Design and Implementation of a Dual-LLM Prescriptive ESG Reporting System in the Indonesian Palm Oil Industry

Niko Firzi Anansyah; Ratu Mutiara  Siregar; Andi Prayogi; Muhammad Akbar Syahbana Pane

doi:10.61255/decoding.v4i2.1404

Authors

Niko Firzi Anansyah Institut Teknologi Sawit Indonesia
Ratu Mutiara Siregar Institut Teknologi Sawit Indonesia
Andi Prayogi Institut Teknologi Sawit Indonesia
Muhammad Akbar Syahbana Pane Institut Teknologi Sawit Indonesia

DOI:

https://doi.org/10.61255/decoding.v4i2.1404

Keywords:

ESG, Information system, LLM, Palm oil sustainability, Prescriptive analytics

Abstract

Purpose – This study aims to develop an automated Environmental, Social, and Governance (ESG) reporting information system based on Large Language Model (LLM) for the palm oil industry to overcome low efficiency, data inconsistencies, and analysis limitations inherent in manual reporting processes.
Methods – This applied research employs the Design Science Research (DSR) paradigm, encompassing needs analysis, system design, implementation, and black-box testing. The system was developed using the Laravel MVC framework and integrated a Dual-LLM API failover architecture (Groq Llama 3 as primary and Gemini as backup). The case study was conducted at PT Surya Mata Ie.
Findings – The developed system successfully automated ESG indicator extraction and prescriptive narrative generation. It utilizes a Strict Weighting Rule, a programmatic safeguard capping the ESG score at 50.0 (as a proof-of-concept testing constraint) if Ganoderma infection exceeds a 20% threshold (supported by agronomic research). During prototype evaluation, this rule intercepted an overly optimistic raw LLM score of 60.0 and corrected it to 50.0. This demonstrates the system's capability to function as a risk-control mechanism, mitigating potential hallucination-driven score inflation and supporting mathematically accountable outputs.
Research implications – The implementation of this system significantly accelerates reporting workflows and serves as an early warning instrument for environmental risks, thereby enhancing real-time managerial decision-making and corporate transparency in complying with global sustainability standards.
Originality – This study pioneers the integration of a Dual-LLM failover mechanism within a Laravel framework tailored for the palm oil sector. It introduces a novel programmatic constraint approach in JSON object parsing to maintain strict mathematical accountability in AI-generated ESG drafts.

Abstract views: 12 ,

PDF downloads: 7

Downloads

Download data is not yet available.

References

T. Lim, “Environmental, social, and governance (ESG) and artificial intelligence in finance: State-of-the-art and research takeaways,” Artif. Intell. Rev., vol. 57, no. 4, p. 76, Feb. 2024, doi: 10.1007/s10462-024-10708-3.

T. Hoang et al., "ESG Reporting Lifecycle Management with Large Language Models and AI Agents," arXiv preprint, Mar. 2026, doi: 10.48550/arXiv.2603.10646.

N. Haryanti, A. Marsono, and M. A. Sona, “Strategi Implementasi Pengembangan Perkebunan Kelapa Sawit Di Era Industri 4.0” [Implementation Strategies for Palm Oil Plantation Development in the Industry 4.0 Era], J. Din. Ekon. Syariah, vol. 8, no. 1, pp. 76–87, Feb. 2021, doi: 10.53429/jdes.v8i1.146.

A. Cravero, A. Bustamante, M. Negrier, and P. Galeas, “Agricultural Big Data Architectures in the Context of Climate Change: A Systematic Literature Review,” Sustainability, vol. 14, no. 13, p. 7855, Jun. 2022, doi: 10.3390/su14137855.

I. H. Fadhlurrahman, Tanto, and M. H. Saputra, “Perancangan Sistem Informasi Monitoring Pelaporan Produksi Sawit Pada Koperasi Wahana Agung” [Design of Palm Oil Production Reporting Monitoring Information System at Koperasi Wahana Agung], J. Elektron. List. Dan Teknol. Inf. Terap., vol. 7, no. 1, pp. 22–32, Jun. 2025, doi: 10.37338/alti.v7i1.452.

F. Erlina, S. Samsudin, and R. A. Putri, “Sistem informasi monitoring pengangkutan dan pelaporan hasil panen kelapa sawit pada PTPN IV unit berangir” [Information System for Monitoring Transportation and Reporting of Palm Oil Harvests at PTPN IV Unit Berangir], Jurnal Sistem Informasi, vol. 12, no. 1, pp. 33–42, Dec. 2024.

H. Naveed et al., “A Comprehensive Overview of Large Language Models,” ACM Trans. Intell. Syst. Technol., vol. 16, no. 5, pp. 1–72, Oct. 2025, doi: 10.1145/3744746.

S. Shahriar, M. G. Corradini, S. Sharif, M. Moussa, and R. Dara, “The role of generative artificial intelligence in digital agri-food,” J. Agric. Food Res., vol. 20, p. 101787, Apr. 2025, doi: 10.1016/j.jafr.2025.101787.

D. O. Sihombing, “Implementasi Natural Language Processing (NLP) dan Algoritma Cosine Similarity dalam Penilaian Ujian Esai Otomatis” [Implementation of Natural Language Processing (NLP) and Cosine Similarity Algorithm in Automated Essay Exam Assessment], J. Sist. Komput. Dan Inform. JSON, vol. 4, no. 2, p. 396, Dec. 2022, doi: 10.30865/json.v4i2.5374.

J. Bailey et al., “Leveraging Generative AI for Data Analysis in Farm Management,” Appl. Eng. Agric., vol. 41, no. 5, pp. 505–519, 2025, doi: 10.13031/aea.16429.

J. Tummers, A. Kassahun, and B. Tekinerdogan, “Reference architecture design for farm management information systems: a multi-case study approach,” Precis. Agric., vol. 22, no. 1, pp. 22–50, Feb. 2021, doi: 10.1007/s11119-020-09728-0.

M. F. Al-Adhim and G. S. Dewi, “Sistem Monitoring IoT Smart Farm Berbasis Web dengan Integrasi Template Dashboard Bootstrap dan Laravel 10” [Web-Based IoT Smart Farm Monitoring System with Bootstrap Dashboard Template Integration and Laravel 10], COMSERVA J. Penelit. Dan Pengabdi. Masy., vol. 4, no. 7, pp. 1973–1981, Nov. 2024, doi: 10.59141/comserva.v4i7.2595.

A. A. Bimantara and R. D. Gunawan, “Sistem Monitoring Produksi Menggunakan Laravel Dan Cork-Bootstrap” [Production Monitoring System Using Laravel and Cork-Bootstrap], J. Inf. Technol. Softw. Eng. Comput. Sci. ITSECS, vol. 1, no. 4, pp. 143–153, Oct. 2023, doi: 10.58602/itsecs.v1i4.73.

G. Surono, Y. Suhanda, and F. Alfiah, “Penerapan MVC Arsitektur Pada Sistem Informasi Monitoring Pada Divisi Produksi Menggunakan Laravel Framework” [Application of MVC Architecture in Production Division Monitoring Information System Using Laravel Framework], J. Sensi, vol. 8, no. 2, pp. 180–189, Aug. 2022, doi: 10.33050/sensi.v8i2.2423.

Z. K. Daulay, S. Suendri, and H. Santoso, “Penerapan Sistem Informasi Monitoring Hasil Panen Dan Produksi Di PTPN III Kebun Sei Baruhur” [Implementation of Harvest and Production Monitoring Information System at PTPN III Kebun Sei Baruhur], Journal of Science and Social Research, vol. 7, no. 3, pp. 980–986, Aug. 2024, doi: 10.54314/jssr.v7i3.2096.

D. A. Rina Sari and M. D. Irawan, “Implementation of Key Performance Indicators in the Palm Oil Harvest Monitoring Information System,” Green Intell. Syst. Appl., vol. 5, no. 2, pp. 150–163, Aug. 2025, doi: 10.53623/gisa.v5i2.782.

S. Shool, S. Adimi, R. Saboori Amleshi, E. Bitaraf, R. Golpira, and M. Tara, “A systematic review of large language model (LLM) evaluations in clinical medicine,” BMC Med. Inform. Decis. Mak., vol. 25, no. 1, p. 117, Mar. 2025, doi: 10.1186/s12911-025-02954-4.

Rizky Delianngi, Ratu Mutiara Siregar, Nurliana, Muhammad Akbar Syahbana Pane, Phaklen Ehkan, and Andi Prayogi, “Performance Evaluation of YOLOv9, YOLOv10, and YOLOv11 for Real-Time Early Detection of Ganoderma Boninense in Oil Palm,” J. RESTI Rekayasa Sist. Dan Teknol. Inf., vol. 10, no. 2, pp. 429–440, Apr. 2026, doi: 10.29207/resti.v10i2.7479.

A. Herdiansah, R. I. Borman, and S. Maylinda, “Sistem Informasi Monitoring dan Reporting Quality Control Proses Laminating Berbasis Web Framework Laravel” [Web-Based Monitoring and Quality Control Reporting Information System for Laminating Process Under Laravel Framework], J. Tekno Kompak, vol. 15, no. 2, p. 13, Aug. 2021, doi: 10.33365/jtk.v15i2.1091.

Y. Wang and I. J. Yusof, “Expert consensus and reliability validation of the portfolio assessment guideline for Chinese practical writing: An empirical study based on fleiss’ kappa,” BenchCouncil Trans. Benchmarks Stand. Eval., vol. 5, no. 4, p. 100248, Dec. 2025, doi: 10.1016/j.tbench.2025.100248.

L. Ouyang et al., “Training language models to follow instructions with human feedback,” 2022, arXiv. doi: 10.48550/ARXIV.2203.02155.

J. Wei et al., “Chain-of-Thought Prompting Elicits Reasoning in Large Language Models,” 2022, arXiv. doi: 10.48550/ARXIV.2201.11903.

K. Singhal et al., “Large language models encode clinical knowledge,” Nature, vol. 620, no. 7972, pp. 172–180, Aug. 2023, doi: 10.1038/s41586-023-06291-2.

M. Li, A. Basit, A. Javed, X. Song, and Y. Ge, “Generative artificial intelligence and ChatGPT in agriculture supply chain management: a systematic literature review and future research agenda,” Br. Food J., vol. 128, no. 13, pp. 121–141, Nov. 2025, doi: 10.1108/BFJ-05-2025-0720.

J. Gallifant et al., “The TRIPOD-LLM reporting guideline for studies using large language models,” Nat. Med., vol. 31, no. 1, pp. 60–69, Jan. 2025, doi: 10.1038/s41591-024-03425-5.

S. Chen et al., “The effect of using a large language model to respond to patient messages,” Lancet Digit. Health, vol. 6, no. 6, pp. e379–e381, Jun. 2024, doi: 10.1016/S2589-7500(24)00060-8.

R. Dara, S. M. Hazrati Fard, and J. Kaur, “Recommendations for ethical and responsible use of artificial intelligence in digital agriculture,” Front. Artif. Intell., vol. 5, p. 884192, Jul. 2022, doi: 10.3389/frai.2022.884192.