Sandbox Tool — Beta

Classroom
Session
Builder

Design structured problem-solving sessions where students work with AI as a thinking partner — not an answer machine. The instructor sets the problem. Students make visible choices. The AI is in the room, not in charge of it.

Built for educators. Every session is designed around human judgment — where to push back, what to accept, where the tool falls short. AI literacy is not a separate subject. It lives inside the problem.

Free from bias by design. Because we are building it together.
Instructor Setup
Choose how you want to build your session materials — let Claude generate them from your scenario, or provide your own.
What course is this for? Who are the students?
Anything the session should be sensitive to — cultural context, prior knowledge gaps, accessibility needs, or things to avoid.
Be specific. Choose a problem within your students' reach but not yet solved — the productive struggle is where the learning lives. If the problem is too easy, students extract an answer. If it's beyond reach, they disengage. The right problem sits in the middle: challenging enough to require real thinking, grounded enough to feel solvable.
What are the 2-3 things you want students to walk away knowing or being able to do?
Building your session
Student Session
Work through the problem with your AI tool. At each checkpoint — stop. Reflect. Record your thinking before moving on.
NO SESSION LOADED

Complete Instructor Setup first to generate session materials. Then return here to run the live session.

Debrief
Capture what each pair found. What diverged? Where did students push back on the AI? What did they accept that they shouldn't have?
RUN A SESSION FIRST

Complete Instructor Setup and run a Student Session before debriefing.

Why this exists

You cannot teach AI literacy without having AI in the room. This tool is built on a single research-backed principle: friction by design. AI is the most efficient discomfort-eliminator ever built — which is precisely why we have to engineer the struggle back in. Research consistently shows that retrieval, productive struggle, and the discomfort of not-yet-knowing are where understanding takes hold. AI undermines learning only when used as a substitute for thinking on problems within a student's reach. The reflection checkpoints, the visible choices, the report-out — these are not administrative steps. They are the friction. Studies of human-AI collaboration consistently find that a small minority of students who use AI as a sparring partner — demanding evidence, asking for counterarguments, refusing to settle — outperform those who simply accept its output. This tool is built to produce more of those students.