Hands-on Use and Adaptation of AI in Developing and Testing Software Applications
2024 (English)Independent thesis Advanced level (professional degree), 20 credits / 30 HE credits
Student thesis
Abstract [en]
This thesis explores the integration of artificial intelligence (AI) in software development. Conducted at the consultancy company Amaceit AB, the study explores the current usage of artificial intelligence across various stages of the software development life cycle. It explores AI techniques such as machine learning, neural networks, deep learning, generative AI, and large language models, emphasizing their roles in enhancing efficiency and accuracy in software development. The study examines the use of AI in the planning, requirements gathering, design, development, testing, deployment, and maintenance phases of the software development process, showcasing how AI automates tasks, optimizes code generation, improves testing accuracy, and enables proactive maintenance. Furthermore, the thesis reviews popular AI tools like GitHub Copilot, Amazon CodeWhisperer, Google's Bard, Microsoft's Bing, Anthropic's Claude, and OpenAI's ChatGPT, comparing their effectiveness in code generation and analyzes their capabilities, benefits, and challenges. The study combines a literature review and a practical implementation, in the form of an AI-based web application using OpenAI's GPT-4 for automated test case generation. Findings highlight AI's effectiveness in improving coding efficiency and software quality, showing its ability to automate tasks, streamline workflows, and speed up development cycles, thereby reducing costs and enhancing software quality. While AI serves as a powerful assistant in software development by helping programmers in their everyday work lives, it is not a substitute for human expertise. The evaluation at Amaceit shows promising results in improving the efficiency of test case generation. It also addresses privacy and data security concerns related to adopting AI and proposes future steps to scale AI implementations and integrate tools directly into developer environments.
Place, publisher, year, edition, pages
2024. , p. 36
Series
UPTEC IT, ISSN 1401-5749 ; 24048
Keywords [en]
artificial intelligence, machine learning, generative AI, large language model, software development, consultancy
National Category
Computer and Information Sciences
Identifiers
URN: urn:nbn:se:uu:diva-538326OAI: oai:DiVA.org:uu-538326DiVA, id: diva2:1897558
External cooperation
amaceit AB
Educational program
Master of Science Programme in Information Technology Engineering
Presentation
2024-08-21, 09:30 (English)
Supervisors
Examiners
2024-09-132024-09-132024-09-13Bibliographically approved