Building a better AI tutor (by Matteo Aquila)

The ICAP Framework: Linking Cognitive Engagement to Active Learning Outcomes

This article describes the ICAP framework that defines cognitive engagement activities on the basis of students’ overt behaviors and proposes that engagement behaviors can be categorized and differ...

https://www.tandfonline.com/doi/abs/10.1080/00461520.2014.965823 social preview image

link.springer.com

Methodologies for Improving the Quality of AI Tutoring in K-12 Education

Many AI tutors leverage large language models (LLMs) today. Given that LLMs are opaque black boxes, robust evaluation and live experimentation to measure the impact of every change are essential. We pioneered AI-powered tutoring for K-12 with the launch of Khanmigo (Khan Academy 2023). We describe the metrics we use to measure AI tutoring quality and student engagement as well as various experiments we have run. We highlight the changes that have moved our metrics, including models, prompting, personalization and agents.

https://link.springer.com/chapter/10.1007/978-3-032-29755-6_14 social preview image

blog.khanacademy.org

How Khan Academy Is Building a Better AI Tutor: Our Most Recent Learnings

Khan Academy shares how it improved its AI tutor Khanmigo with faster responses, smarter data use, and better student learning outcomes.