Automation in Military Intelligence Workflows: Integrating RPA, Databases, and Offline LLMs

Authors

DOI:

https://doi.org/10.3849/aimt.02077

Keywords:

Artificial Intelligence, Robotic Process Automation, military intelligence, Large Language Models, automated data processing, intelligence requirements management

Abstract

This article examines the integration of Robotic Process Automation (RPA), a structured PostgreSQL database, and an offline Large Language Model (LLM) within a military Intelligence Requirements Management and Collection Management (IRM&CM) workflow. Using a comparative case study of two intelligence staffs – one employing intelligent automation and one relying on traditional methods – the study evaluates impacts on processing speed, accuracy, analytical quality, and workload. Results show that automation substantially improves report throughput, reduces procedural errors, and enables faster, more coherent intelligence production while maintaining analyst oversight. The findings demonstrate that secure, offline Artificial Intelligence (AI) combined with RPA can significantly enhance lower-echelon intelligence operations without compromising doctrinal standards or analytical integrity.

References

ATP 2-33.4: Intelligence Analysis [online]. Washington: Department of the Army, 2020 [viewed 2025-11-15]. Available from: https://www.utahmilitia.org/members/lib/adp/atp2-33-4.pdf

FM 2-0: Intelligence [online]. Washington: Department of the Army, 2023 [viewed 2025-11-15]. Available from: https://ia902808.us.archive.org/3/items/2023-2024-us-army-fm/ARN39259-FM_2-0-000-WEB-2.pdf

Intelligence, Counter-Intelligence and Security Support to Joint Operations [online]. London: MOD, 2023 [viewed 2025-11-15]. Available from: https://assets.publishing.service.gov.uk/media/653a4b0780884d0013f71bb0/JDP_2_00_Ed_4_web.pdf

Concept of the Build-up of the Armed Forces of the Czech Republic 2035 (in Czech) [online]. 2024 [viewed 2025-11-18]. Available from: https://mocr.mo.gov.cz/assets/informacni-servis/zpravodajstvi/kvacr_2035_final.pdf

Automated Data Processing: Basics, Methods & Business Applications [online]. 2025 [viewed 2025-11-18]. Available from: https://infomineo.com/blog/automated-data-processing-basics-methods-business-applications/

FAGBENLE, E., J.Z. KHAMENEH and G. AJAYI. Reducing Administrative Burden in Primary Care Through Intelligent Workflow Automation. International Journal of Science, Architecture, Technology and Environment, 2024, 1(7), pp. 164-184. https://doi.org/10.63680/ijsate032487.012.

KAHN, P., et al. Teacher Agency and Generative Artificial Intelligence: Teaching in Higher Education as a Responsive Cultural Activity. Learning, Media and Technology [online]. 2025 [viewed 2025-11-20]. https://doi.org/10.1080/17439884.2025.2575993.

ZHAO, X., Y. YANG, Y. NIU and X. LI. Uncertainty-Aware Multi-Modal Learning for Autonomous Pallet Handling in Dynamic Warehouse Scenarios. IEEE Access, 2025, 13, pp. 168732-168742. https://doi.org/10.1109/ACCESS.2025.3613729.

GREEN, J.M. Establishing System Measures of Effectiveness [online]. 2001 [viewed 2026-11-23]. Available from: https://apps.dtic.mil/sti/tr/pdf/ADA405408.pdf

Intelligence, Drones, and Artificial Intelligence: The Czech Army Enters a New Era of Information [online]. 2024 [viewed 2025-11-23]. Available from: https://www.czdefence.com/article/intelligence-drones-and-artificial-intelligence-the-czech-army-enters-a-new-era-of-information

STODOLA, P. Utilisation of Artificial Intelligence in Natural Language Processing: Text Categorisation [part of the project report]. Analysis of the Use of Artificial Intelligence in Open Source Intelligence OYUOB20240002, 2024-2026 [Research project].

HASTIE, T., R. TIBSHIRANI and J. FRIEDMAN. The Elements of Statistical Learning. New York: Springer, 2009. ISBN 978-0-387-84857-0.

HOROWITZ, M.C. and L. KAHN. Bending the Automation Bias Curve: A Study of Human and AI-Based Decision Making in National Security Contexts. International Studies Quarterly, 2024, 68(2), sqae020. https://doi.org/10.1093/isq/sqae020.

HOQUE, A., et al. AI and Machine Learning in Banking: Driving Efficiency and Innovation. Well Testing, 2025, 34(S3), pp. 79-98. ISSN 1004-4388.

HEINONEN, O. Design and Implementation of a Machine Learning-Based Tool and a Robotic Process Automation Workflow for SAP S/4HANA Item Setusp [Master’s Thesis] [online]. LUT University, 2025 [viewed 2025-12-07]. Available from: https://lutpub.lut.fi/bitstream/handle/10024/170551/Diplomityo_Heinonen_Otto.pdf?sequence=1&isAllowed=y

RUSSELL, S. and P. NORVIG. Artificial Intelligence: A Modern Approach. 4th ed. Harlow: Pearson, 2021. ISBN 0-13-461099-7.

Too Much Data, Too Few Analysts: How AI Offers a 'Force Multiplier' for Intelligence Analysts [online]. 2025 [viewed 2025-12-07]. Available from: https://defensescoop.com/2025/11/12/too-much-data-too-few-analysts-how-ai-offers-a-force-multiplier-for-intelligence-analysts/

Downloads

Published

18-08-2026

Issue

Section

Case study

Categories

How to Cite

Kačmařík, O., Vašíček, R., Podoba, J., & Říha, J. (2026). Automation in Military Intelligence Workflows: Integrating RPA, Databases, and Offline LLMs. Advances in Military Technology, 375-394. https://doi.org/10.3849/aimt.02077

Similar Articles

1-10 of 370

You may also start an advanced similarity search for this article.