AI tutoring · Interactive learning

Co-construction Canvas

I redesigned the live AI tutoring classroom around a shared canvas, so students build the answer step by step instead of watching a slide.

Role
Product Design Strategist
Timeline
About 1 month, ongoing
Team
PM · Academics · Engineering · Customer Success Managers
Status
Prototype, student testing next

My contribution

I redesigned the classroom around the canvas, built a coded prototype with Claude, designed the AI tutor’s avatars, and turned reviews with academics and customer success managers into decisions for the team.

This is ongoing work at my current company. Some details are left out, colleagues are named by role, and the screens show a prototype, not a shipped product.

Problem

Students were watching the lesson, not doing it.

Paper is an education company that brings online tutoring to K-12 students through their schools, including live math lessons taught by an AI tutor. That AI tutor taught from slide decks, so students mostly listened, and a slide could not build a visual step by step. We saw it in the data: usage, dosage, course completion, and exit ticket scores.

01

The lesson can’t be worked on

The slide stays still. The AI tutor talks, the student listens, then answers in the chat.

02

The work happens off screen

Students solve on paper and send a photo when they are done. The AI tutor only sees the final answer, so it cannot guide them step by step.

03

Slides lose attention

Long stretches of listening to a static slide make it hard for students to stay focused.

The questionHow might we turn a live AI lesson from watching slides into students building the math themselves?

Design stance

Put the work on the lesson itself, so students do the math on screen and the AI tutor can guide each step.

Research

Look at what exists before adding more.

I tested Aristotle end to end and reviewed StudyFetch, to see how other tutors use a canvas.

What it means for us

Most interactions are still choosing an answer. Our canvas focuses on building it. To judge how deep an activity goes, the team used ICAP, a learning science framework by Michelene Chi. It sorts what students do into four levels, from deepest to shallowest, and research shows students learn more at the deeper ones:

  • InteractiveThinking it through with someone. Explaining to the AI tutor, hearing a challenge, and revising.
  • ConstructiveMaking something new. Splitting a fraction bar or writing an explanation.
  • ActiveDoing something with what is shown. Tapping or picking an answer.
  • PassiveReceiving. Listening to the AI tutor talk over a slide.

Feedback

What changed after the reviews.

I walked academics and customer success managers through the design, then worked with engineering on what a small shared tool set could cover. Their feedback shaped the prototype below.

01

Customer success managers

They saidAudio is the top reason a session fails, and some Chromebooks have touchscreens.

What changedA sound test before the lesson starts, and students tap to move on instead of saying yes.

02

Academics

They saidPause was hard to find, the tutor felt small, and speed control added clutter.

What changedA labeled Pause lesson button in the top bar, a larger tutor with the student camera closer, and no speed control in V1.

03

Engineering

They saidTapping and picking are easy to grade, but they pull lessons back to choosing an answer.

What changedBuilding tasks stay in the plan, and grading them is tracked as an open question.

04

All three teams

They saidAbout a dozen tools could cover three quarters of lessons.

What changedV1 starts with 5 to 10 tools, each mapped to a group of standards.

Simple taps and drag and drops are surface level engagement. Co-construction, like a whiteboard or writing and critiquing sentences, deepens thought.

Academics team, design review (paraphrased)
ICAP ladder from Passive to Interactive
Rank by depthToday’s slides sit at Passive. Tap to count is Active. Each lesson should reach the level its standard asks for.
A small shared tool set mapped to standards
One small tool setThe canvas shares a lesson format with the authoring studio, so the same tools work in both.

Product Design

Give the canvas the room. Keep the tutor close.

Lesson context on top, the canvas in the middle, the tutor at the bottom. Each screen answers a problem found in the project.

AI tutor stickers for every lesson moment
One character, every momentStart, working, hints, encouragement, good job, and goodbye, plus math and reading.
AI tutor logo with horizontal and stacked lockups
Mark and lockupsHorizontal and stacked lockups of the seedling mark.

Version 3 The latest round. The chat moves into the side panel, and key terms collect there as the tutor introduces them.

Open version 3 full screen

Version 2 The earlier round. A lesson outline sits on the left and the chat runs along the bottom.

Open version 2 full screen

Results

Reviewed, with student testing next.

Academics and customer success managers have reviewed the prototype. Usability testing with students is next, so outcome numbers will follow.

Stage
Prototype

Coded with Claude from a real lesson deck.

Reviewed by
2 teams

Academics and customer success managers.

V1 scope
5 to 10 tools

Mapped to groups of standards.

Next
Student tests

On Chromebooks.