Weak healthcare coverage and the subsequent shortage of health professionals in rural areas of Mozambique, associated with the geographical distance between medical centers and linguistic obstacles between healthcare workers and patients who communicate only in local languages, hinder access to essential services. These factors result in barriers to the early detection of epidemiological outbreaks, such as Cholera and Malaria (WHO, 2026). This paper proposes a system featuring a rapid assessment architecture (triage) capable of appropriately addressing the aforementioned constraints. The intelligent system, based on Natural Language Processing (NLP) and hybrid interfaces (Voice/USSD), utilizes chatbots trained to interpret symptoms reported in national languages (Nhungue, Cisena, Emakhuwa, Changana, among others). The model ensures automated preliminary triage, dispensing with the need for smartphones or immediate human interaction, thereby promoting digital sovereignty and the democratization of access to diagnosis (Gomez et al., 2022).