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
Integrating Generative AI into Test-driven Development Inspired Framework: An Experimental Evaluation
University West, Department of Engineering Science.
University West, Department of Engineering Science.
2025 (English)Independent thesis Basic level (degree of Bachelor), 10 credits / 15 HE creditsStudent thesis
Abstract [en]

The rapid evolution of generative AI tools in software engineering has opened new possibilities for automating coding tasks. Test-Driven Development (TDD) is a well-established methodology that enhances code quality by enforcing test creation before implementation. This study examines the integration of Generative AI into a TDD inspired workflow. In an experimental framework, code produced with and without predefined test cases is evaluated, and an iterative correction cycle enables the model to refine its solutions. Results show that providing test cases as input leads to more accurate code generation, while the iterative process yields further improvements in correctness. These outcomes highlight both the promise and the practical challenges of adopting generative AI within structured development practices.

Place, publisher, year, edition, pages
2025. , p. 32
Keywords [en]
Generative AI, Test-drive, development, framework
National Category
Computer Sciences Software Engineering
Identifiers
URN: urn:nbn:se:hv:diva-24026Local ID: EHD500OAI: oai:DiVA.org:hv-24026DiVA, id: diva2:1991982
Subject / course
Computer engineering
Educational program
Datateknik - högskoleingenjör
Supervisors
Examiners
Available from: 2025-09-01 Created: 2025-08-26 Last updated: 2025-09-30Bibliographically approved

Open Access in DiVA

No full text in DiVA

By organisation
Department of Engineering Science
Computer SciencesSoftware Engineering

Search outside of DiVA

GoogleGoogle Scholar

urn-nbn

Altmetric score

urn-nbn
Total: 46 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