The effect of context awareness on perceived task-completion support depends on the pedagogical guidance style it is paired with¶

Claim · All claims
Evidence · 1 study · causal r2 · q3
Currency · newest study 2026 · not yet checked against its sources · not reviewed by a person

Subclaims¶

q3 i? Interaction-pattern evidence from Figure 2 shows Direct-guidance conditions were rated similarly for task-completion support regardless of context, while with Socratic guidance, full context reduced perceived support for task completion. → Madeleine Eastwood 2026

Evidence¶

Madeleine Eastwood 2026¶

Madeleine Eastwood, Harshith Narne, Joseph Hilby, Paul Denny, Ashish Aggarwal, and Amanpreet Kapoor. (2026). Guardrails or Roadblocks? Effects of Pedagogical Style and Context Awareness in AI Teaching Assistants for Programming. https://arxiv.org/abs/2609.29995 doi:10.48550/arxiv.2609.29995

q3 · i? · causal · r2

Authors' interpretation of the interaction plots in Figure 2 (mean ratings by context awareness and guidance style, N=132) from the randomized experiment, indicating "context awareness was not uniformly beneficial" and its effect depended on the paired pedagogical style.

"When Direct guidance was available, students rated the chatbot similarly for supporting task completion regardless of how much context was provided. In contrast, when the chatbot was Socratic, providing full context reduced students' perceived support for task completion."

Discussion¶

Related Claims¶

• Contingent scaffolding improves learning more than fixed or absent support. — the general claim this finding bears on, with the studies behind it
• Students rate the Socratic + Full Context AI TA significantly lowest for perceived support of task completion — related
• AI TA condition shows no statistically significant differences in perceived task-comprehension support, correctness, or interaction stress — related
• Direct conditions descriptively show higher post-task full comprehension than Socratic conditions, with Direct + Full Context highest and Socratic + Full Context lowest — related
• 15% of students used an external LLM, with the highest descriptive rate in the Socratic + Full Context condition, mainly citing inadequate guidance — related