Full text loading...
The adoption of Generative Artificial Intelligence (AI) within highly regulated industries poses unique technical and governance challenges, particularly when strict data sovereignty requirements prohibit the use of cloud-based AI services. In the Indonesian upstream oil and gas sector, SKK Migas operates under a mandate of zero data exfiltration, requiring all analytical and AI workloads to be executed entirely within on-premise infrastructure.
This paper presents the design, implementation, and empirical evaluation of an on-premise Generative AI system developed to support two critical operational needs: (1) the interpretation of complex regulatory documentation and (2) analytical querying of large-scale structured reserve databases. The study was conducted between July and December 2025 and focuses on practical architectural decisions made under severe computational constraints.