IBL News | New York
Professor Lorena A. Barba at George Washington University presented a new AI mentor at the institution’s School of Engineering & Applied Science, one that is both student-centered and faculty-led.
“What sets our approach apart is its focus on pedagogical design and cost-effectiveness. Unlike enterprise-wide solutions, the pay-as-you-go model could save institutions significant resources while offering greater customization,” Profesor Barba explained.
According to a July 2024 survey by the Digital Education Council, 86% of students already use AI in their studies.
“Most are using ChatGPT, and not very well. Our AI mentor addresses this reality by providing a customizable, course-specific tool that grounds AI responses in course materials,” Profesor Barba explained during a presentation [video | pdf document].
Key features of this AI mentor include:
• Instructor-controlled AI persona
• Integration of course resources
• Context-aware responses (via RAG)
• Flexible model selection (no vendor lock-in)
• Cost usage tracking via AI vendor dashboard
Professor Lorena A. Barba showcased the AI mentor’s interface with a live demo, showing how to add course resources, set the AI’s behavior through prompts, and moderate student interactions.
The demo included examples of the AI mentor responding to student queries, showcasing its ability to provide course-specific information and encourage critical thinking.
This pilot was conducted in collaboration with ibl.ai as the technical partner.
(Disclosure: ibl.ai is the parent company of iblnews.org news service).
On Friday, I presented to the @gwuengineering faculty my work on a course-level #AI mentor. By a recent survey, 86% of students already use AI in studies—mostly ChatGPT, and not very well. A course AI-mentor addresses this in a way that is both student-centered and faculty-led…
— Lorena Barba @labarba@fosstodon.org (@LorenaABarba) September 8, 2024