Our Approach

The National Tutoring Observatory is building the first large-scale, open-access dataset of real-world tutoring interactions. By collecting millions of hours of audio, video, and text data, the NTO provides multimodal insight into how educators teach—and how students learn—in real time. The “Million Tutor Moves” (MTM) repository will link every educator move to student outcomes, helping researchers and developers understand what makes tutoring effective, widely accessible, and scalable. Digital learning platforms capture what students do, but not how educators respond. The NTO fills this gap—showing how teachers and tutors guide thinking, build understanding, and support emotional and cognitive growth. This open infrastructure will fuel the next generation of research and AI tools to enhance human teaching and learning.

NTO approach diagram 1

The NTO community—now comprising more than 300 researchers, tutoring providers, technology developers, and practitioners—has identified annotation and other processing of tutoring interactions as a key bottleneck in improving instructional quality of human and AI-powered tutors. While tutoring providers in our initial NTO cohort—Carnegie Learning, Eedi, PLUS, Saga, Third Space Learning, TeachFX, UPchieve—collectively serve hundreds of thousands of students, their ability to transform tutoring data into actionable insight is constrained by limited infrastructure for scalable, privacy-preserving annotation tools.

Reliable “ground truth” data is essential for understanding effective tutoring, but traditional human annotation is slow, inconsistent, and prone to error. Ambiguous tasks (e.g., what counts as a hint), subjective judgments (e.g., patience or frustration), and simple mistakes (e.g., fatigue or mis-clicks) all reduce quality. NTO tools simplify this process with AI-assisted workflows that support feedback, iteration, and consistency—empowering researchers and developers to generate and scale reliable insights.

We partner with tutoring providers, school districts, practitioners, researchers, and privacy experts to build, test, and scale infrastructure that matters to educators and students.

NTO approach diagram 2

For the Stakeholders

Lorem ipsum dolor sit amet, consectetur adipiscing elit, sed do eiusmod tempor incididunt ut labore et dolore magna aliqua. Ut enim ad minim veniam, quis nostrud exercitation ullamco laboris nisi ut aliquip ex ea commodo consequat. Duis aute irure dolor in reprehenderit in voluptate velit esse cillum dolore eu fugiat nulla pariatur. Excepteur sint occaecat cupidatat non proident, sunt in culpa qui officia deserunt mollit anim id est laborum.

Click on one of the buttons below to learn more about how it pertains to you.

Partnering Across the Tutoring Ecosystem

The National Tutoring Observatory works in close partnership with a diverse set of stakeholders to advance the science and practice of tutoring. Our work is grounded in collaboration with researchers, edtech developers, school districts, and tutoring providers, each of whom plays a critical role in improving learning outcomes at scale. Read more for a deeper dive on how we partner.

Partnering Across the Tutoring Ecosystem

The National Tutoring Observatory works in close partnership with a diverse set of stakeholders to advance the science and practice of tutoring. Our work is grounded in collaboration with researchers, edtech developers, school districts, and tutoring providers, each of whom plays a critical role in improving learning outcomes at scale. Read more for a deeper dive on how we partner.

Community of Practice

With support from an NSF MSRI Incubator award (NSF #2321499), we established a vibrant and collaborative community of researchers, technology developers, and practitioners. Below is a summary of our meeting materials. Please contact nat_tutoring_ob@cornell.edu to request access to the meeting recordings listed below.

Incubator workshop

2023

2024

January 2024

Platform/Service Deep Dive- Carnegie Learning

Button Lorem Ipsum

February 2024

PII and De-identification with Ryan Baker and Langdon Holmes

Button Lorem Ipsum

March 2024

July Convening Planning

Button Lorem Ipsum

April 2024

Databrary with Karen Adolph, Rick Gilmore, and Elizabeth Sheckler

Button Lorem Ipsum

May 2024

Teacher Perspectives on Fair and Ethical AI

Button Lorem Ipsum

July 2024

Partner Convening at Georgia Tech

Button Lorem Ipsum

2025

January 2025

Partner Launch Meeting

Button Lorem Ipsum

April 2025

Tutor Move Taxonomies

Button Lorem Ipsum

May 2025

NTO Engineering Pipelines

Button Lorem Ipsum

June 2025

NTO Tech Demo

Button Lorem Ipsum

July 2025

Data Agreements

Button Lorem Ipsum

August 2025

Tech Infrastructure

Button Lorem Ipsum

September 2025

Tutoring Move Annotator

Button Lorem Ipsum

October 2025

Data Competitions

Button Lorem Ipsum