<mods:mods version="3.3" xsi:schemaLocation="http://www.loc.gov/mods/v3 http://www.loc.gov/standards/mods/v3/mods-3-3.xsd" xmlns:mods="http://www.loc.gov/mods/v3" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance"><mods:titleInfo><mods:title>MARC Records with ChatGPT: Lessons Learned</mods:title></mods:titleInfo><mods:name type="personal"><mods:namePart type="given">John</mods:namePart><mods:namePart type="family">Kimbrough</mods:namePart><mods:role><mods:roleTerm type="text">author</mods:roleTerm></mods:role></mods:name><mods:abstract>Georgetown University undertook a small pilot project this summer to test ChatGPT’s ability to produce MARC records for items in various formats. I would like to share some lessons we learned, including what the AI got right, frequent errors made by ChatGPT, and workflows for proofreading records as a team. The lessons have helped inform us about using the Alma AI Metadata Assistant, and to evaluate its output.</mods:abstract><mods:classification authority="lcc">Alma</mods:classification><mods:classification authority="lcc">General Topics</mods:classification><mods:originInfo><mods:dateIssued encoding="iso8601">2024-10-25</mods:dateIssued></mods:originInfo><mods:genre>Conference or Workshop Item</mods:genre></mods:mods>