Educators gamify learning materials or create learning games using generative AI with iterative, phased prompting¶

Strategy · All strategies
Evidence · 3 claims (2 for, 1 mixed) · 1 study (1 theoretical), q1 · 0 of 1 report an effect size · 3 claims rest on one study

Description¶

The article proposes that teachers use LLMs and generative AI to gamify teaching or generate learning games, for instance by supporting generation of artwork, code, or game levels, or adapting popular board games such as Monopoly for specific learning purposes. Because game design is complex, it is important to break complex prompts into a series of small, specific steps and phases, using techniques such as chain-of-thought prompting or role prompting to enhance output quality.

Design Implications¶

Context¶

Requirements¶

• A playful, experimental, and iterative style of engagement in which game makers continually reassess goals and explore new solutions based on generated outputs.

Constraints¶

• Successful generation of games with LLMs requires prompting skill and critical evaluation of generated outputs, which tinkering might enhance.

Target Learners¶

• educators and teachers developing game-based learning materials

Target Learning Goals¶

• creation of engaging game-based learning materials for subject-matter learning

Claims¶

• Optimizing prompts can vastly improve the accuracy of LLM outputs, but critical evaluation of the resulting outputs still requires domain expertise. [+W]
• LLM output can be misleading or erroneous because a stochastic element in text generation sometimes selects less likely continuations, so it requires continuous supervision and critical evaluation by domain experts. [~W]
• Well-designed games can promote persistence in practice and high-quality engagement, and when basic needs of autonomy, competence, and relatedness are met, learning becomes its own reward, reducing the temptation to outsource cognitive effort to LLMs. [+W]

Related Strategies¶

• Learning by generating games with LLMs, supported by prompting pedagogy
• Teachers iteratively refine LLM-simulated student ideas with classroom context before instructional use
• Co-create micro-intervention repertoires with generative AI through a seed-request-refine prompt sequence, with the instructor curating output
• Phase-aligned teaching applications for LLM-supported learning across five phases
• Treat AI-generated lesson plans as drafts requiring teacher evaluation, adaptation, and pedagogical judgment
• Use generative AI as a brainstorming partner for divergent ideation while treating didactic transformation as a human responsibility
• Use structured initial prompts and iterative optimization when generating lesson plans with ChatGPT

Examples¶

-

Key Sources¶

• Huber, S. E., Kiili, K., Nebel, S., Ryan, R. M., Sailer, M., & Ninaus, M. (2024). Leveraging the Potential of Large Language Models in Education Through Playful and Game-Based Learning. Educational Psychology Review. https://doi.org/10.1007/s10648-024-09868-z