Tutor CoPilot

Product or Programme · All products and programmes
Evidence · 4 claims (3 for, 1 mixed) · 3 studies (2 causal, 1 review), q2–q4 · 0 of 3 report an effect size · 3 claims rest on one study

Description

Tutor CoPilot is a human-AI tutoring-support tool developed by Wang and colleagues that provides customizable, real-time expert-like guidance to tutors during K–12 mathematics sessions.

Components

• Human-AI real-time expertise scaling: models of expert thinking embedded in human workflows complement human contextual knowledge: The article's theory of change holds that many tutors lack the experience to respond effectively in the moment, producing low-quality responses like generic feedback or giving away the answer. "By offering real-time guidance tailored to the conversation and following high-quality strategies, Tutor CoPilot empowers tutors with the right language to develop the student's understanding." The approach combines complementary strengths: AI lacks educators' grounded, context-specific knowledge of curricula, assessment standards, and individual students, but can provide real-time guidance during instructional moments, while the human selects expert-curated strategies — without which LMs tend to default to repetitive strategies. (Rose E. Wang et al. (2025))

Claims

• Students whose tutors have access to Tutor CoPilot are 4 percentage points more likely to master lesson topics (pass exit tickets) in live K-12 math tutoring [+M]
• Tutors perceive Tutor CoPilot as helpful for on-the-spot explanations but flag suggestions that are not grade-level appropriate and 'too smart' [~W]
• Tutor CoPilot's benefit is largest for lower-rated and less-experienced tutors (9 p.p. and 7 p.p.), diminishing as tutor effectiveness increases [+M]
• Tutors with Tutor CoPilot access use more understanding-fostering strategies (e.g., prompting students to explain) and rely less on giving away answers than control tutors [+M]

Related Products and Programmes

-

Key Sources

• Rose E. Wang, Ana T. Ribeiro, Carly D. Robinson, Susanna Loeb, and Dora Demszky. (2025). Tutor CoPilot: A Human-AI Approach for Scaling Real-Time Expertise. arXiv:2410.03017v2. https://arxiv.org/abs/2410.03017v2

Page metadata

Field	Value
type	product
id	tutor-copilot
title	Tutor CoPilot
description	Tutor CoPilot is a human-AI tutoring-support tool developed by Wang and colleagues that provides customizable, real-time expert-like guidance to tutors during K–12 mathematics sessions.
status	review
product_kind	software
generated	by process:settle-candidates on 2026-10-12
trust	unverified — no one has confirmed this page's content

Frontmatter is the page's machine-readable record — see the Schema & Guide.