Feedback right away, on the step
Feedback is one of the strongest influences on learning, but its kind matters: feedback about the task and the next step helps, feedback about the person can backfire. Kluger and DeNisi (1996) found over 38% of feedback effects were negative. Good feedback is timely and specific. DuckyHelper checks each step as you go and points at the exact place something went wrong.
“FI effectiveness decreases as attention moves up the hierarchy closer to the self and away from the task”
Feedback on the step, right away
In the film, a wrong quiz answer gets "Not quite" and a one-line why. The feedback is about the work, and it comes while you are still on it:
- Not quite, and why (Mac and web)
- The first wrong line (Mac app)
- On the step, on your screen (Mac app)
- Every step checked (Mac app)
- About the work, not about you (Mac and web)
What the research found
Feedback is one of the most powerful influences on learning and achievement
(Hattie & Timperley, 2007)
John Hattie and Helen Timperley's review says good feedback answers three questions: where am I going, how am I going, and where to next. Valerie Shute's review of formative feedback adds how to deliver it:
formative feedback should be nonevaluative, supportive, timely, and specific
(Shute, 2008)
Feedback is not automatically good. In a large meta-analysis, Avraham Kluger and Angelo DeNisi found a moderate average benefit, but over 38% of the effects were negative. The pattern, in their words: feedback works less well “as attention moves up the hierarchy closer to the self and away from the task.”
In other words, "you're bad at math" hurts; "this minus sign flipped" helps. Computer tutors that gave immediate, short feedback on each step worked well. The Cognitive Tutors' authors reported that the best style was one in which
the tutor provides immediate feedback, consisting of short and directed error messages
(Anderson et al., 1995)
and that in the best cases, students reached the same level as conventional instruction in one third of the time. A randomized trial with 2,850 seventh graders found online homework with timely feedback and hints raised end-of-year math scores (Roschelle et al., 2016).
Feature by feature
Not quite, and why
Quiz answers get Correct, or "Not quite" with a one-sentence why. Wrong choices in a quiz are the real mistakes learners make, so the why is about your actual slip. Mac and web.
The first wrong line
"Is this right?" In the Mac app, a computer algebra check goes through your math line by line and names the first wrong line and why. Mac app.
On the step, on your screen
Ducky circles the exact spot on your own page and writes a note beside your line. It tells you what you got right first, then shows you the one step that went wrong. Mac app.
Every step checked
Tutorials in your own apps move on only when you really did the step. The typing coach marks a wrong letter red, under that letter, as you type. Mac app.
About the work, not about you
It praises your effort and the good moves you made. The Mistakes page calls them "Slips Ducky noticed, not scores." Mac and web.
What this page does not claim
These studies tested other people, other schools and other tools. DuckyHelper has not been tested in a study like these, so none of these results are DuckyHelper's results. They are the reasons behind how it teaches.
The papers on this page
Using Large Language Models to Assess Tutors' Performance in Reacting to Students Making Math Errors
Frequently asked questions
What makes feedback effective?
Research reviews point to feedback that is about the task, specific, and timely, and that tells the learner where they are going, how they are doing and what to do next (Hattie and Timperley, 2007; Shute, 2008).
Can feedback hurt learning?
Yes. Kluger and DeNisi (1996) found over 38% of feedback effects in their meta-analysis were negative, especially when feedback drew attention to the person rather than the task.
Does DuckyHelper tell me exactly where I went wrong?
Yes. Quizzes explain each miss, the Mac app's math check names the first wrong line, and Ducky can circle the spot on your own page. It points at where to look and leaves the fix to you.
Sources
- Hattie, J., & Timperley, H. (2007). The Power of Feedback. Review of Educational Research, 77(1), 81-112. (accessed 2026-10-09)
- Shute, V. J. (2008). Focus on Formative Feedback. Review of Educational Research, 78(1), 153-189. (accessed 2026-10-09)
- Kluger, A. N., & DeNisi, A. (1996). The effects of feedback interventions on performance: A historical review, a meta-analysis, and a preliminary feedback intervention theory. Psychological Bulletin, 119(2), 254-284. (accessed 2026-10-09)
- Anderson, J. R., Corbett, A. T., Koedinger, K. R., & Pelletier, R. (1995). Cognitive Tutors: Lessons Learned. Journal of the Learning Sciences, 4(2), 167-207. (accessed 2026-10-09)
- Wisniewski, B., Zierer, K., & Hattie, J. (2020). The Power of Feedback Revisited: A Meta-Analysis of Educational Feedback Research. Frontiers in Psychology, 10, 3087. (accessed 2026-10-09)
- Black, P., & Wiliam, D. (1998). Assessment and Classroom Learning. Assessment in Education: Principles, Policy & Practice, 5(1), 7-74. (accessed 2026-10-09)
- Roschelle, J., Feng, M., Murphy, R. F., & Mason, C. A. (2016). Online Mathematics Homework Increases Student Achievement. AERA Open, 2(4), 2332858416673968. (accessed 2026-10-09)
- Daheim, N., Macina, J., Kapur, M., Gurevych, I., & Sachan, M. (2024). Stepwise Verification and Remediation of Student Reasoning Errors with Large Language Model Tutors. EMNLP. (accessed 2026-10-09)
- Kakarla, S., et al. (2024). Using Large Language Models to Assess Tutors' Performance in Reacting to Students Making Math Errors. AAAI Workshop on AI for Education. (accessed 2026-10-09)
Related principles
Ready to learn
DuckyHelper is ready on your Mac. Learn with Eddy on its blackboard, or with Ducky right on your screen.
