2 Introduction The literature on creativity and innovation consistently highlights three keys to generating good ideas: producing many ideas, producing ideas of generally high quality, and, notably, the cultivation of ideas with higher variance (Girotra et al 2010). The third driver, the concept of high variance, is particularly emphasized in the innovation community. It is captured in popular recommendations such as “think outside the box” (Young 1965), “encourage wild ideas” (Osborn 1948, Kelley and Littman 2001), or “explore the blue ocean” (Kim and Mauborgne 2005). Drawing on this perspective, idea generation can be conceptualized as exploring a highly complex solution landscape with vastly different values associated with each point in the landscape (Levinthal and March 1993, Sommer and Loch 2004). Especially if this solution landscape is rugged, any attempt of deriving an optimal solution through synthesis is likely to fail. Instead, a broad exploration of different regions of the solution landscape is called for. If this exploration is done through trial-and-error, as it tends to be the case in the field of creativity and innovation, it is thus imperative that the set of trials (the pool of ideas that are considered) be as diverse as possible. Across the fields of computer science, entrepreneurship, and psychology, there exists an exploding interest in using AI to generate ideas and to alter and augment the practice of brainstorming. However, despite the ability of AI systems to dramatically increase the productivity and quality of the idea generation process, they appear to grapple with creating a wide dispersion of ideas (i.e., ideas are too similar to each other, see Dell'Acqua et al 2023), which inherently limits the novelty (Girotra et al 2023) of the ideas, the variance of the idea quality, and ultimately, and most importantly, the quality of the best ideas. The apparent lack of dispersion in a set of AI generated ideas motivates our main research question we aim to address in this paper. How might one increase the diversity of an AI generated pool of ideas? Since our primary focus is on AI in the form of large language models (LLMs), increasing the diversity of a pool of ideas boils down to a matter of prompt engineering. We thus refine our research question to: How might one choose prompts in LLMs to increase the diversity of an AI generated pool of ideas? To find out what prompts lead to the most diverse idea pools, we compare multiple prompting strategies. This includes (1) minimal prompting, (2) instructing the LLM to take on different personas, (3) sharing creativity techniques from the existing literature with the LLM, and (4) Chain of Thought (CoT) prompting which asks the LLM to work in multiple, distinct steps. As