ACRL Artificial Intelligence (AI) Interest Group

 View Only
last person joined: 23 hours ago 

To provide a forum for discussing the impact of AI on libraries and related topics, facilitating the exchange of ideas, best practices, and collaborative initiatives among library professionals.
Community members can post as a new Discussion or email ALA-ACRL-AI-IG@ConnectedCommunity.org.
Before you post: please note job postings are prohibited on ALA Connect. Please see the Code of Conduct for more information.
  • 1.  AI agents searching library databases

    Posted Aug 04, 2025 02:01 PM

    Has anyone experimented with having AI agents 'go into' your databases and search for articles? Apparently they can do that now. (Actually I think they've been able to, in theory, for a while). What makes things different now is it's a freely available feature, at least with ChatGPT. Therefore making it more likely that students will come across it and try it. 



    ------------------------------
    Sarah Hood
    Research & Instruction Librarian
    Santa Fe Community College
    She/Her/Hers
    ------------------------------


  • 2.  RE: AI agents searching library databases

    Posted Aug 04, 2025 02:12 PM
    It seems to me that AI agents would not be able to access most databases because they are protected by paywalls. I do know there are databases where you can "switch on" AI agents to assist with searches. But ChatGPT should only be able to gain entry to open access resources, not library databases that require institutional access or credentials. 

    Ashley Tschakert Foertmeyer, MSLIS
    Teaching and Engagement Librarian
    Corns 114
    Ohio Wesleyan University
    Pronouns: she/her/hers

    ajtschakertfoertmeye@owu.edu
    740-368-3558 (office)






  • 3.  RE: AI agents searching library databases

    Posted Aug 04, 2025 02:36 PM
    Hi

    I have tried with ChatGPT agent. I asked it to go into Ebscohost databases and summarize top ranked papers on topic x.

    During the login process, it would hand over control to the human. OpenAI claims to be not logging/screenshotting when the human takes over. Once the human hands over to the agent, the agent will continue it's task

    I also managed to ask it to go into Scopus and do research on X. Again, it worked as expected, though time was up after just 30 minutes.

    Thus far though, I don't think it is very good. It is extremely slow, cross domain errors, the agent can get confused when there are too many links and ends up just "googling" sometimes  (e.g. Looking at your Primo).

    So far, I don't think i have seen it use full-text from our databases either. Because it is so slow, I think it managed to only summarise maybe 10 articles from Scopus because the 30 minute time was up.

    Oh and don't brother to try using Google Scholar via library link, it's totally blocked.

    At this stage, I feel academic (not general) deep research tools are still better than just straight out using agent to search databases. That said SciSpace Agents seem to do very well.

    In the long run, I expect a blend of techniques, for example there is little point doing a "live browse" of website x, when your search engine is setup with direct access via a vector database, which is much faster and more stable.

    Still, I can see agents being called for one particular use case, download full-text via institutional entitlements.







    Regards