Introductory programming courses often require students to solve many small programming exercises as part of their learning. Researchers have previously suggested that the context used in the problem description for these exercises is likely to impact student engagement and motivation. Furthermore, supplying programming exercises that cover a broad range of contexts, or even allowing learners to select contexts to personalise their own exercises, may support the interests of a diverse student population. Unfortunately, it is very time-consuming for instructors to create large numbers of programming exercises that target a wide range of contextualised problems. However, recent work has shown that large language models may have the potential to automate the mass production of programming exercises, reducing the burden on instructors. In this research, we explore the potential of OpenAI’s GPT-4 to create high-quality and novel programming exercises that are thematically aligned to specified contexts. We employ prompt engineering to compare distinct strategies for generating many programming exercises with various contextualised problem descriptions and we then evaluate the quality of the exercises generated.