Abstract: Symptom-based triage and risk assessment is often the first step in patient triage but can be highly subjective, time-consuming, and prone to error, especially in resource-limited settings. Artificial Intelligence (AI) can enhance triage and reduce errors in triage and risk assessment , especially in resource-limited settings. Sevamob provides artificial intelligence enabled healthcare platform to organizations and developed SymptomsAI, an AI system for disease prediction using symptoms of patients. It uses large language model for initial disease prediction based on patient symptoms and clinical data. To determine the accuracy of Sevamob SymptomsAI, we used an Android smartphone/tablet with the Sevamob app. The app was operated by a nurse.