Digitala Vetenskapliga Arkivet

Change search
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf
Hands-on Use and Adaptation of AI in Developing and Testing Software Applications
Uppsala University, Disciplinary Domain of Science and Technology, Mathematics and Computer Science, Department of Information Technology, Division of Systems and Control.
2024 (English)Independent thesis Advanced level (professional degree), 20 credits / 30 HE creditsStudent 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
Available from: 2024-09-13 Created: 2024-09-13 Last updated: 2024-09-13Bibliographically approved

Open Access in DiVA

fulltext(2004 kB)1079 downloads
File information
File name FULLTEXT01.pdfFile size 2004 kBChecksum SHA-512
a3dd186dc5d668f2fd041aad2e02b0eaabc435cc404b5329430c44faaa73a0ad75861f55b34dd2d761d160e3c1e90c0033f2569cfdf55d6c1ba5c665f5706ebb
Type fulltextMimetype application/pdf

By organisation
Division of Systems and Control
Computer and Information Sciences

Search outside of DiVA

GoogleGoogle Scholar
Total: 1081 downloads
The number of downloads is the sum of all downloads of full texts. It may include eg previous versions that are now no longer available

urn-nbn

Altmetric score

urn-nbn
Total: 967 hits
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf