Design AI feedback and task scope to leave room for open-ended creative exploration¶

Strategy · All strategies
Evidence · 2 claims (1 for, 1 mixed) · 2 studies (1 causal, 1 review), q3 · 0 of 2 report an effect size · 2 claims rest on one study

Description¶

Because GPT feedback's impact on creativity was limited, the article points to the "directive nature of GPT feedback or the structured scope of learning tasks, which may not have encouraged open-ended creative exploration." The implementable move for designers is to loosen the directiveness of AI feedback and widen the task scope so learners can explore creatively rather than only follow directed corrections.

Design Implications¶

Context¶

Requirements¶

• Learning tasks and AI feedback that permit open-ended learner exploration rather than only directive correction

Constraints¶

• Applies to creativity outcomes; the study's structured, Bloom-aligned IoT units did not produce creativity gains

Target Learners¶

• undergraduate students

Target Learning Goals¶

• creativity
• higher-order thinking skills

Claims¶

• GPT feedback in VR markedly improved problem-solving and critical thinking but had limited impact on creativity [+W]
• Overreliance on AWE may lower learners' critical thinking and creativity [~W]

Related Strategies¶

• Discourage mental offloading to AI by balancing guidance depth and frequency with application opportunities

Examples¶

-

Key Sources¶

• Wang, W.-S., Lin, C.-J., Lee, H.-Y., Huang, Y.-M., & Wu, T.-T. (2025). Enhancing self-regulated learning and higher-order thinking skills in virtual reality: the impact of ChatGPT-integrated feedback aids. Education and Information Technologies, 30, 19419–19445. https://doi.org/10.1007/s10639-025-13557-x