Much of our cultural legacy remains hidden in documents that traditional OCR cannot read and digital platforms struggle to surface. This session explores how one library is using emerging AI models to extract text from heavily degraded documents and historic handwriting, combined with modern development approaches to present these materials in new ways. Designed for librarians, archivists, and digital humanities practitioners, attendees will gain practical knowledge applicable to their own collections, regardless of technical background.
Learning Objective(s): 1) Identify AI tools beyond chat models, such as vision language models, that can extract text from degraded documents and historic handwriting; 2) Describe modern 'vibe-based' development approaches that lower technical barriers for creating digital collection interfaces; and 3) Evaluate how these emerging tools and techniques might be applied to cultural heritage materials in their own organizations.
