A Large Language Model-Assisted Organizational Decision Support System Integrating Organizational Data with Management Frameworks

Organizations generate structured and unstructured evidence across workforce activities, projects, assessments, reports, and managerial communication, yet these data are often fragmented across different organizational systems. This study presents IntellicaHR, an Organizational Decision Support System assisted by Large Language Models. The system transforms everyday organizational activities into structured indicators and semantic evidence that can support analysis across organizational and management levels. The McKinsey 7S Framework organizes the collected evidence across key organizational dimensions, whereas Deming’s System of Profound Knowledge guides executive-level interpretation. We evaluated the proposed system through three literature-grounded synthetic organizational scenarios, along with supplementary analyses of its semantic-classification and executive-interpretation components. The scenarios produced distinct organizational profiles and role-specific decision-support outputs. An exploratory evaluation of the semantic-classification component showed substantial repeatability, robustness to prompt reformulation, and 95.0% agreement with human-derived sentiment labels, but it was not organization-specific validation. In a blinded human evaluation, 16 participants assessed three alternative executive interpretations: a descriptive Business Intelligence baseline, a generic Large Language Model interpretation, and the proposed Deming-grounded interpretation. The Deming-grounded interpretation received the highest overall ratings and significantly outperformed the Business Intelligence baseline, but not the generic Large Language Model condition. These findings support functional and interpretive coherence without establishing real-world diagnostic validity or organizational effectiveness.