Use structured initial prompts and iterative optimization when generating lesson plans with ChatGPT¶

Strategy · All strategies
Evidence · no claims cited

Description¶

The article proposes key methods for AI-assisted lesson planning, highlighting steps in generating lesson plans and searching for multimedia resources, supported by a prompt framework with structured initial prompts and iterative optimization based on evaluation dimensions. The article motivates this by noting that "Poorly constructed prompts can yield vague or irrelevant results, reducing the tool's practical utility and user experience." Teachers should structure initial prompts around lesson theme, objectives, content, methods, and resources, then iteratively refine outputs against evaluation dimensions.

Design Implications¶

Context¶

Requirements¶

• Access to ChatGPT (GPT-4o) and a structured prompt framework covering theme determination, plan generation, design optimization, and content filling.

Constraints¶

• The article notes that even with structured prompting, ChatGPT outputs may remain impractical, unsafe, or repetitive and require teacher filtering and revision.

Target Learners¶

• Children's art teachers of students aged 6-12 (K1-K6)

Target Learning Goals¶

• Efficient, high-quality lesson planning for STEAM art education

Related Strategies¶

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

Examples¶

-

Key Sources¶

• Zhihua Luo and Rabail Tahir. (2025). ChatGPT-Assisted Lesson Planning for Children's STEAM Arts Education: An Experimental Study on Benefits, Challenges, Methods, and a Prompt Framework. International Journal of Artificial Intelligence in Education. https://doi.org/10.1007/s40593-025-00513-6