In a usability study, 12 U.S. STEM teachers rated all generated learning interactives 7 or above for usability, averaging above 8.1, with 3 of 36 requests deemed too low quality to present¶
Claim · All claims
Evidence · 1 study · designr2·q2
Currency · newest study 2026 · not yet checked against its sources · not reviewed by a person · recheck by 2029: tool and model accuracy changes quickly
Subclaims¶
Reading the evidence codes
q is the design tier, i the impact, n the sample, and the kind with its r
the rigour judged within that kind: what each code means.
This claim: no standardized effect is recorded in observations/ for it yet, so no benchmark reading is possible.
q2 i? Teachers creating three simulation requests each (36 total) rated all resulting interactives 7 or above on usability, with an average above 8.1. → Alisa Kovshov 2026
Evidence¶
Alisa Kovshov 2026¶
Alisa Kovshov, Anisha Choudhury, Anna Iurchenko, Amy Keeling, Avinatan Hassidim, Ayelet Shasha Evron, Ayça Çakmakli, Diana Akrong, Femi Olanubi, Gal Elidan, Ian Li, Ido Lerer, Katherine Chou, Lidan Hackmon, Michal Gordon, Nir Kerem, Niv Efron, Preeti Singh, Rena Levitt, Rotem Yulzary, Shlomi Ben Shimon, Sophie Allweis, Tracey Lee-Joe, Tzvika Stein, Yaniv Carmel, Yael Haramaty, Yishay Mor, Yossi Matias and Yuri Lev. (2026). Harnessing Generative UI for Education: Tailored Learning Interactives. Google Research. https://arxiv.org/abs/2609.20738 doi:10.48550/arxiv.2609.20738
q2 · i? · design · r2
Teacher usability study in which 12 U.S. STEM teachers (6 male, 6 female) each created three simulation requests, for 36 requests total. Ratings were on a usability scale where "an average rating of above 8.1, corresponding to good usability" was achieved.
"Overall reception was quite positive with teachers rating all simulations as 7 or above in terms of usability with an average rating of above 8.1, corresponding to good usability"
Discussion¶
Related Claims¶
- Independent expert teachers accepted 86% of generated STEM learning interactives, rating most as good or excellent, with biology simulations weakest on aesthetics and UX — related
- Iterative generate-then-refine with multi-axis critiques raises the share of usable generated simulations from 3.5% after first generation to 69.3% after 10 improvement rounds — related
- Teachers rate LearnLens positively across usability, relevance, and accuracy, with all nine Likert items averaging at least 4.1/5 — related
- Learner acceptance of AI simulations is generally high, with System Usability Scale scores of 61.6 to 78.56 and 72%-93% willingness to recommend — related
Page metadata
| Field | Value |
|---|---|
type |
claim |
id |
teacher-usability-study-average-rating-above-8-1 |
title |
In a usability study, 12 U.S. STEM teachers rated all generated learning interactives 7 or above for usability, averaging above 8.1, with 3 of 36 requests deemed too low quality to present |
description |
In a usability study, 12 U.S. |
status |
review |
evidence_strength |
moderate |
newest_evidence |
2026 |
recheck_by |
2029 |
generated |
by process:wiki-ingest on 2026-10-10 |
trust |
unverified — no one has confirmed this page's content |
sources |
1 — alisa-kovshov-2026 |
Frontmatter is the page's machine-readable record — see the Schema & Guide.