Hybrid Cognitive Systems in the Era of LLMs: Distributed Cognition, the Rise of “Vibe Coding”, and New Sociotechnical Risks in Brazilian Software Engineering

• Marcelo Massashi Simonae UTFPR
• Marlon Marcon UTFPR

DOI: https://doi.org/10.5753/eniac.2026.31486

Resumo

The integration of Large Language Models (LLMs) into Software Engineering (SE) practices is catalyzing a profound sociotechnical transformation. While LLMs promise unprecedented productivity gains, this intuitive approach radically alters the mediation of developer intent. This research presents a vision and research proposal arguing that the symbiotic interaction between software developers and generative AI agents gives rise to Hybrid Cognitive Systems (HCS). This paper establishes a structured conceptual framework to analyze how HCS operate, synthesizing multi-agent agile workflows, shifting human-AI role dynamics, and cognitive adoption factors. Furthermore, we critically examine how these systems may lead to the erosion of engineering best practices and technical debt. Due to the lack of current empirical data, this work proposes a comprehensive, future qualitative methodological procedure through a multiple-case study in the Brazilian IT industry, modeling the tension between augmented cognition and technical degradation to evaluate the sector’s “Organizational Readiness” for advanced autonomous automation and Artificial General Intelligence (AGI).

Referências

Abrahão, S., Grundy, J., Pezzè, M., Storey, M.-A., and Tamburri, D. (2025). Software engineering by and for humans in an ai era. ACM Transactions on Software Engineering and Methodology, 34.

Alami, A. and Ernst, N. (2025). Human and machine: How software engineers perceive and engage with ai-assisted code reviews compared to their peers.

Bainbridge, L. (1983). Ironies of automation. Automatica, 19(6):775–779.

Brasil (2018). Lei nº 13.709, de 14 de agosto de 2018. lei geral de proteção de dados pessoais (lgpd). Acessado em: 23 jun. 2026.

Carlini, N., Tramer, F., Wallace, E., Jagielski, M., Herbert-Voss, A., Lee, K., Roberts, A., Brown, T., Song, D., Erlingsson, U., Oprea, A., and Raffel, C. (2021). Extracting training data from large language models. In 30th USENIX Security Symposium (USENIX Security 21), pages 2633–2650. USENIX Association.

Cinkusz, K., Chudziak, J. A., and Niewiadomska-Szynkiewicz, E. (2025). Cognitive agents powered by large language models for agile software project management. Electronics, 14(1).

Derner, E., Batistič, K., Zahálka, J., and Babuska, R. (2024). A security risk taxonomy for prompt-based interaction with large language models. IEEE Access, PP:1–1.

Dhole, K. (2023). Large language models as sociotechnical systems. Endsley, M. R. (2017). From here to autonomy: Lessons learned from human–automation research. Human Factors, 59(1):5–27.

Gadde, A. (2025). Democratizing software engineering through generative ai and vibe coding: The evolution of no-code development. Journal of Computer Science and Technology Studies, 7:556–572.

Kreuzberger, D., Kühl, N., and Hirschl, S. (2023). Machine learning operations (mlops): Overview, definition, and architecture. IEEE Access, 11:31866–31879.

Lambiase, S., Catolino, G., Palomba, F., Ferrucci, F., and Russo, D. (2025). Investigating the role of cultural values in adopting large language models for software engineering. ACM Transactions on Software Engineering and Methodology, 35.

Lundberg, S. M. and Lee, S.-I. (2017). A unified approach to interpreting model predictions. In Advances in Neural Information Processing Systems, volume 30. Curran Associates, Inc.

Meske, C., Hermanns, T., Weiden, E., Loser, K.-U., and Berger, T. (2025). Vibe coding as a reconfiguration of intent mediation in software development: Definition, implications, and research agenda.

Mäkinen, S., Skogström, H., Laaksonen, E., and Mikkonen, T. (2021). Who needs mlops: What data scientists seek to accomplish and how can mlops help? IEEE Software, 38(2):109–115.

Nasir, B. and Hussain, I. (2024). Automating agile workflows: The role of multi-agent llms in modern software engineering.

Ribeiro, M. T., Singh, S., and Guestrin, C. (2016). "why should i trust you?": Explaining the predictions of any classifier. In Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, pages 1135–1144.

Ribeiro, M. T., Singh, S., and Guestrin, C. (2018). Anchors: High-precision model-agnostic explanations. In Proceedings of the AAAI Conference on Artificial Intelligence, volume 32.

Runeson, P. and Höst, M. (2009). Guidelines for conducting and reporting case study research in software engineering. Empirical Software Engineering, 14(2):131–164.

Salem, N., Hudaib, A., Al-Tarawneh, K., Salem, H., Tareef, A., Salloum, H., and Mazzara, M. (2024). A survey on the application of large language models in software engineering. Computer Research and Modeling, 16:1715–1726.

Tadi, S. R. C. C. T. (2025). Developer and llm pair programming: An empirical study of role dynamics and prompt-based collaboration. International Journal of Advanced Research in Science Communication and Technology, 5:436–444.

Teece, D. J. (2007). Explicating dynamic capabilities: the nature and microfoundations of (sustainable) enterprise performance. Strategic Management Journal, 28(13):1319–1350.

Viswanadhapalli, V. (2024). Ai-augmented software development: Enhancing code quality and developer productivity using large language models. pages 2456–4184.

Yin, R. K. (2018). Case study research and applications: Design and methods. Sage publications, 6th edition.

Zou, C. (2024). Sociotechnical risks of simulating humans with language model agents.