This $899,979 Project Grant award from the National Science Foundation's STEM Education program (CFDA 47.076) supports a three-year collaboration between the Concord Consortium and Perkins School for the Blind to create an accessible, AI-powered data exploration environment for blind and low-vision (BLV) K-12 students. The project aims to leverage a large language model and expertise in educational technology and BLV learning innovations to enable BLV students to interact with data through voice commands, sonification, and AI-generated audible descriptions. The goal is to transform the educational experience and broaden participation in data science and STEM fields. The project team will research and develop an AI-powered agent embedded in the NSF-funded Common Online Data Analysis Platform (CODAP) to facilitate accessible data exploration for BLV users. The project will employ an iterative development process, include co-design sessions with BLV users, and investigate the impact of interactive and generative technologies on BLV students' engagement and understanding of datasets. The project outputs will include the web-based, AI-powered agent integrated with CODAP, which will be made publicly available along with LLM training materials and research findings.