1887

Abstract

Summary

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.

Loading

Article metrics loading...

/content/papers/10.3997/2214-4609.202639124
2026-03-09
2026-02-07
Loading full text...

Full text loading...

References

  1. A. N.Hadie, I.Tahyudin, and T.Hariguna, “Enhancing Accessibility in Local Government Data Portals via Retrieval- Augmented Generation: A Case Study on Satu Data Indonesia in Banyumas Regency”, J. Tek. Inform. (JUTIF), vol. 6, no. 4, pp. 2420–2433, Sep. 2025.
    [Google Scholar]
  2. Gao, Y., Xiong, Y., Gao, X., Jia, K., Pan, J., Bi, Y., Dai, Y., Sun, J., Wang, M., & Wang, H., 2023. Retrieval-Augmented Generation for Large Language Models: A Survey, arXiv:2312.10997.
    [Google Scholar]
  3. Mahjour, S.K. & Mahjour, S.S., 2025. Intelligent Reservoir Decision Support: An Integrated Framework Combining Large Language Models, Advanced Prompt Engineering, and Multimodal Data Fusion for Real-Time Petroleum Operations, arXiv:2509.11376.
    [Google Scholar]
  4. SKK Migas, 2020. Indonesia’s Framework of Petroleum Resources (IFPR) and Regulatory Documents, Internal regulatory documentation, SKK Migas, Jakarta, Indonesia.
    [Google Scholar]
/content/papers/10.3997/2214-4609.202639124
Loading
/content/papers/10.3997/2214-4609.202639124
Loading

Data & Media loading...

This is a required field
Please enter a valid email address
Approval was a Success
Invalid data
An Error Occurred
Approval was partially successful, following selected items could not be processed due to error