<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom"><channel><title>Tutoring on AI and Society Course</title><link>https://msucerl.org/cmse101/tags/tutoring/</link><description>Recent content in Tutoring on AI and Society Course</description><generator>Hugo</generator><language>en-us</language><lastBuildDate>Thu, 21 May 2026 00:00:00 +0000</lastBuildDate><atom:link href="https://msucerl.org/cmse101/tags/tutoring/index.xml" rel="self" type="application/rss+xml"/><item><title>1.2 AI Tutoring Systems</title><link>https://msucerl.org/cmse101/use-cases/1-2-ai-tutoring-systems/</link><pubDate>Thu, 21 May 2026 00:00:00 +0000</pubDate><guid>https://msucerl.org/cmse101/use-cases/1-2-ai-tutoring-systems/</guid><description>&lt;h1 id="ai-tutoring-systems"&gt;AI Tutoring Systems&lt;/h1&gt;
&lt;h2 id="context--systems-architecture"&gt;Context &amp;amp; Systems Architecture&lt;/h2&gt;
&lt;p&gt;AI tutoring systems have transitioned from rigid rule-based cognitive tutors to conversational platforms powered by large language models (LLMs). The most visible system is Khan Academy’s &lt;em&gt;Khanmigo&lt;/em&gt;, introduced as a pilot in 2023. Khanmigo leverages foundational models (originally GPT-4, updated to GPT-4 Turbo and GPT-4o) bounded by system-level instructions that compel the AI to act as a Socratic guide rather than directly providing answers. The educational goal is to scale individual instruction to mitigate the post-pandemic learning loss.&lt;/p&gt;</description></item></channel></rss>