Prompt Potential: A Pilot Assessment of Using Generative Artificial Intelligence (ChatGPT-4) as a Tutor for Engineering and Maths

The meteoric rise of GenAI has caused many educators to be consternated by its potential to undermine assessment. However, there is a more optimistic view to instead focus on the pedagogical affordances that GenAI can bring, for example, in tailoring personalised learning experiences for students. In this pilot study, we investigate ChatGPT-4's potential to act as a one-on-one tutor for engineering and mathematical concepts. We use three research-informed prompt strategies and simulate interactions with high-, mid-, and low-performing students. We find that the learning experience is best tailored to high-performing students. However, to gain comfort in using it, the experience must be error-free. We discovered performance varied by topic, but there indeed are topics that ChatGPT-4 can engage with error-free or with a slight chance of errors.