In the summer of 2024, ASU Library undertook a pilot project using the Artificial Intelligence (AI) tool ChatGPT. The purpose of this pilot was to investigate the suitability of ChatGPT to facilitate discoverability and curation of digital collections within the ASU Library repository ecosystem. A considerable challenge at ASU Library is the large amount of digital material that needs to be described, at least minimally. Our resources do not currently permit a dedicated position to create metadata at the scale required. Therefore, ASU Library took part in the Arizona State University’s AI Innovation Challenge, a university-wide initiative to grant free ChatGPT Enterprise licenses to ASU faculty, staff, and students with ideas to positively impact the future of education. Our project posed the question of whether ChatGPT can positively impact our ability to generate accurate metadata that aligns with relevant best practices. For this project, we used an existing archival collection of government documents, for which human-created metadata already exists. We compared the AI generated metadata to manually-created metadata to test the relevancy of outputs and determine the minimum level of oversight. Through participation in this Innovation Challenge, we wanted to determine if the metadata generated through AI is within a tolerable level of variance from the existing metadata and thus can be expanded to other collections.