LLM assisted web application functional requirements generation: A case study of four popular LLMs over a Mess Management System

TL;DR

This study compares four popular LLMs in generating functional requirements for a web application, assessing their accuracy, completeness, and consistency in producing use cases, business rules, and workflows.

Contribution

It provides a comparative analysis of LLMs' effectiveness in generating software requirements, highlighting their strengths and limitations in a practical case study.

Findings

Claude produced the most complete specifications.

Gemini was more precise in its outputs.

All LLMs struggled with generating relevant business rules.

Abstract

Like any other discipline, Large Language Models (LLMs) have significantly impacted software engineering by helping developers generate the required artifacts across various phases of software development. This paper presents a case study comparing the performance of popular LLMs GPT, Claude, Gemini, and DeepSeek in generating functional specifications that include use cases, business rules, and collaborative workflows for a web application, the Mess Management System. The study evaluated the quality of LLM generated use cases, business rules, and collaborative workflows in terms of their syntactic and semantic correctness, consistency, non ambiguity, and completeness compared to the reference specifications against the zero-shot prompted problem statement. Our results suggested that all four LLMs can specify syntactically and semantically correct, mostly non-ambiguous artifacts. Still, they may be inconsistent at times and may differ significantly in the completeness of the generated specification. Claude and Gemini generated all the reference use cases, with Claude achieving the most complete but somewhat redundant use case specifications. Similar results were obtained for specifying workflows. However, all four LLMs struggled to generate relevant Business Rules, with DeepSeek generating the most reference rules but with less completeness. Overall, Claude generated more complete specification artifacts, while Gemini was more precise in the specifications it generated.