Project Grant 2507879

This Project Grant award from the National Science Foundation (NSF) under the Technology, Innovation, and Partnerships (TIP) program (CFDA 47.084) provides $305,000 to Across AI, Inc. to develop a novel AI framework that integrates algorithmic logical reasoning with machine learning models to enhance the analysis of unstructured data. The broader commercial impact of this Small Business Innovation Research (SBIR) Phase I project is to transform enterprise knowledge work by improving how businesses analyze and act on unstructured data, initially targeting enterprise sales processes. The research aims to investigate key questions around whether a structured, logic-driven AI system can outperform end-to-end language model-based methods, how to design AI workflows to enhance user trust and explainability, and what interaction models best support knowledge workers in integrating AI-driven insights. The project will evaluate the framework's effectiveness by measuring its performance against state-of-the-art AI systems in real-world business tasks, with the goal of demonstrating improvements in reliability, usability, and user adoption to lay the foundation for scalable AI-driven automation in knowledge-intensive industries.