Page 68 - DP-2-2

Design+ Da Vinci AI Tutor in art history learning

Moving forward, future development efforts should qualitative feedback provided nuanced insights, revealing
prioritize refining voice recognition and interaction a strong appreciation for the comprehensive and engaging
capabilities to ensure seamless communication, broadening nature of interactions, alongside criticism related to
compatibility across devices, especially for macOS and excessive informational depth, platform incompatibility –
mobile users, and incorporating more robust adaptive particularly with macOS – and user interface challenges.
learning algorithms to better accommodate diverse student The predominance of text-based interactions further
needs. Further empirical research is essential to quantify suggests areas of refinement in voice-driven interfaces,
the direct impacts of AI-driven pedagogy on student necessitating optimization for broader accessibility.
achievement, retention, and engagement over extended Significantly, the tutor exemplifies the potential for
periods. In addition, expanding the model across other AI-driven solutions to reshape pedagogical strategies,
humanities disciplines, such as history, literature, and especially within humanities education, which traditionally
philosophy, will provide critical insights into the scalability emphasizes nuanced interpretation and critical thinking.
and adaptability of such smart educational tools, ultimately By operationalizing theoretical frameworks, such as
enriching digital pedagogy in higher education. Vygotsky’s zone of proximal development and Kolb’s

5.4. Lessons learned and recommendations experiential learning theory, the tool effectively enhanced
learner autonomy and facilitated deeper cognitive
The implementation of the tutor has provided several engagement. The study thus affirms the potential role that
critical lessons. First, technical barriers, such as operating emergent technologies can play in education, advocating for
system compatibility and installation complexity, integrative, responsive, and contextually rich instructional
significantly hinder adoption and must be addressed to methodologies. Nevertheless, critical technical and
broaden accessibility. Second, aligning the tutor’s content methodological improvements remain imperative.
and interactivity with diverse learner needs is essential for Future research must address platform compatibility,
fostering meaningful engagement. Personalized adaptive particularly across operating systems such as macOS
algorithms and user-driven feedback systems are key to and mobile devices, to broaden accessibility. In addition,
achieving this alignment. Third, the inclusion of dynamic, adaptive content algorithms require further refinement
multimedia-rich content and interactive features enhances to ensure instructional materials dynamically align with
the tutor’s ability to captivate and educate students diverse learner profiles and academic levels. Longitudinal
effectively. Therefore, while the initial deployment of studies exploring sustained impacts on learner outcomes
the system has underscored both its potential and its and integration of emerging technologies, including
limitations, it has also charted a path forward for refining augmented reality and enhanced NLP capabilities, are
AI-driven educational tools. recommended to expand the tutor’s effectiveness and

6. Conclusion scope. Moreover, ethical considerations surrounding
data privacy, bias reduction, and equitable deployment
The deployment and evaluation of the Da Vinci AI Tutor must underpin subsequent research endeavors to ensure
underscore significant advancements in the application responsible and inclusive educational innovation. Thus,
of generative AI within higher education, specifically ongoing development and systematic research are crucial
targeting the humanities discipline of art history. to realizing the full pedagogical potential of AI-driven
Designed to bridge historical context and contemporary tutoring systems in humanities education.
pedagogical approaches, the tutor integrates a historically
accurate Leonardo da Vinci avatar within immersive Acknowledgments
VR environments. This innovative approach addressed None.
enduring pedagogical challenges, including individualized
instruction, scalability, and equitable access, by Funding
combining multimodal interaction and adaptive learning None.
methodologies. The mixed-methods study highlighted
the tutor’s capacity for enhancing student engagement, Conflict of interest
comprehension, and accessibility through personalized
instruction and immediate feedback. Quantitative The authors declare that they have no competing interests.
data demonstrated varied engagement levels, with the
majority of students expressing limited perceived utility, Author contributions
indicating potential misalignment with user expectations Conceptualization: James Hutson
or technological challenges affecting usability. Conversely, Formal analysis: Tiffani Barner

Volume 2 Issue 2 (2025) 18 doi: 10.36922/dp.8365