Project Feliann: An AI-Orchestrated, Low-Code Research Support Ecosystem For Student Success and Service Efficiency in a Philippine Higher Education Institution

Student researchers at small and mid-sized higher education institutions (HEIs) in the Global South wait days, sometimes longer, to secure a research adviser, get compliance documents verified, or receive statistical feedback. This paper documents the design, development, and pilot implementation of Project Feliann, an AI-orchestrated, low-code research-support ecosystem built by the Research, Planning, and Analytics Services (RPAS) office of Aldersgate College Inc., a private HEI in Nueva Vizcaya, Philippines. Following Design Science Research (DSR) methodology, the team combined a low-code orchestration platform (n8n), a large language model (Google Gemini), and existing Google Workspace infrastructure to automate four processes: adviser matching, a secure academic-standing chatbot, compliance triage for data-analysis requests, and preliminary statistical auto-analysis. The pilot began in December 2025 and is approximately 90 percent complete. Two of the four workflows already run on live student data. Internal, non-independently audited estimates point to large reductions in turnaround time and an annual infrastructure cost of roughly ₱4,741, or about US$84, though formal validation remains pending. The project was separately recognized in the 2026 World's Universities with Real Impact (WURI) rankings, placing 31st in the Student Support and Engagement category. This paper offers one of the few documented accounts of a low-code, AI-orchestrated alternative to enterprise RPA built in-house at a resource-constrained Philippine HEI, and it sets out a concrete agenda for the empirical validation the system has not yet undergone.