AI Knowledge Bytes : Artificial Intelligence in Libraries Lunch ‘n Learn Series

Maintaining up-to-date and accurate information on electronic resources is a constant challenge, as resources merge or change hands, vendors acquire one another, marketing brings name changes, and schools negotiate bespoke packages. Greg Argo, Open Education & Affordable Content Librarian at Minitex, and practicum student Simon Deutsch will share a project addressing outdated records in Minitex’s Cooperative Purchasing and Electronic Resources Services (CPERS) database and workflows. Simon created an automated process—using JSON prompting, OpenRefine, Python scripting, and the Claude API—that reviewed more than 1,400 e-resource records, all without advanced coding skills. This session will highlight both the technical methods for wrangling AI tools and the implications for improving data quality and front-end services, offering takeaways for librarians interested in applying similar AI-driven approaches to their own data management challenges.

Theresa Berger (she/her) is Digital Library Services Librarian at the University of Minnesota, where she oversees digitization and digital collections development for Archives and Special Collections. This presentation will discuss ways in which a closed ChatGPT model can be used to generate alt text (alternative text) in archival image collections, using a "human-in-the-loop" approach. Theresa will highlight both strengths and weaknesses of the tool, as well as suggestions for overall workflows, showing ways in which AI can be used to shift (not replace) resources in an effort to better serve our users, stakeholders, and our communities.

Artificial intelligence features are increasingly appearing in library databases—sometimes as opt-in options, sometimes by default. How can library professionals engage proactively to ensure these tools align with our values? This session introduces the REACT Framework developed at Loyola Marymount University, a model we’ve explored at Minitex, and invites discussion on evaluating AI features in library databases.

This presentation explores the use of Microsoft Copilot to create engaging activities and assessments for Open Educational Resources (OER). By leveraging Copilot's AI capabilities, content gaps can be identified and bridged, ensuring a comprehensive and cohesive learning experience for students. The session provides practical insights and strategies for educators looking to enhance their OER with AI-driven solutions.

In an era where artificial intelligence is reshaping communication, access, and our daily lives, it’s crucial that we don’t lose sight of the people at the center. This talk explores the intersection of AI and accessibility, and why human judgment, empathy, and oversight are more important than ever.

In this session, we’ll dive into:

• How AI tools are being used to improve accessibility (and where they fall short)
• Real-world challenges that arise when AI replaces or overshadows human input
• Best practices for designing AI systems that include people — not push them aside
• Practical strategies for keeping people “in the loop” so that technology empowers, rather than excludes

Whether you’re a designer, developer, educator, policy advocate, or simply curious about the future of technology, you’ll come away with insight and actionable ideas for building more inclusive AI-powered systems.
 

Join Ninh Tran and Greta Bahnemann as they share their experiences using AI transcription for digital collection items. TranscribeAI is a new tool developed at Minitex that uses Google Gemini to transcribe typed, handwritten, and mixed-text documents. By automatically downloading items from digital repositories (e.g., Minnesota Digital Library) and using metadata to provide context, TranscribeAI produces highly accurate transcripts while reducing staff time and costs. This session will highlight the challenges of traditional OCR and manual transcription, demonstrate how TranscribeAI addresses them, and share best practices for integrating AI-generated transcripts into library workflows. Attendees will learn how AI-driven transcription enhances accessibility, improves discovery through keyword-searchable text, and preserves the cultural integrity of historical documents. We will also discuss lessons learned from recent pilot projects, including the importance of human review and quality assurance. Join us to explore how TranscribeAI can transform your library’s digital collections by increasing discoverability and broadening access for all users.