--- title: "A model built to teach | DuckyHelper" url: "https://duckyhelper.com/research/built-to-teach/" description: "DuckyHelper's tutor is trained on 1,000,000+ tutoring examples and inspired by 100+ learning-science papers: a tutor, not an answer machine." updated: "2026-10-09" --- The model # A model built to teach DuckyHelper's tutor 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 is a tutor, not an answer machine: 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. [Watch the film](https://duckyhelper.com/films/built-to-teach/)[See the principles](https://duckyhelper.com/research/principles/) [All films](https://duckyhelper.com/films/#model) Why ## Answers 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 GPT-4 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](https://duckyhelper.com/research/principles/guide-dont-hand-over-answers/) ## The model card DuckyHelper's tutor, as the film's model card shows it | What | DuckyHelper's tutor | | --- | --- | | Built to | Teach. A tutor, not an answer machine | | Trained on | 1,000,000+ tutoring examples | | Inspired by | 100+ learning-science papers (see [the library](https://duckyhelper.com/research/library/)) | | Listens to | Your voice, in your language | | Looks at | Your screen, in the Mac app only, while you talk to it | | Shows with | Drawings on your screen, a blackboard, pictures, graphs, simulations, worked steps | | Checks with | Questions, quizzes, hints and spaced flashcard review | 1,000,000+ ## 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 Each principle, the paper on screen in the film, and what the tutor does | | Principle | Paper in the film | What the tutor does | Film | | --- | --- | --- | --- | --- | | 01 | [Teach one on one](https://duckyhelper.com/research/principles/teach-one-on-one/) | Bloom, 1984 | A live voice tutor for one learner | 23.4 s | | 02 | [Guide, don't hand over answers](https://duckyhelper.com/research/principles/guide-dont-hand-over-answers/) | Bastani et al., 2025 | Hints before answers | 31.0 s | | 03 | [Draw it as you explain](https://duckyhelper.com/research/principles/draw-it-as-you-explain/) | Mayer & Moreno, 2003 | The pen draws on your screen | 34.8 s | | 04 | [Show a worked example](https://duckyhelper.com/research/principles/worked-examples/) | Sweller & Cooper, 1985 | Worked steps, one move each | 38.6 s | | 05 | [Quiz, don't re-read](https://duckyhelper.com/research/principles/retrieval-practice/) | Roediger & Karpicke, 2006 | Quizzes in the moment | 42.4 s | | 06 | [Have them explain it back](https://duckyhelper.com/research/principles/explain-it-back/) | Chi et al., 1994a | Asks what you think | 46.2 s | | 07 | [Space it out](https://duckyhelper.com/research/principles/spaced-practice/) | Cepeda et al., 2006 | Flashcards that come back | 50.0 s | ## How it teaches, in one session 1. 1. You ask You ask out loud, about anything, or about what is on your screen (the Mac app sees it). 2. 2. It asks what you think It asks what you already think, then explains in short steps, drawing as it talks. 3. 3. One question per step After each step it asks one question and waits for your answer. 4. 4. Hints, then the answer Stuck? A nudge, a bigger hint, the worked step. The answer comes last. 5. 5. It points at the slip Got it wrong? It points at the exact step, and says why. 6. 6. 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 [0:60A model built to teach60 s, narrated](https://duckyhelper.com/films/built-to-teach/) ## Frequently asked questions ### What is DuckyHelper trained on? DuckyHelper's tutor 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 the tutor 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 ChatGPT? No. A general chatbot is built to answer questions. DuckyHelper's tutor is trained on tutoring examples and has teaching rules and tools (hints, quizzes, flashcards, 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 1. [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.](https://doi.org/10.3102/0013189X013006004) (accessed 2026-10-09) 2. [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.](https://doi.org/10.1073/pnas.2422633122) (accessed 2026-10-09) 3. [Mayer, R. E., & Moreno, R. (2003). Nine Ways to Reduce Cognitive Load in Multimedia Learning. Educational Psychologist, 38(1), 43-52.](https://doi.org/10.1207/S15326985EP3801_6) (accessed 2026-10-09) 4. [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.](https://doi.org/10.1207/s1532690xci0201_3) (accessed 2026-10-09) 5. [Roediger, H. L., & Karpicke, J. D. (2006). Test-Enhanced Learning: Taking Memory Tests Improves Long-Term Retention. Psychological Science, 17(3), 249-255.](https://doi.org/10.1111/j.1467-9280.2006.01693.x) (accessed 2026-10-09) 6. [Chi, M. T. H., De Leeuw, N., Chiu, M.-H., & Lavancher, C. (1994a). Eliciting Self-Explanations Improves Understanding. Cognitive Science, 18(3), 439-477.](https://doi.org/10.1207/s15516709cog1803_3) (accessed 2026-10-09) 7. [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.](https://doi.org/10.1037/0033-2909.132.3.354) (accessed 2026-10-09) ## Keep reading ### Research: a tutor built on learning science How DuckyHelper's tutor is built to teach: the model, a library of 100+ learning-science papers, the principles it follows and our white papers. ### How people learn: 12 principles Twelve learning-science principles behind DuckyHelper, from one-on-one tutoring to spacing, each with the research and the tutor behaviour it drives. ### The learning-science library: 100+ papers 100+ real learning-science papers behind DuckyHelper, sorted by principle, each with a citation, a link to the publisher and a one-line summary. ### Built to teach: learning science in a voice tutor White paper: how DuckyHelper's tutor turns ten findings from learning science into teaching rules and tools, and the limits of that work. ### What 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. ### Every DuckyHelper feature: what it does, where it runs, and a short film of each What DuckyHelper for Mac does: Eddy teaches out loud on a blackboard, and Ducky sees your screen, draws on it and walks you through your own apps. ## Ready to learn DuckyHelper is ready on your Mac. Learn with Eddy on its blackboard, or with Ducky right on your screen. [Download for Mac](https://duckyhelper.com/download/) [See what it does](https://duckyhelper.com/features/) The Mac app needs Apple silicon and macOS 14 Sonoma or later. There is no Chromebook, Windows or web version right now.