CNI: Coalition for Networked Information

  • About CNI
    • Membership
    • Staff
    • Steering Committee
    • CNI Awards
    • History
    • CNI News
  • Membership Meetings
    • Next Meeting
    • Past Meetings
    • Future Meetings
  • Topics
  • Events & Projects
    • Membership Meetings
    • Workshops & Projects
    • Other Events
    • Event Calendar
  • Resources
    • CNI Publications
    • Program Plan
    • Pre-Recorded Project Briefing Series
    • Videos & Podcasts
    • Executive Roundtables
    • Follow CNI
    • Historical Resources
  • Contact Us

Discovery and Use Reimagined: Connecting Scholarly Collections and Artificial Intelligence Workflows

Home / Topics / Artificial Intelligence / Discovery and Use Reimagined: Connecting Scholarly Collections and Artificial Intelligence Workflows

November 17, 2025

Redesigning Discovery for AI-First Users

Rosalyn Metz
Chief Technology Officer, Libraries and Museum
Emory University

Miri Botzer
Vice President, Product Innovation, Academic & Government
Clarivate

Allen Jones
Senior Director of Digital Libraries & Technical Services
The New School
 

As students and researchers begin more of their academic work inside artificial intelligence (AI) systems rather than library portals, traditional models of discovery face a profound challenge. For libraries, this shift poses both a risk and an opportunity: discovery must evolve to meet users where they are. This session will explore how discovery can be reimagined for an AI-first environment. It will examine how emerging standards, such as the Model Context Protocol (MCP), can be used to embed library services directly into user workflows and consider possibilities like Generative Engine Optimization (GEO), which may influence how scholarly content becomes visible in AI-driven responses. At the heart of this shift is the library’s core role as the safeguard of scholarly sources, entitlements, and context, ensuring that even as technologies evolve, trust and integrity remain central.

https://rosalynmetz.substack.com/p/bots-barriers-and-the-future-of-the 


Improving Learning and Research by Connecting Collections and LLMs Through Model Context Protocol

Dan Cohen
Dean of the Library, Professor of History
Northeastern University

Evan Simpson
Associate Dean for Experiential Learning and Academic Engagement
Northeastern University
 

This year, the Northeastern University Library (NUL) developed and launched an MCP (Model Context Protocol) server and associated plugin for the AI chatbot Claude. For academic requests, NUL’s enhancement of Claude makes extensive use of library resources, such as peer-reviewed articles, rather than the web resources normally consulted by LLMs through retrieval-augmented generation (RAG). Early testing of this combination has seen not only an improved experience for students and faculty seeking relevant library materials, but has sparked some new ideas for supporting teaching and assisting in the genesis and lifecycle of research.

https://newsletter.dancohen.org/archive/the-librarys-new-entryway/

Share this:

  • Click to share on Facebook (Opens in new window) Facebook
  • Click to share on LinkedIn (Opens in new window) LinkedIn
  • Click to share on Mastodon (Opens in new window) Mastodon
  • Click to share on Bluesky (Opens in new window) Bluesky
  • Click to share on X (Opens in new window) X

Filed Under: Artificial Intelligence, CNI Fall 2025 Project Briefings, Digital Libraries, Emerging Technologies, Information Access & Retrieval, Metadata, Project Briefing Pages
Tagged With: cni2025fall, Project Briefings & Plenary Sessions

Last updated:  Monday, November 17th, 2025

 

Contact Us

1025 Connecticut Ave, NW #1200
Washington, DC 20036
202.296.5098

Contact us
Copyright © 2025 CNI

  • Copyright Policy
  • Privacy Policy
  • Site map

Keeping up with CNI

CNI-ANNOUNCE is a low-volume electronic forum used for information about the activities and programs of CNI, and events and documents of interest to the CNI community.
Sign up

Follow CNI

LinkedInBlueSkyFacebookTwitterYouTubeVimeoMastodon

A joint project