NSF FF: Planning: Co-Designing an AI Tool to Strengthen Student Reasoning with Scientific Data

Award ID: 2627639

This FINDERS Foundry award strengthens students ability to interpret scientific graphs while helping them utilize AI tools responsibly as thinking partners rather than shortcuts. Many students struggle with graph interpretation, especially when graphs integrate multiple scientific ideas or require careful reasoning. This project will design a classroom tool to support clearer instructional strategies around AI, encouraging student questioning and verification of AI outputs. Educators, students, and families from a variety of school districts will collaborate to design a tool for responsible AI engagement, which improves reasoning skills, and supports stronger understanding of scientific data. This FINDERS Foundry award creates design specifications for an AIsupported tool that helps students analyze, critique, and revise scientific graphs. Technical design tasks include the codesign of workshops with educators and students, development of storyboards outlining graphreasoning workflows, and construction of metacognitive scaffolds which guide students through replotting data, evaluating trends, and identifying a wide variety of graphical representations. The project documents studentAI interactions to understand how learners use computational supports to interrogate graphical evidence and augment scientific reasoning. Outputs include detailed technical specifications, pilotready measures, and a development plan for future integration of the tool into secondary science instruction aligned with emerging AI literacy standards. The project is a design framework for AIenabled graph critique to enhance students analytical capacity while reinforcing the role of evidencebased interpretation 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