Implementing AI for Enhanced Public Services Gov.br: A Methodology for the Brazilian Federal Government

Maísa Kely de Melo, Maísa Kely de Melo, Silvia Reis, Silvia Reis, Vinícius Di Oliveira, Vinícius Di Oliveira, Vinícius Di Oliveira, Allan Faria, Allan Faria, Ricardo de Lima, Ricardo de Lima, Li Weigang, Li Weigang, Jose Salm Junior, Jose Salm Junior, Joao Souza, Joao Souza, Vérica Freitas, Pedro Brom, Pedro Brom, Pedro Brom, Herbert Kimura, Herbert Kimura, Daniel Cajueiro, Daniel Cajueiro, Gladston Luiz da Silva, Gladston Luiz da Silva, Victor Celestino, Victor Celestino

2024

Abstract

The website portal of the Brazilian federal government (Gov.br) consists of pages from almost 40 ministries, 180 public agencies and up to 5000 public services for all citizens, posing a significant challenge in improving service quality. This article presents an innovative methodology to implement artificial intelligence (AI) to address these challenges, to enhance the efficiency, accessibility, and quality of services to the population. The methodology combines elements of Lean Office, Design Sprint, Analytic Hierarchy Process (AHP), and advanced AI techniques, particularly Large Language Models (LLMs), making it flexible and adaptable to the needs of government entities. Developed in collaboration with project managers, public servants, and stakeholders, the methodology includes a survey of demands, selection, and prototyping of AI projects in a complex government context. The practical application selected the Gov.br portal for prototyping, involving the development of an advanced generative agent to interact with citizens, clarify doubts, direct to the requested services, and provide human interaction when necessary. The recommended practices offer a valuable contribution to other developing countries seeking to integrate AI solutions into their public services.

Paper Citation

in Harvard Style

Kely de Melo M., Reis S., Di Oliveira V., Faria A., de Lima R., Weigang L., Salm Junior J., Souza J., Freitas V., Brom P., Kimura H., Cajueiro D., Luiz da Silva G. and Celestino V. (2024). Implementing AI for Enhanced Public Services Gov.br: A Methodology for the Brazilian Federal Government. In Proceedings of the 20th International Conference on Web Information Systems and Technologies - Volume 1: WEBIST; ISBN 978-989-758-718-4, SciTePress, pages 90-101. DOI: 10.5220/0012997000003825

in Bibtex Style

@conference{webist24,
author={Maísa Kely de Melo and Silvia Reis and Vinícius Di Oliveira and Allan Faria and Ricardo de Lima and Li Weigang and Jose Salm Junior and Joao Souza and Vérica Freitas and Pedro Brom and Herbert Kimura and Daniel Cajueiro and Gladston Luiz da Silva and Victor Celestino},
title={Implementing AI for Enhanced Public Services Gov.br: A Methodology for the Brazilian Federal Government},
booktitle={Proceedings of the 20th International Conference on Web Information Systems and Technologies - Volume 1: WEBIST},
year={2024},
pages={90-101},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0012997000003825},
isbn={978-989-758-718-4},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 20th International Conference on Web Information Systems and Technologies - Volume 1: WEBIST
TI - Implementing AI for Enhanced Public Services Gov.br: A Methodology for the Brazilian Federal Government
SN - 978-989-758-718-4
AU - Kely de Melo M.
AU - Reis S.
AU - Di Oliveira V.
AU - Faria A.
AU - de Lima R.
AU - Weigang L.
AU - Salm Junior J.
AU - Souza J.
AU - Freitas V.
AU - Brom P.
AU - Kimura H.
AU - Cajueiro D.
AU - Luiz da Silva G.
AU - Celestino V.
PY - 2024
SP - 90
EP - 101
DO - 10.5220/0012997000003825
PB - SciTePress