A model built to teach
It shows you, asks you back, and leaves the last step to you.

Where does Dad sit so the seesaw balances? It writes turn = weight × distance on the board and works it out.DuckyHelper is built to teach and trained to teach. It is trained on 1,000,000+ tutoring examples and inspired by 100+ learning-science papers. It does not just hand you the answer: it asks what you think, gives hints before answers, draws while it explains, checks you with quick questions and brings ideas back on a spaced schedule.
Quizzes when you ask.
Say quiz me and a quiz rises out of the pill. Miss one and it shows you why.
QuizzesAnswers are easy. Learning is not.
A chatbot is built to answer. That is great for facts and bad for homework: in a 2025 field experiment, students who practiced with a plain AI chat did worse on the exam once it was gone, while a version built to hint instead of answer mostly avoided the harm. Getting the answer and learning how are different jobs. DuckyHelper does the second one. What that study found
The model card
| What | DuckyHelper |
|---|---|
| Built to | Teach. It asks you back |
| Trained on | 1,000,000+ tutoring examples |
| Inspired by | 100+ learning-science papers (see the library) |
| Listens to | Your voice, in your language |
| Looks at | Your screen, in the app only, while you talk to it |
| Shows with | Drawings on your screen, and worked steps, simulations, quizzes and a blackboard out of the pill |
| Checks with | Questions, quizzes, hints and spaced flashcard review |
Trained on 1,000,000+ tutoring examples
Trained to teach, on a million examples of tutoring, and built around 100+ papers on how people learn. The film shows it as one real exchange pulling back to a million.
Seven principles, in the film's order
| Principle | Paper in the film | What DuckyHelper does | Film | |
|---|---|---|---|---|
| 01 | Teach one on one | Bloom, 1984 | Live voice teaching for one learner | 23.4 s |
| 02 | Guide, don't hand over answers | Bastani et al., 2025 | Hints before answers | 31.0 s |
| 03 | Draw it as you explain | Mayer & Moreno, 2003 | The pen draws on your screen | 34.8 s |
| 04 | Show a worked example | Sweller & Cooper, 1985 | Worked steps, one move each | 38.6 s |
| 05 | Quiz, don't re-read | Roediger & Karpicke, 2006 | Quizzes in the moment | 42.4 s |
| 06 | Have them explain it back | Chi et al., 1994a | Asks what you think | 46.2 s |
| 07 | Space it out | Cepeda et al., 2006 | Flashcards that come back | 50.0 s |
How it teaches, in one session
- 01
You ask
You ask out loud, about anything, or about what is on your screen (the app sees it).
- 02
It asks what you think
It asks what you already think, then explains in short steps, drawing as it talks.
- 03
One question per step
After each step it asks one question and waits for your answer.
- 04
Hints, then the answer
Stuck? A nudge, a bigger hint, the worked step. The answer comes last.
- 05
It points at the slip
Got it wrong? It points at the exact step, and says why.
- 06
It comes back later
What you missed becomes a flashcard that comes back before you forget it.
Honest limits DuckyHelper has not been tested in a controlled study, and we publish no benchmark scores or learning gains of our own. The numbers on these pages belong to the papers that reported them. When we run a study, its results will be here, whatever they show.
More films
A tutor for anyone
60 s, Bloom 1984 in Swiss dots, music only

Try it on your own work
Press fn on a Mac (Ctrl+Shift+Space on Windows and Linux) and say it out loud. It sees your screen, so it works on your own problem with you, and shows you.
“Show me why on the board.”
DuckyHelper is an app for Mac (Apple silicon, macOS 14 or later), Windows and Linux.
Questions
What is DuckyHelper trained on?
DuckyHelper is trained on 1,000,000+ tutoring examples and inspired by 100+ learning-science papers. It is trained to teach: to guide, hint and check rather than hand over answers.
What does built to teach mean?
That every part of it is designed around how people learn: it asks before it tells, hints before it answers, draws while it explains, checks with quick questions and schedules review. The principles page links each behaviour to its research.
Is DuckyHelper just a chatbot?
No. A general chatbot is built to answer questions. DuckyHelper is trained on tutoring examples and has teaching rules and tools (hints, quizzes, drawing on your screen) that a chatbot does not.
Has DuckyHelper been studied?
Not yet. It has no study results of its own. We cite the published research it is built on, and when a study of DuckyHelper is done, its results will be published here.
Sources
- Bloom, B. S. (1984). The 2 Sigma Problem: The Search for Methods of Group Instruction as Effective as One-to-One Tutoring. Educational Researcher, 13(6), 4-16. (accessed 2026-10-09)
- Bastani, H., Bastani, O., Sungu, A., Ge, H., Kabakcı, Ö., & Mariman, R. (2025). Generative AI without guardrails can harm learning: Evidence from high school mathematics. Proceedings of the National Academy of Sciences, 122(26), e2422633122. (accessed 2026-10-09)
- Mayer, R. E., & Moreno, R. (2003). Nine Ways to Reduce Cognitive Load in Multimedia Learning. Educational Psychologist, 38(1), 43-52. (accessed 2026-10-09)
- Sweller, J., & Cooper, G. A. (1985). The Use of Worked Examples as a Substitute for Problem Solving in Learning Algebra. Cognition and Instruction, 2(1), 59-89. (accessed 2026-10-09)
- Roediger, H. L., & Karpicke, J. D. (2006). Test-Enhanced Learning: Taking Memory Tests Improves Long-Term Retention. Psychological Science, 17(3), 249-255. (accessed 2026-10-09)
- Chi, M. T. H., De Leeuw, N., Chiu, M.-H., & Lavancher, C. (1994a). Eliciting Self-Explanations Improves Understanding. Cognitive Science, 18(3), 439-477. (accessed 2026-10-09)
- Cepeda, N. J., Pashler, H., Vul, E., Wixted, J. T., & Rohrer, D. (2006). Distributed practice in verbal recall tasks: A review and quantitative synthesis. Psychological Bulletin, 132(3), 354-380. (accessed 2026-10-09)
Keep exploring
Research
How DuckyHelper is built to teach: the model, a library of 100+ learning-science papers, the principles it follows and our white papers.
OpenPrinciples
Twelve learning-science principles behind DuckyHelper, from one-on-one tutoring to spacing, each with the research and what DuckyHelper does because of it.
OpenLibrary
100+ real learning-science papers behind DuckyHelper, sorted by principle, each with a citation, a link to the publisher and a one-line summary.
OpenBuilt to Teach
White paper: how DuckyHelper turns ten findings from learning science into teaching rules and tools, and the limits of that work.
OpenWhat the evidence says about AI tutors
Randomized trials of AI tutors so far: Harvard physics, Ghana, Nigeria, Tutor CoPilot, and the PNAS study where AI help hurt. What they show, and do not.
OpenFeatures
Every DuckyHelper feature: press one key in any app and ask out loud. It sees your screen and shows you, on a blackboard, in 3D or in ink on your screen, and on a Mac it does the work in your apps with its own cursor.
Open
Do anything
Ask it a question or hand it a job, in any app.
Doing jobs for you is in the Mac app. Asking works on Mac, Windows and Linux.
