Publication Type
Presentation
Version
publishedVersion
Publication Date
10-2026
Abstract
At SMU Libraries, after a year of experimentation, user testing, and preparation, we have just launched an AI-assisted chatbot to handle Tier 1 questions – will the library be open this weekend, where can I find printers, what workshops does the library offer, etc. While this can be thought of as a technology-forward project, we hope to illustrate how the human elements were essential to elevate the project. Throughout this journey, while learning the ins and outs of new technologies, we placed more emphasis on user-centred service design and we will show how other libraries can do so as well.
We started our project by conducting interviews and focus group discussions to investigate users’ preferences, e.g., how would they like information to be presented, user expectations when interacting with a chatbot, etc. Then, we focused our development on melding the library’s expectations of the chatbot with the users'. Before rollout, we engaged our users once again, collecting their experiences in the form of a journal wherein we asked them to detail their interactions – noting down how it made them feel, and how we could improve, etc. This gave us a wealth of feedback to analyse and work on – either to improve the chatbot through technical tweaks behind the scenes or inform how we would plan change management and conduct user education. Having just rolled out our chatbot, we are still seeking feedback from broader community users and are eager to understand their experiences and usage patterns.
Our presentation will showcase how we integrated our user-first approach to our project as well as in the technical design of the AI chatbot. We will highlight some features of Microsoft Copilot Studio which we utilised to accomplish our goals, go into more details of how our users influenced the design, and share lessons we learned throughout this project.
Keywords
Automation, library services, chatbot, design thinking, human-centered, digital transformation, SMU Libraries, Microsoft Copilot Studio
Discipline
Artificial Intelligence and Robotics | Library and Information Science
Publication
Libraries for Tomorrow Conference 2026: The Future is Now – Adapting to Exponential Change, October 27-28
First Page
1
Last Page
15
City or Country
Singapore
Embargo Period
10-29-2026
Citation
SEAH, Samantha and LI, Zhenyan.
User-first approach to designing a library AI chatbot. (2026). Libraries for Tomorrow Conference 2026: The Future is Now – Adapting to Exponential Change, October 27-28. 1-15.
Available at: https://ink.library.smu.edu.sg/library_research/255
Creative Commons License

This work is licensed under a Creative Commons Attribution-NonCommercial-No Derivative Works 4.0 International License.
Additional URL
https://las.org.sg/conference/