While there exist several tools to leverage Large Language Models (LLMs) for code generation, their capabilities are limited to the source code editor and are disconnected from the overall software development process. These tools typically generate standalone code snippets that still require manual integration into the codebase. There is still a lack of integrated solutions that seamlessly automate the entire development cycle, from backlog items to code generation and merge requests. We present the Pipeline for Automated Code Generation from Backlog Items (PACGBI), an LLM-assisted pipeline integrated into GitLab CI. PACGBI reads backlog items in the code repository, automatically generates the corresponding code, and creates merge requests for the generated changes. Our case study demonstrates the potential of PACGBI in automating agile software development processes, allowing parallelization of development and reduction of development costs. PACGBI can be utilized by software developers and enables nontechnical stakeholders and designers by providing a holistic solution for using LLMs in software development. A screencast of this tool is available at https://youtu.be/TI53m-fIoyc, its source code at https://github.com/Masa-99/pacgbi.

Current approaches to model-driven development of web applications focus on traditional, hypertext-based web applications. Consequently, their models mainly address the aspects hyptertext structure and navigation paths of the web application. The presentation aspect, however, is supported only in a rather abstract manner, in particular, modeling the different states of the HTML elements is not supported. Therefore, while useful for their intended purpose of modeling traditional, thin-client applications, these approaches are not quite suitable for designing modern Single Page Applications (SPAs), whose functionalities are reflected by changes of their HTML elements’ properties and dependencies between them rather than by hypertext structures and navigation paths. In the realm of SPAs, modeling, formal model validation, and code generation need better support.In this paper, we present an approach to modeling SPAs with UML state machines and translating these to JavaScript controller code as well as to the formal specification language Maude. Also, we demonstrate how the formal model can be used to verify the modeled system. Our approach thus provides an intuitive, easy-to-use, and yet powerful means to model-driven development of SPAs.