In preliminary user acceptance testing, 84% of participants rated Taklif.AI's personalization feature as beneficial¶

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

Subclaims¶

q2 i? In preliminary user acceptance testing with 68 participants, 84% (57/68) rated the personalization feature as beneficial, with engagement and future-use items scoring at least 4 on a 5-point scale. → Zaki Kurdya 2026

Evidence¶

Zaki Kurdya 2026¶

Zaki Kurdya, Mohammed Zuqlam, Salem Amassi, Shady Telbany, Motaz Saad. (2026). Taklif.AI: LLM-Powered Platform for Interest-Based Personalized College Assignments. https://arxiv.org/abs/2605.05842 doi:10.48550/arxiv.2605.05842

q2 · i? · design · r2

Preliminary user acceptance testing at the Islamic University of Gaza with 68 participants (65 undergraduate students, 3 educators), each personalizing at least one assignment after a 2-minute introduction and completing a structured questionnaire. The reported result is that "84% of participants (57/68) rated the personalization feature as beneficial". No effect size is printed.

"84% of participants (57/68) rated the personalization feature as beneficial (items 1 and 4 scored≥4)."

Discussion¶

Related Claims¶

• 91% of UAT participants rated the Taklif.AI user interface as intuitive — related
• Under a simulated load of 100 concurrent users, Taklif.AI averaged 30 seconds end-to-end response time per request — related
• During development testing, Taklif.AI guardrails rejected roughly 12% of interests, 8% of input documents, and 3% of generated assignments — related
• Teachers rate LearnLens positively across usability, relevance, and accuracy, with all nine Likert items averaging at least 4.1/5 — related