decides to stop or continueThe agent waits here for your OK.
  7. Progress log

How it decides

It scores answers against an issue checklist and targets weak topics.

  • Missed issue twice: target topic
  • Rule without application: feedback
  • Target 80% of issues

Make it yours

Every agent is a starting point. You choose these settings for your own situation.

  • Target score
  • Time limits
  • Topics
  • Feedback style

What keeps you in control

It always asks you first

  • Session plan

Hard limits

  • Never used during a closed exam
  • Never claims model answers are official

It stops when

  • Done: target met
  • Stop: exam date passed

Set it up

We guide you through the set-up, step by step

Members get the full set-up guide for this agent. No technical skills needed: you copy, paste and upload.

10 minto set it up in your AI
5 AIsChatGPT, Claude, Copilot, Gemini, Grok
  • One set of instructions to paste into your AI, with the clicks for ChatGPT, Claude, Microsoft 365 Copilot, Gemini and Grok
  • The agent then walks you through connecting your own data, one source at a time
  • A downloadable copy with the flow chart, the rules and the full guide
Get access to this agent

An example run

What happensIn a torts session on December 2, the student spotted 6 of 10 issues and missed assumption of risk for the second time, so the target check failed. The agent built the next fact pattern around defenses, with a ski resort injury. The student spotted 9 of 10 and stated the rule correctly. The student decided to stop and move to contracts.

More agents for law students