AI-powered teaching, origami design, and fish biology strategies

Your new Strategy Toolkit newsletter (May 5, 2025)

(1) Tutor is my co-pilot

In the wonderful world of AI experimentation, it’s great to discover studies such as the work* of Stanford University’s Rose Wang and team. Using known effective strategies from experienced tutors, Wang created a remote tutoring application based on GPT-4 to provide online tutors with real-time assistance while on the job. The results from running a wide-ranging experiment with elementary math tutors are encouraging and worth exploring further.

“When a student makes an error, according to previous work by some of the same authors, effective teachers choose a strategy for addressing the mistake. The authors identified 11 strategies, such as ask a question, explain a concept, provide a hint, or encourage the student. Moreover, they found that an LLM that executed a strategy chosen by an expert teacher performed significantly better than an LLM that was prompted with a strategy chosen at random or no specific strategy. Letting inexperienced tutors choose a strategy while an LLM generates a response helps them learn how to execute the strategy. Students, in turn, benefit from responses that mimic those of an experienced teacher.”**

* Wang, R., et al “Tutor CoPilot: A Human-AI Approach for Scaling Real-Time Expertise,” arXiv; https://doi.org/10.48550/arXiv.2410.03017

** “LLM Support for Tutors,” The Batch (March 26, 2025); https://www.deeplearning.ai/the-batch/issue-294/