Use AI chatbots as one-shot generators of candidate cooperative learning techniques, then select via a researcher-built rubric¶

Strategy · All strategies
Evidence · no claims cited

Description¶

The article demonstrates a human-AI workflow in which the researcher prompts multiple AI chatbots once with course content and cooperative learning principles, then evaluates the generated proposals against predetermined criteria. "Two key documents were prepared and presented to five different artificial intelligence (AI) chatbots (ChatGPT, Copilot, DeepSeek, Gemini, and Qwen)." Proposals were scored on novelty, alignment with cooperative learning principles, course-context fit, and clarity/practicality; "Based on this systematic evaluation, Qwen's CCCT was selected for experimental implementation."

Design Implications¶

Context¶

Requirements¶

• Comprehensive prompt documents describing course content, learner characteristics, and cooperative learning elements and techniques; a predetermined evaluation rubric; human researcher retains selection, adaptation and implementation decisions

Constraints¶

• The process was a single prompt per chatbot rather than iterative co-design; the article characterizes the AI's role as "AI-generated" or "AI-assisted generation" rather than co-design

Target Learners¶

• teacher educators and instructional designers developing techniques for higher education courses

Target Learning Goals¶

• designing tailored cooperative learning techniques aligned with course content and learner characteristics

Related Strategies¶

• Translate deductive coding rubrics into structured zero-shot prompts to compare LLM coding against human coding

Examples¶

-

Key Sources¶

• Özgür Tutal. (2026). Artificial intelligence assisted design of a novel cooperative learning technique for higher education. Scientific Reports. https://doi.org/10.1038/s41598-026-50770-1