Please use this identifier to cite or link to this item: https://hdl.handle.net/10419/330340 
Year of Publication: 
2025
Series/Report no.: 
Working paper from the Security Management degree program at the NBS Northern Business School Hamburg No. 3/2025
Publisher: 
NBS Northern Business School, Institute for Intelligence and Security Management (I2SM), Hamburg
Abstract: 
The creation of an Intelligence Collection Plan (ICP) is a key step at the intersection of the direction phase (see Figure 1) and Intelligence Requirement Management (IRM) within the intelligence cycle. This is intended to enable the systematic structuring of information requirements and the targeted management of research and reconnaissance. In practical application, however, there are challenges in terms of time, content, and technology that can lead to delays, inconsistencies, and quality losses. The ICP-LLM is a tool that uses large language models (LLMs) to automatically generate the lower levels of an ICP-specific intelligence requirements (SIRs) and essential elements of information (EEIs). This speeds up and simplifies the creation of ICPs. The aim of this working paper is to shed light on the background to the development of ICP-LLM. It also takes a look at how the tool's usefulness and applicability are being experimentally evaluated as part of a course at the NATO Civil-Military Cooperation Centre of Excellence (CCOE). The aim is to investigate the extent to which the use of ICP-LLM makes the creation of ICPs more efficient, improves structural quality, and is considered relevant to practice by users. The results will provide insight into whether and to what extent LLM-supported assistance systems can offer added value for use in an intelligence context. In a further step, the tool will be put to the test in a research project at I2SM on organized crime as part of crime analysis.
Additional Information: 
The German version of Working Paper No. 3/2025 is available here: https://hdl.handle.net/10419/330339
Document Type: 
Working Paper

Files in This Item:





Items in EconStor are protected by copyright, with all rights reserved, unless otherwise indicated.