Aug 2026· Economic Sciences· 0 citations· 11 references
TL;DR
The paper is trying to deeply analyze the pros and cons of implementing GenAI into software development, analysing current applications used in software development life cycle (SDLC), drawing upon case studies and programmer experience, and examining effect on code quality, team working and project timeline.
Abstract
Integrating GenAI into the software development lifecycle represents a critical advancement for current application development practices, development and maintenance. AI tools such as ChatGPT, Copilot, GitHub and Amazon CodeWhisperer tools are used by the engineers to automate routine tasks such as generation of code segments, documentation and assistance with debugging and test case creation. These functions are also to help engineer to be more efficient and to minimize the difficulty for junior level software developers to join the development. To provide ready access to information and help during development. While on the one hand it is useful but also it has its share of problems. Dependency on AI generated code is not yet considered to be secured. These are particularly used in the most critical systems where minor error may put big safety issue. There are significant concerns about intellectual property, originality of code and data privacy. Many GenAI models rely on data from openly available resources, where copyrights and sensitive information could be incorporated, as well as concern over engineers depend on AI. This can impact the fundamental problem solving capabilities of engineers and innovation will decrease. The paper is trying to deeply analyze the pros and cons of implementing GenAI into software development, analysing current applications used in software development life cycle (SDLC), drawing upon case studies and programmer experience, examining effect on code quality, team working and project timeline.This paper offers guidance in right implementation, identifying and outlining the best practice methods when integrating AI tools into software development. Examining both the opportunities and drawbacks of GenAI allows for greater understanding of how modern tools can be best utilized within the context of academic research and enterprise IT applications.
In software development, AI has become a tool with a wide range of capabilities, from generating code to helping with debugging and even writing documentation. Still, a major puzzle for developers is that the outputs coming from AI can be quite inconsistent and also unpredictable at times. And this is primarily because inputs from developers are usually vague or unstructured. This also means that the role of well-crafted instruction files is absolutely essential in determining the behavior of AI that is reliable and also aware of the context. These instruction files that are structured serve as the medium that connects what a developer wants with what an AI is going to do. They make sure that things are crystal clear, that actions can be done again, and that everything is in line with the standards of the project. Otherwise, using AI may result in outputs that differ not only in the quality but also in the style and correctness, which may cause wastage of time and lessened faith in their usefulness. This article presents a well-organized methodology for crafting and handling instruction files so as to achieve a higher level of uniformity and efficiency in AI-supported developers' operations. By making inputs consistent and incorporating constraints specific to the domain in issue, developers are able to majorly upgrade the quality of their output and at the same time minimize their number of iterations. Studies have shown that through investing in designing strong instructions one not only gets the best out of AI but also is able to facilitate cross-team collaboration more effectively. At the end of the day use of instruction files that are structured is a key element to changing the nature of AI from just being an aid to becoming a reliable partner in the field of software engineering of today.
Madhurima Kommuru· International Journal of Art...· 0 citations
Overall, this survey provides a structured characterization of the current state of AIware testing research and identifies key structural challenges that must be addressed to support lifecycle-aware, reliable AIware systems.
K. Gonzalez, Mariam El Mezouar· AIware· 0 citations
The growing adoption of Large Language Models (LLMs) in Software Engineering has reinforced the expectation that coding activities can be largely automated. However, this perception may represent yet another historical search for a solution capable of eliminating the inherent challenges of software development. This article discusses the transition from a code-centered paradigm to Specification-Driven Development. We argue that artificial intelligence reduces some of the effort associated with writing source code, but it does not eliminate the complexity of developing professional software systems. Instead, it shifts this complexity toward domain understanding, requirements elicitation, specification development, validation, maintenance, and software evolution. Building on this perspective, we discuss the renewed centrality of Requirements Engineering, considering its implications for productivity and software quality, as well as risks associated with automation bias, ambiguity propagation, Specification Overfitting, and the accumulation of Specification Debt. Finally, we propose the Specification Paradox: the more capable artificial intelligence systems become at automatically generating software, the greater the dependence on correct, complete, verifiable, and explainable human-produced specifications. We conclude that the future of Software Engineering will depend not only on machines'ability to generate code, but also on humans'ability to correctly specify, evaluate, and evolve what is intended to be built.
Traceability is an important part of safety-critical software development in areas such as avionics, space, and automotive engineering. Ada is often used in these systems. It shows how requirements are implemented in code and how changes are reflected in commits and issue reports. Automated traceability tools for Ada are not as common as those for other programming languages. Currently, the systematic linking of requirements to Ada source files, version-control history, and issue artifacts is often a manual process that requires effort to maintain throughout the software lifecycle. We present ADATracer, a software traceability tool designed to recover links between natural language requirements, Ada source files, version-control commits, and issue-tracking artifacts. The tool uses keyword-based retrieval, semantic vector embeddings, and a Neo4j-based knowledge graph. It includes an Ada-aware parser that accounts for language features such as package specifications, bodies, and strong typing. ADATracer supports traceability recovery and graph-based exploration, allowing for the inspection of evidence chains from requirements to implementation and issue resolution. We apply ADATracer to the open-source Ada Web Application (AWA) framework, where the tool identifies traceability links. This work facilitates traceability in certification-driven Ada development and provides a framework for further study in safety-critical software systems. The source code and demonstration video are publicly available at https://github.com/rishalab/ADATracer and https://youtu.be/sb66cEffF-o.
Modern companies that incorporate complex software systems as part of their market products are increasingly seeking technological independence in the development and maintenance of these systems. Such companies typically manage very large codebases, often comprising millions of lines of code. Testing, maintaining, and transforming these codebases requires multi-functional analysis and development tools, which cannot simply be obtained off the shelf. This is largely due to the inherent difficulty of many fundamental program analysis problems — indeed, several of these problems are formally undecidable (for example, pointer analysis and garbage collection for C programs). At the same time, large industrial codebases often use only a limited subset of the features available in their respective programming languages. Consequently, program analysis problems that are undecidable in the general case may become tractable for these restricted, domain-specific subsets. This observation creates opportunities for specialized approaches. This article proposes an approach for developing domain-specific program analysis solutions tailored to particular large industrial codebases. Such solutions are in high demand for tasks including fuzzing, symbolic execution, automated test generation, static analysis, code transformation and optimization, and vulnerability detection. The development of such custom domain-specific analysis tools becomes feasible because code-owning companies typically possess substantial engineering resources. These resources can be leveraged in combination with open-source frameworks and ecosystems such as Eclipse, Low Level Virtual Machine, and Microsoft Visual Studio Code. Furthermore, the economic impact is often significant: effective analysis solutions lead to substantial cost savings and quality improvements, which justifies the investment in specialized tool development. The proposed method consists of the following key stages: problem and idea analysis, solution design, requirements development, implementation, testing and validation, deployment and transfer. A central element of this method is the development of code templates that define the subset of the basic programming language used within the codebase. These templates provide a formal foundation for analysis and constrain the variability that tools must support. Notably, requirements development, tool implementation, and validation proceed in parallel, with testing tightly integrated into the development process. Using this method, several tools have been successfully developed, including a static analysis tool for C applications tailored for fuzzing, a clone detection and refactoring tool for a large network device software codebase, and other domain-specific solutions. Each project typically involved between one and three developers and lasted one to two years. While effective, the proposed method is resource-intensive. Analysis of completed projects shows that when a fully specified technical assignment is available from the outset, the required resources for implementing program analysis solutions can be reduced by several times. However, the strength of the method lies in situations where no detailed technical specification can be produced in advance. In such cases, the method enables iterative elicitation of requirements, reducing the risk of developing tools that do not meet real project needs.
D. Koznov· Scientific and Technical Jou...· 0 citations
This article explores the practical application of AI tool (ChatGPT v3.5 and 4) in the full lifecycle of a real-world software development project, based on field research of 2023-2024 in Europe. The research evaluates the effectiveness of AI in generating core software artifacts, including functional specifications, software code, automated tests, user documentation, and application content. While the AI tool proved to be a powerful assistant for creating and refining these deliverables, its limitations became evident in areas requiring up-to-date technical guidance or creative input in product business logic development. In general, ChatGPT significantly accelerated the development process, with project team members reporting a substantial increase in productivity. The study also highlights best practices for AI usage in software engineering, emphasizing the importance of service-oriented design, iterative prompt refinement, and ongoing human oversight. Despite its shortcomings in generating original ideas or adapting to evolving platform requirements, ChatGPT demonstrated strong capabilities in automating repetitive tasks and enhancing overall efficiency. The findings confirm the research hypothesis that AI can reliably produce key software development artifacts with minimal human input, marking a pivotal step toward the broader integration of AI in software engineering practices.
Denis Svyatoslavovich Pashchenko· Revista Multidisciplinar Epi...· 0 citations