EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Automating Institutional Internal Communication with a Generative Artificial Intelligence Agent and Scheduled Workflows at IFTO - Araguatins Campus

Nicolas Heitor Feitosa Costa, Fábio Emanuell Abreu Cardoso, Julio Cesar Santos Sousa, Valéria dos Santos Silva Torres, Gabriel Ribeiro Milhomem Ferreira, Allan Carlos Araújo Teixeira, Ramásio Ferreira de Melo

REMUNOM · 16.11.2026 · 13 (24) · 1-27

DOI: 10.66104/2fxv0d97 ↗

Kurz gefasst

Fachartikel in der Zeitschrift REMUNOM, online erschienen am 16.11.2026. Verfasst von Nicolas Heitor Feitosa Costa und 6 weiteren Autor:innen. Die Arbeit nennt 9 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Internal communication in public educational institutions is often hindered by administrative overload, fragmented formal channels and slow information dissemination. This article describes the development, deployment and extension of an internal communication agent based on generative artificial intelligence at the Federal Institute of Tocantins (IFTO) - Araguatins Campus. The research, applied in nature and qualitative-descriptive in approach, followed an evolutionary prototyping cycle conducted at the Artificial Intelligence and Automation Research Laboratory (LEIAA). The solution, with a hybrid architecture (self-hosted Docker containers and cloud services), combines the n8n orchestration platform, the PostgreSQL database, the Evolution API messaging gateway and the GPT-4o-mini language model, integrated with Google Workspace services through the Model Context Protocol (MCP). The system operates in two modes: in the reactive mode, the language model interprets natural language requests and performs calendar, e-mail and spreadsheet actions; in the proactive mode, scheduled routines query institutional spreadsheets and send messages built from templates. Between May and June 2026, five proactive workflows (institutional events, undergraduate thesis defences, birthdays, academic calendar and scheduled messages) operated in three real WhatsApp groups of the campus, comprising staff, students and faculty. During this period, notices were sent daily according to the spreadsheet records, and the team observed no failures in the event and birthday dispatches. A comparison with systems described in the literature indicates that the solution combines actions executed by a language model, proactive messaging to groups and self-hosted orchestration; its effect on the communication team's routine, however, has not yet been measured.

Zitieren

APA

Costa, N. H. F., Cardoso, F. E. A., Sousa, J. C. S., Torres, V. D. S. S., Ferreira, G. R. M., Teixeira, A. C. A., & Melo, R. F. D. (2026). Automating Institutional Internal Communication with a Generative Artificial Intelligence Agent and Scheduled Workflows at IFTO - Araguatins Campus. REMUNOM, 13(24), 1-27. https://doi.org/10.66104/2fxv0d97

Vancouver

Costa NHF, Cardoso FEA, Sousa JCS, Torres VDSS, Ferreira GRM, Teixeira ACA, et al. Automating Institutional Internal Communication with a Generative Artificial Intelligence Agent and Scheduled Workflows at IFTO - Araguatins Campus. REMUNOM. 2026;13(24):1-27. doi:10.66104/2fxv0d97

BibTeX
@article{Costa2026,
  author = {Costa, Nicolas Heitor Feitosa and Cardoso, Fábio Emanuell Abreu and Sousa, Julio Cesar Santos and Torres, Valéria dos Santos Silva and Ferreira, Gabriel Ribeiro Milhomem and Teixeira, Allan Carlos Araújo and Melo, Ramásio Ferreira de},
  title = {Automating Institutional Internal Communication with a Generative Artificial Intelligence Agent and Scheduled Workflows at IFTO - Araguatins Campus},
  journal = {REMUNOM},
  year = {2026},
  volume = {13},
  number = {24},
  pages = {1--27},
  doi = {10.66104/2fxv0d97}
}
Kostenlos starten →