Abstract
Prompt engineering plays a pivotal role in effective interaction with large language models (LLMs), including ChatGPT. Understanding user intent behind interactions with LLMs is an important part of prompt construction to elicit relevant and meaningful responses from them. Existing literature sheds little light on this aspect of prompt engineering. Our study seeks to address this knowledge gap. Using the example of building a chatbot for startup teams to obtain better responses from ChatGPT, we demonstrate a feasible way of classifying user intent automatically using ChatGPT itself. Our study contributes to a rapidly increasing body of knowledge of prompt engineering for LLMs. Even though the application domain of our approach is startups, it can be adapted to support effective prompt engineering in various other application domains as well.