Reproduce “One Developer Is All You Need: A Case Study of an AI-Augmented One-Person Squad in a Brownfield Enterprise” 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
Marcelo Vilas Boas, Gustavo Pinto, Edward Roberto Monteiro, Vinicius Fernandes Carida, Danilo Ribeiro
An investigation into an AI-augmented one-person squad at Itaú Unibanco demonstrated that a single staff engineer, leveraging multi-agent AI and a Spec-Driven Development workflow, can accelerate complex enterprise software delivery by 50% and reduce costs by over 85%, all while upholding high quality standards.
Key insights
- The quality of natural-language specifications is the most critical determinant for successful AI-augmented development, directly impacting the quality of AI-generated code.
- The model functions as a multiplier for an *experienced* engineer's throughput, requiring deep institutional and domain knowledge to evaluate AI outputs and ensure quality.
- Significant efficiency gains stem from collapsing inter-discipline coordination overhead, as AI agents absorb routine specialist work, reducing cognitive load on the single human engineer.
Summary by alphaXiv.
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.