Sbir fast-track: a proprietary argumentation heuristic framework for structured reasoning and logic evaluation in presentation authoring

The National Science Foundation awarded Becise LLC a $1,554,830 cooperative agreement on July 1, 2026, under the NSF Technology, Innovation, and Partnerships program (CFDA 47.084) to develop a proprietary argumentation heuristic framework for structured reasoning and logic evaluation in presentation authoring software.

The project delivers a multi-agent orchestration system that transforms presentation software from a passive design tool into an active thinking partner by capturing full-sentence arguments rather than fragmented bullet points and validating logical soundness before slide design. The innovation embeds decades of proprietary research into prescriptive rules for clear argumentation, implemented through a proprietary evaluation engine that critiques user input to improve both clear reasoning and engaging rhetoric. The technology targets data-heavy sectors including marketing and risk analysis, where clear communication drives commercial success, and follows a software-as-a-service business model designed to improve through learning from expert feedback.

Work is performed in Evanston, Illinois. The period of performance runs from July 1, 2026, through June 30, 2029. Anticipated technical results include a validated framework for refining agent orchestration in AI-driven presentation critique systems.

Abstract

The broader/commercial impact of this small business innovation research (sbir) fast-track project introduces a technical innovation in cognitive science and human-AI collaboration that transforms software from a passive design tool into an active thinking partner. By capturing full-sentence arguments rather than fragmented bullet points, the technology ensures that the underlying logic of a presentation is sound before a single slide is designed. The primary market opportunity targets data-heavy sectors like marketing and risk analysis, where clear communication is a critical factor for commercial success. The business model follows a software-as-a-service approach, providing a durable advantage through a proprietary system that improves as IT learns from expert feedback. This small business innovation research (sbir) fast-track project addresses the technical challenge of translating rules for creating clear presentations into objective heuristics implemented by an automated system of coaches. Current AI presentation platforms focus on aesthetic improvement, and when they critique or create content, they rely on generic writing coaching combined with rhetorical styles learned from ineffective presentations. In contrast, this project translates decades of proprietary research and active application into prescriptive rules for clear argumentation for presentations and embeds those rules in a novel multi-agent orchestration layer. The research objectives include the development of a proprietary evaluation engine that critiques user input to improve both clear reasoning (e.g., expressing claims as full sentences instead of bullets) and engaging rhetoric (for example, positioning an argument to match a goal that the audience cares about). The anticipated technical results include a validated framework for refining agent orchestration based on expert-led feedback loops and automatically rendered slides from a structured argument interface. This work advances the field of human-centered artificial intelligence by creating an architecture that prioritizes structured thinking over simple generative output, providing a new foundation for high-stakes organizational communication and advancing understanding of computer-supported collaborative work. 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.- subawards are not planned for this award.