SBIR Phase II: Agentic AI Augmenting Qualitative Data Analysis

Award ID: 2417969

The broader impact/commercial potential of this Small Business Innovation Research (SBIR) Phase II project is a market-ready AI CoPilot for qualitative data collection, analysis, and evaluation in a single Software-as-a-Service (SaaS) platform with use cases as varied as academic research to human resource management. The research and development of this novel AI CoPilot for qualitative data will improve the accuracy and efficiency of qualitative data analytics while identifying potential biases in data and accelerating the process of analysis and discovery. The project aims to shift how qualitative data is leveraged in research and industry to offer more robust, real-time, and contextually relevant insights from qualitative data. An enhanced approach to analyzing qualitative data may result in more informed decision-making and higher quality outcomes across market sectors with clear societal impacts immediately evidence in educational institutions as well as in the delivery of healthcare informatics and market research providing timely data for wide swaths of society. The proposed project aims to develop a comprehensive Software-as-a-Service (SaaS) platform that integrates a proprietary Artificial Intelligence (AI)-enabled suite of qualitative data analysis tools with nuanced and contextually relevant analysis of qualitative data. The primary objective is optimization of a novel system which collects, structures, and stores unstructured data for subsequent analysis by both human and AI-enabled raters to increase accountability leading to higher quality outcomes and more informed decision-making. The core enabling technology includes dynamic dashboards, advanced analytics, and customer-relationship management (CRM) tools which integrate across the suite of qualitative analytic tools. The research will focus on refining the platform's architecture for scalability and integrating responsive proprietary AI models. The anticipated technical results include a robust, scalable platform capable of delivering accurate and reliable data analysis, significantly improving the workflow of data analysts in various fields. The methodology involves iterative testing, user feedback integration, and continuous enhancement of AI models to ensure the platform meets high standards of performance and usability This award reflects NSF's statutory mission and has been deemed worthy of support through evaluation using the Foundation's intellectual merit and broader impacts review criteria.

NSF Program Director: Lindsay Portnoy