A Lean and Spec-Driven AI-Assisted Software Development Lifecycle for Applied AI Education: The AI-SDLC Approach. Martin, A. & Schwander, S. September, 2026. arXiv:2609.24348 [cs.SE]
A Lean and Spec-Driven AI-Assisted Software Development Lifecycle for Applied AI Education: The AI-SDLC Approach [link]Paper  A Lean and Spec-Driven AI-Assisted Software Development Lifecycle for Applied AI Education: The AI-SDLC Approach [link]Paper  doi  abstract   bibtex   
AI coding agents increasingly support software development beyond code completion, including planning, implementation, testing, and repository-level task execution. Their practical use, however, often remains only weakly connected to established software engineering practices. The aim of this work is to develop and evaluate a lightweight, spec-driven lifecycle for governed agentic software engineering. The lifecycle combines established software engineering practices with repository-local guidance through specifications, AGENTS.md, and phase-specific agent skill files. The approach was developed in the context of the FHNW course AI-assisted Software Development and applied by students to business-oriented software use cases. Its educational and practical applicability is explored through a student survey combining closed rating items with open-ended questions. The contribution of this work is a process-oriented framework that enables AI coding agents to operate with bounded autonomy within an explicit, reviewable, and test-oriented software development lifecycle.
@misc{martin_lean_2026,
	title = {A {Lean} and {Spec}-{Driven} {AI}-{Assisted} {Software} {Development} {Lifecycle} for {Applied} {AI} {Education}: {The} {AI}-{SDLC} {Approach}},
	copyright = {Creative Commons Namensnennung - Nicht kommerziell - Keine Bearbeitungen 4.0 Internationale Lizenz},
	shorttitle = {A {Lean} and {Spec}-{Driven} {AI}-{Assisted} {Software} {Development} {Lifecycle} for {Applied} {AI} {Education}},
	url = {http://arxiv.org/abs/2609.24348},
	doi = {10.48550/arXiv.2609.24348},
	abstract = {AI coding agents increasingly support software development beyond code completion, including planning, implementation, testing, and repository-level task execution. Their practical use, however, often remains only weakly connected to established software engineering practices. The aim of this work is to develop and evaluate a lightweight, spec-driven lifecycle for governed agentic software engineering. The lifecycle combines established software engineering practices with repository-local guidance through specifications, AGENTS.md, and phase-specific agent skill files. The approach was developed in the context of the FHNW course AI-assisted Software Development and applied by students to business-oriented software use cases. Its educational and practical applicability is explored through a student survey combining closed rating items with open-ended questions. The contribution of this work is a process-oriented framework that enables AI coding agents to operate with bounded autonomy within an explicit, reviewable, and test-oriented software development lifecycle.},
	urldate = {2026-09-22},
	publisher = {arXiv},
	author = {Martin, Andreas and Schwander, Sandro},
	month = sep,
	year = {2026},
	note = {arXiv:2609.24348 [cs.SE]},
	url_paper={https://api.zotero.org/users/1325684/publications/items/SNLI5A5I/file/view}
}

Downloads: 0