Investigation of AI tools Performance in the Definition of Microservices Software Architectures

Σωτηρόπουλος, Γεώργιος; Sotiropoulos, Georgios

dc.contributor.author	Σωτηρόπουλος, Γεώργιος	el
dc.contributor.author	Sotiropoulos, Georgios	en
dc.date.accessioned	2026-02-05T07:19:17Z
dc.date.available	2026-02-05T07:19:17Z
dc.identifier.uri	https://dspace.lib.ntua.gr/xmlui/handle/123456789/63313
dc.identifier.uri	http://dx.doi.org/10.26240/heal.ntua.31008
dc.rights	Default License
dc.subject	Τεχνολογία Λογισμικού	el
dc.subject	Software Engineering	en
dc.subject	Artificial Intelligence	en
dc.subject	Τεχνητή Νοημοσύνη	el
dc.subject	Microservices	en
dc.subject	Software Requirements Specification (SRS)	en
dc.subject	Retrieval-Augmented Generation (RAG)	en
dc.title	Investigation of AI tools Performance in the Definition of Microservices Software Architectures	en
dc.title	Διερεύνηση Επιδόσεων Εργαλείων Τεχνητής Νοημοσύνης στον Ορισμό Αρχιτεκτονικών Λογισμικού Μικροϋπηρεσιών	el
dc.contributor.department	Τομέας Τεχνολογίας Πληροφορικής και Υπολογιστών	el
heal.type	bachelorThesis
heal.classification	Τεχνολογία Λογισμικού	el
heal.classification	Software Engineering	en
heal.classification	Τεχνητή Νοημοσύνη	el
heal.classification	Artificial Intelligence	en
heal.language	en
heal.access	free
heal.recordProvider	ntua	el
heal.publicationDate	2025-07-04
heal.abstract	The design of software architecture is a pivotal step in the software development lifecycle, bridging user requirements and system implementation through the definition of high-level structural designs. Despite its critical importance, architectural design remains a challenging, time-intensive, and error-prone process. This thesis investigates the performance of artificial intelligence (AI) tools, specifically large language models (LLMs), in automating the generation of software architectures focusing on Microservices-based systems. Building on prior research, this study explores how different input formats, ranging from plain-text requirements to detailed specification documents, model selection and Retrieval-Augmented Generation (RAG) techniques, affect the quality and compliance of AI-generated architectural designs with the software requirements. We apply an evaluation framework based on assessments from domain experts and we introduce a set of objective metrics to pave the road towards an automatic evaluation process. Additionally, this study explores whether smaller, locally hosted LLMs can serve as practical alternatives to commercially available AI tools. The results provide insights into the potential for AI to transform the architectural design phase of software development, enhancing design efficiency and quality while reshaping the role of software architects in collaborative human-AI workflows. This work contributes to the growing field of AI-assisted software engineering and outlines future research avenues to further integrate intelligent automation into complex system design.	en
heal.advisorName	Βεσκούκης, Βασίλειος
heal.committeeMemberName	Βεσκούκης, Βασίλειος
heal.committeeMemberName	Στάμου, Γεώργιος
heal.committeeMemberName	Παπασπύρου, Νικόλαος
heal.academicPublisher	Εθνικό Μετσόβιο Πολυτεχνείο. Σχολή Ηλεκτρολόγων Μηχανικών και Μηχανικών Υπολογιστών. Τομέας Τεχνολογίας Πληροφορικής και Υπολογιστών	el
heal.academicPublisherID	ntua
heal.numberOfPages	136
heal.fullTextAvailability	false