AI agent for law students
Hypo Issue-Spotting Drill Agent
Raise a student's issue-spotting accuracy through adaptive practice rounds.
What it does
Issue spotting is the skill that most exams test, yet students practice it rarely and get little feedback. The agent picks a doctrine area from the student's weak list and builds a fact pattern in exam style with a hidden list of issues. The student writes their issue list and the agent compares it with the hidden list, scoring what was found, missed and invented. It then gives feedback on each miss and builds a harder fact pattern on the weak topic. Each round adapts to what the student missed. The student approves which topics move to the review list. Edge case: the student spots negligence but not the contract waiver, so the next pattern puts the waiver in plain view.
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.
Read the steps as a list
- Student starts a practice session
- Read the weak topic list and recent scores
- Pick a topic and build a fact pattern with a hidden issue list
- Present the pattern and wait for the student's issue list
- Compare the student's list with the hidden list
- Did the student find at least 70 percent of issues?If not: Explain each miss and build a new pattern on the same topic. Back to step 3.
- Score found, missed and invented issues
- Student approves which topics move to the review listThe agent waits here for your OK.
- Is the topic mastered across two rounds?If not: Raise difficulty or repeat with a changed fact pattern. Back to step 3.
- Session score and updated weak list
How it decides
It picks the topic with the lowest recent score. After each round it raises difficulty if the student finds 80 percent of issues and repeats the topic with a clearer pattern if they find less than half.
- Pick the topic with the lowest score in the last 3 rounds
- At 80 percent or above raise difficulty
- Below 50 percent repeat the topic with clearer facts
- Invented issues are scored separately
Make it yours
Every agent is a starting point. You choose these settings for your own situation.
- Target score before raising difficulty (default 80 percent)
- Topics in scope
- Rounds per session (default 3)
- Length of fact patterns
What keeps you in control
It always asks you first
- Student approves topics moving to or off the review list
Hard limits
- Never presents a hidden issue as fact outside the exercise
- Never grades the student for an official course
It stops when
- Done: topic mastered or session time ends
- Stop: student ends the session
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.
- 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
