Gustavo Pinto

Luciane Silva, Thayssa Rocha, Nicole Davila et al.

Design Systems (DS) help standardize front-end development, yet developers still face challenges when translating high-fidelity mockups into consistent, production-ready interfaces. Although AI-assisted tools have emerged as a potential solution, empirical evidence on their effectiveness within DS-centered workflows remains limited. This paper reports a controlled experiment conducted at a large Brazilian enterprise that compares manual development, DS-only development, and DS-aware AI-assisted development across Angular, iOS, and Android stacks. Results from two experimental cycles show that AI assistance significantly reduced time-to-delivery (by 46.7% to 69.4%), increased task completeness, and decreased performance variability. Analysis of break patterns further suggests reduced workflow friction and smoother task execution. These findings provide empirical evidence that DS-aware AI tools can significantly accelerate development, improve design fidelity, and yield practical benefits for industrial front-end workflows.

Marcelo Vilas Boas, Gustavo Pinto, Edward Roberto Monteiro et al.

AI tools are enabling engineers to absorb roles previously distributed across cross-functional squads, yet there is little structured evidence on how to design or evaluate such a one-person squad in a regulated enterprise setting. Without that evidence, organizations adopting this model lack guidance on which design decisions make it viable and which conditions cause it to break down. We report a case study in which a single staff engineer, supported by four AI agents under a Spec-Driven Development workflow, delivered a brownfield product initiative scoped for a four-person squad in half the planned time, with 90\% acceptance of AI-generated code on first review, full integration test pass rates, and an above-85\% reduction in direct staffing cost. The results indicate that AI does not replace team members it multiplies the throughput of the experienced engineer who remains, making specification quality and institutional knowledge, not model capability, the binding constraints on one-person squad success.

Gustavo Pinto, Pedro Eduardo de Paula Naves, Ana Paula Camargo et al.

Enterprise teams building internal coding agents face a gap between prototype performance and production readiness. The root cause is that technical model quality alone is insufficient -- tool design, safety enforcement, state management, and human trust calibration are equally decisive, yet underreported in the literature. We present CodeGen, an internal coding agent at Zup, and show that targeted tool design (e.g., string-replacement edits over full-file rewrites) and layered safety guardrails improved agent reliability more than prompt engineering, while progressive human oversight modes drove organic adoption without mandating trust. These findings suggest that the engineering decisions surrounding the model -- not the model itself -- determine whether a coding agent delivers real value in practice.