The rapid rise in popularity of Generative AI and Large Language Models (LLMs) has brought both innovation and controversy, particularly regarding plagiarism and IP law infringements. However, one underexplored concern is the generation of code by these models, which, despite their potential, often includes errors and promotes poor programming practices. This paper explores new methods to address these issues by integrating LLMs with Automated Machine Learning (AutoML). By leveraging AutoML’s capabilities in hyperparameter tuning and model selection, we propose a novel approach for generating robust machine learning algorithms. This integration aims to enhance the accuracy and reliability of code generation while mitigating legal risks. Our findings include the application of Natural Language Processing (NLP) and Natural Language Understanding (NLU) techniques to interpret chatbot prompts, thereby improving the generation and customization of machine learning models. The proposed methodology demonstrates practical implementation and high prediction accuracy, offering a promising solution to the current challenges faced by LLM-based code generation. In summary the findings of the paper are as follows: A new implementation of natural language processing for natural language understanding in the context of chatbot prompts aims to serve as an initial step for feature extraction, which will be utilised by an AutoML system to generate machine learning algorithms.