---
format: "aidr-story-markdown/v1"
id: "df9e799a874b2dab7fc9ff31b276e117981b627dc072a7f7161daf593ef75051"
canonical_url: "https://aidr.today/df9e799a?lang=en"
title: "AI Tutoring with Khanmigo in a Two-Year School Experiment"
lang: "en"
requested_lang: "en"
available_langs: ["en","vi"]
translation_fallback: null
fallback_fields: []
published_at: "2026-10-06T00:00:45.000Z"
category: "Research"
topics: ["llm"]
source_urls: ["https://edworkingpapers.com/ai26-1551","https://news.ycombinator.com/item?id=49972419"]
summary: "A two-year cluster randomized trial in 18 Tennessee middle schools provided some of the first large-scale experimental evidence on AI tutoring, with randomly assigned students using Khan Academy's AI tutor, Khanmigo, configured to coach rather than give answers during daily remedial mathematics sessions."
---

# AI Tutoring with Khanmigo in a Two\-Year School Experiment

> [Open the canonical story](<https://aidr.today/df9e799a?lang=en>)

**Published:** 2026-10-06T00:00:45.000Z
**Category:** Research
**Topics:** llm

## Summary

A two\-year cluster randomized trial in 18 Tennessee middle schools provided some of the first large\-scale experimental evidence on AI tutoring, with randomly assigned students using Khan Academy's AI tutor, Khanmigo, configured to coach rather than give answers during daily remedial mathematics sessions\.

## Sources

- [Story source](<https://edworkingpapers.com/ai26-1551>)
- [Discussion](<https://news.ycombinator.com/item?id=49972419>)