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]
Paper
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
{"_id":"ZybxNxjBNaHtuwykb","bibbaseid":"martin-schwander-aleanandspecdrivenaiassistedsoftwaredevelopmentlifecycleforappliedaieducationtheaisdlcapproach-2026","author_short":["Martin, A.","Schwander, S."],"bibdata":{"bibtype":"misc","type":"misc","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":[{"propositions":[],"lastnames":["Martin"],"firstnames":["Andreas"],"suffixes":[]},{"propositions":[],"lastnames":["Schwander"],"firstnames":["Sandro"],"suffixes":[]}],"month":"September","year":"2026","note":"arXiv:2609.24348 [cs.SE]","url_paper":"https://api.zotero.org/users/1325684/publications/items/SNLI5A5I/file/view","bibtex":"@misc{martin_lean_2026,\n\ttitle = {A {Lean} and {Spec}-{Driven} {AI}-{Assisted} {Software} {Development} {Lifecycle} for {Applied} {AI} {Education}: {The} {AI}-{SDLC} {Approach}},\n\tcopyright = {Creative Commons Namensnennung - Nicht kommerziell - Keine Bearbeitungen 4.0 Internationale Lizenz},\n\tshorttitle = {A {Lean} and {Spec}-{Driven} {AI}-{Assisted} {Software} {Development} {Lifecycle} for {Applied} {AI} {Education}},\n\turl = {http://arxiv.org/abs/2609.24348},\n\tdoi = {10.48550/arXiv.2609.24348},\n\tabstract = {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.},\n\turldate = {2026-09-22},\n\tpublisher = {arXiv},\n\tauthor = {Martin, Andreas and Schwander, Sandro},\n\tmonth = sep,\n\tyear = {2026},\n\tnote = {arXiv:2609.24348 [cs.SE]},\n\turl_paper={https://api.zotero.org/users/1325684/publications/items/SNLI5A5I/file/view}\n}\n\n\n\n","author_short":["Martin, A.","Schwander, S."],"key":"martin_lean_2026","id":"martin_lean_2026","bibbaseid":"martin-schwander-aleanandspecdrivenaiassistedsoftwaredevelopmentlifecycleforappliedaieducationtheaisdlcapproach-2026","role":"author","urls":{"Paper":"http://arxiv.org/abs/2609.24348"," paper":"https://api.zotero.org/users/1325684/publications/items/SNLI5A5I/file/view"},"metadata":{"authorlinks":{}},"downloads":0},"bibtype":"misc","biburl":"https://bibbase.org/zotero-mypublications/andreasmartin","dataSources":["cEgnxBqYRFNdjfnYF"],"keywords":[],"search_terms":["lean","spec","driven","assisted","software","development","lifecycle","applied","education","sdlc","approach","martin","schwander"],"title":"A Lean and Spec-Driven AI-Assisted Software Development Lifecycle for Applied AI Education: The AI-SDLC Approach","year":2026}