In a self-selected survey, students favored delayed disclosure and agency, but 39.3% found the system too indirect and 42.9% reported repetition¶

Claim · All claims
Evidence · 1 study (2 entries) · design r2 · q2
Currency · newest study 2026 · not yet checked against its sources · not reviewed by a person

Subclaims¶

q2 i? Among 28 survey respondents, 18 (64.3%) agreed they could make their own design decisions and 21 (75.0%) disagreed that the system revealed too much information too early. → Sara Riazi and Pedram Rooshenas 2026 q2 i? Eleven of 28 respondents (39.3%) found the system too indirect when they needed a more explicit answer, and 12 of 28 (42.9%) reported repeated questions or explanations. → Sara Riazi and Pedram Rooshenas 2026 (2)

Evidence¶

Sara Riazi and Pedram Rooshenas 2026¶

Sara Riazi and Pedram Rooshenas. (2026). An Educator-Guided LLM Pedagogical Agent for Scaffolded Feedback in Conceptual Database Design. https://arxiv.org/abs/2610.00870 doi:10.48550/arxiv.2610.00870

q2 · i? · design · r2

Optional, ungraded survey of 63 enrolled students; 31 responded, one excluded, leaving at most 30 system users (47.6% of enrollment). The article reports "18 of 28 respondents (64.3%)" and "21 of 28 (75.0%)" from this self-selected sample.

"Eighteen of 28 respondents (64.3%) agreed that they could make their own design decisions, and 21 of 28 (75.0%) disagreed that the system revealed too much information too early."

Sara Riazi and Pedram Rooshenas 2026 (2)¶

Sara Riazi and Pedram Rooshenas. (2026). An Educator-Guided LLM Pedagogical Agent for Scaffolded Feedback in Conceptual Database Design. https://arxiv.org/abs/2610.00870

q2 · i? · design · r2

Same self-selected survey; the article reports "39.3% found the system too indirect" and "42.9% reported repeated questions or explanations", with open-ended responses requesting more localized guidance and less repetition.

"Eleven of 28 respondents (39.3%) found the system too indirect when they needed a more explicit answer, and 12 of 28 (42.9%) reported repeated questions or explanations."

Discussion¶

Related Claims¶

• Qualitative analysis found staged disclosure sometimes withheld inaccurate diagnostic details, but some errors still shaped student revisions — related
• In the AVP, per-turn disclosure change responds to trainee exploration but not measurably to trainee empathy, and the static baseline shows no significant joint response — related
• Most learners disregarded the system's learning and repetition recommendations, with self-regulated decision-making taking precedence over the suggested path — related