Guilherme Corredato Guerino

Guilherme Corredato Guerino, João Pedro de Souza Olivo Tardivo, Renato Balancieri et al.

Context. Software startups face significant challenges in building minimum viable products, particularly in the early stages, when resources are limited and expertise in user experience is scarce. Objective. Introduce StartFlow, a structured method that helps non-specialized professionals create MVP prototypes using the wireflow technique, a combination of wireframes and user flows. StartFlow consists of three steps: (i) organizing features; (ii) building wireflows; and (iii) verifying and refining them based on usability heuristics. Method. To assess the method Startflow, we first conducted a focus group with researchers in Software Engineering, Human-Computer Interaction, and Software Startups. Afterward, we conducted a proof-of-concept study, which consisted of an experiment and a heuristic evaluation with experts. Results. The qualitative analysis of the focus group revealed that participants found the method straightforward, flexible, and helpful in structuring user flows and identifying visual components. However, they also pointed out the need to improve its presentation, clarify its iterative nature, and strengthen its connection to broader UX principles. The results of the proof-of-concept indicate that participants who used StartFlow created clearer prototypes, adhered to the proposed user stories and business rules, and presented fewer usability defects. Furthermore, the method was well evaluated for its ease of use and intended future adoption. Conclusion. The study reinforces the potential of StartFlow as an accessible tool to support user-centered development in software startups from the earliest stages of their product development.

Guilherme Guerino, Luiz Rodrigues, Luana Bianchini et al.

This study explores the integration of Augmented Intelligence (AuI) in Intelligent Tutoring Systems (ITS) to address challenges in Artificial Intelligence in Education (AIED), including teacher involvement, AI reliability, and resource accessibility. We present MathAIde, an ITS that uses computer vision and AI to correct mathematics exercises from student work photos and provide feedback. The system was designed through a collaborative process involving brainstorming with teachers, high-fidelity prototyping, A/B testing, and a real-world case study. Findings emphasize the importance of a teacher-centered, user-driven approach, where AI suggests remediation alternatives while teachers retain decision-making. Results highlight efficiency, usability, and adoption potential in classroom contexts, particularly in resource-limited environments. The study contributes practical insights into designing ITSs that balanceuser needs and technological feasibility, while advancing AIED research by demonstrating the effectiveness of a mixed-methods, user-centered approach to implementing AuI in educational technologies.