Innovations in computational methodologies have significantly transformed the landscape of scientific research, in silico experiments have replaced some of the physical experiments. ChemFlow, a novel proof-of-concept platform introduced in this paper, coalesces these advancements by automating the creation of workflows. Designed specifically for the bioinformatics field, ChemFlow leverages Large Language Models and prompt engineering techniques to interpret natural language descriptions and convert them into executable workflows without the need for manual coding. Our contributions are two-fold: first, we introduce an innovative workflow generation and execution platform with the help of large language models, and second, we introduce a novel set of prompt optimisation strategies that improve both the accuracy and efficiency of the generated workflows. ChemFlow enables researchers to focus on domain-specific challenges rather than computational intricacies, making it a pivotal tool for advancing scientific productivity and innovation.