Professor Lorena A. Barba at George Washington University presented a new AI agent at the institution’s School of Engineering & Applied Science, one that is both student-centered and faculty-led. According to Professor Barba:
"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."
"Most are using ChatGPT, and not very well. Our AI agent addresses this reality by providing a customizable, course-specific tool that grounds AI responses in course materials."
Professor Lorena A. Barba showcased the AI agent’s interface to faculty, showing how to add course resources, set the AI’s behavior through prompts, and moderate student interactions. The demo included examples of the AI agent responding to student queries, showcasing its ability to provide course-specific information and encourage critical thinking.
Key features of this AI agent 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
Extremely simple LMS embedding via LTI
"ibl.ai's generative AI in education is set apart by their unparalleled expertise and their commitment to empowering educators by putting full control in their hands. Their platform enables instructors to customize AI agents, ensuring that the AI responses are always grounded in course materials—minimizing the risk of inaccuracies or hallucinations. For any educational institution looking to lead the future of AI-driven learning, ibl.ai is the gold standard."
- Professor Lorena Barba
Many more higher education institutions at ibl.ai/partners are reporting similar results.
UPDATE
At GWU's TRIALS Conference on February 3-4 2025, GWU and ibl.ai showcased their “Student-Centered Approach to AI in the Classroom”:
AI Agents in the Classroom – Faculty can customize AI agents to enhance student learning and engagement.
AI as Tutor, Coach & Teammate – Students use AI for understanding, creativity, and support in coursework.
Real-World Data Collection – Surveys, focus groups, and faculty interviews track AI agent impact.
Customizable & Model-Agnostic – AI agents can be adapted for different courses and learning styles.
Focus on Motivation & Engagement – Research explores how AI affects students’ drive and performance.
Best Practices for Faculty – Guides and insights help instructors integrate AI agents effectively.
Open Science & Shared Learning – Findings will be shared to improve AI literacy in education globally.
How does it work?
GWU's implementation partner, ibl.ai, provides an application layer generative AI solution to the university.
It's language model-agnostic (works with OpenAI, Gemini, Llama, Anthropic and any other LLM), oriented for student success and faculty support with deep analytics and safety layers, and highly customizable.
In terms of pricing, while ChatGPT charges $20 per student per month and Microsoft Copilot charges $80 per student per year for entire student populations, ibl.ai offers flexible, pay-as-you go pricing models and bulk rates that pale in comparison.
For more information about ibl.ai AI Agents and to start for free on web, iOS and Android, please visit ibl.ai for Higher Education or message our team.