Reproduce “A Lean and Spec-Driven AI-Assisted Software Development Lifecycle for Applied AI Education: The AI-SDLC Approach” on OpenResearch
Turn your favorite coding agents into research agents that review literature, develop hypotheses, and run experiments.
Universal app for Apple silicon and Intel. Requires macOS 11 or later.
About this paper
Andreas Martin, Sandro Schwander
The authors present AI-SDLC, a lightweight lifecycle for agentic software development. It preserves requirements, architecture decisions, tasks, tests, and agent guidance in version-controlled files, organizing work into iterative phases from specification through deployment. In an exploratory survey of 13 students, all respondents said Specify sharpened requirements before implementation; this self-report does not establish quality improvement or causal effects beyond the cohort.
Summary by alphaXiv.
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.