The increasing demand for data scientists has highlighted the need for up-skilling and efficient tools in the field. Generative AI offers a promising so-lution for automating coding tasks and enhancing productivity. This paper investigates the effectiveness of prompt engineering techniques for code generation in data science applications using Google’s Gemini large language model (LLM). By examining the quality of AI-generated code for tasks such as data cleaning, exploratory data analysis (EDA), and machine learning model building, this study aims to identify best practices for prompt engi-neering and contribute to a better understanding of how to effectively utilize generative AI models for code generation in the data science field. The study analyzes the accuracy and efficiency of the generated code, as well as its ability to handle complex data science tasks. Findings suggest that prompt engineering plays a crucial role in shaping the quality and effectiveness of AI-generated code, and that generative AI has the potential to significantly accelerate data science workflows.