Rapid Evaluation of the Impact of Gemini Guided Learning on Students’ Mathematics Scores in School Grades 8 and 9 in India

Last registered on October 27, 2025

Pre-Trial

General Information

Title

RCT ID

AEARCTR-0017071

Initial registration date

October 24, 2025

Initial registration date is when the trial was registered.

It corresponds to when the registration was submitted to the Registry to be reviewed for publication.

First published

October 27, 2025, 8:58 AM EDT

First published corresponds to when the trial was first made public on the Registry after being reviewed.

Locations

There is information in this trial unavailable to the public. Use the button below to request access.

Request Information

Primary Investigator

Name

Natalia Valdes Aspillaga

Affiliation

Fab Inc

Contact Primary Investigator

Other Primary Investigator(s)

PI Name

Usman Khawar

PI Affiliation

Fab Inc

Contact Investigator

PI Name

Paul Atherton

PI Affiliation

Fab Inc

Contact Investigator

Additional Trial Information

Status

In development

Start date

2025-10-30

End date

2026-06-30

Keywords

Education

Additional Keywords

Artificial Intelligence, EdTech, AI Tutoring

JEL code(s)

I24

Secondary IDs

Prior work

This trial does not extend or rely on any prior RCTs.

Abstract

This study evaluates the impact of Gemini Guided Learning, an AI-powered instructional experience within Gemini that provides personalised learning through guided questions, step-by-step scaffolding, and multimodal resources rather than supplying direct answers, on mathematics learning and developing metacognitive skills in grade 8 and 9 in India (ages 13–15). This evaluation is part of a multisite evaluation. The trial randomly assigns classrooms either to continue with regular teaching or to use Gemini in approximately half of their mathematics lessons over an eight to nine (8-9) week period. The same teachers are responsible for both treatment and control classrooms; all will receive training on how to use the tool, though it will only be applied in treatment classes. Mathematics performance of students and teachers will be assessed at the beginning and end of the intervention. The study will provide rigorous evidence on whether AI-supported guided learning can strengthen mathematics learning in junior secondary education.

External Link(s)

Registration Citation

Citation

Atherton, Paul, Usman Khawar and Natalia Valdes Aspillaga. 2025. "Rapid Evaluation of the Impact of Gemini Guided Learning on Students’ Mathematics Scores in School Grades 8 and 9 in India." AEA RCT Registry. October 27. https://doi.org/10.1257/rct.17071-1.0

Sponsors & Partners

Partner

Name

City Montessori Schools

Type

none

URL

https://cmseducation.org/

Name

the Centre for Science of Student Learning (CSSL)

Type

URL

https://www.cssl.in/

Experimental Details

Interventions

Intervention(s)

Gemini Guided Learning is an AI-powered instructional tool within Gemini, designed to support students’ mathematics learning and metacognitive development through guided questions, step-by-step scaffolding, adaptive feedback, and multimodal resources rather than providing direct answers. Infused with Google’s LearnLM research, Gemini encourages students to reflect on their own thinking, deepening metacognition while fostering curiosity and active engagement. The intervention will be implemented in grade 8 and grade 9 (ages 13–15) over an eight- to nine-week period, during which students in treatment classrooms will use Gemini in about half of their mathematics lessons. Teachers will receive training on how to use the tool, although it will only be applied in treatment classrooms.

Intervention Start Date

2025-10-30

Intervention End Date

2025-12-30

Primary Outcomes

Primary Outcomes (end points)

The primary outcome of interest is student mathematics achievement, measured using standardised assessments aligned with the grade 8 and 9 curriculum and administered at endline.

Primary Outcomes (explanation)

Secondary Outcomes

Secondary Outcomes (end points)

The secondary outcome measures students’ metacognitive skills, defined as their capacity to reflect on their reasoning, evaluate their understanding, and regulate their learning strategies while engaging with mathematical tasks.

Secondary Outcomes (explanation)

Experimental Design

This study employs a cluster randomized controlled trial with classrooms as the unit of randomization. Randomization is stratified by school, grade level (8 and 9), and mathematics teacher using computer-generated random assignment with a pre-specified seed. This stratification approach ensures balanced allocation across key prognostic factors and prevents potential confounding between teacher effects and treatment effects.
Classrooms are randomly assigned to either: (1) Treatment arm receiving access to an AI-powered mathematics tutoring platform in addition to standard instruction, or (2) Control arm receiving standard mathematics instruction only.

Experimental Design Details

Not available

Randomization Method

Done in office by a computer using stata

Randomization Unit

Classroom

Was the treatment clustered?

Yes

Experiment Characteristics

Sample size: planned number of clusters

100 classrooms (37 grade 8 and 65 grade 9) across 7 schools

Sample size: planned number of observations

4,150

Sample size (or number of clusters) by treatment arms

50 control and 50 treated

Minimum detectable effect size for main outcomes (accounting for sample design and clustering)

Using a two-level classroom-cluster design with α=0.05 (two-tailed), power=0.80, ICC=0.18, 100 clusters, average cluster size=30, 50/50 allocation, and covariates explaining 45% of within-cluster variance (baseline maths grades) and 35% of between-cluster variance, the MDES is 0.206 SD on the student-level standardised mathematics score

Supporting Documents and Materials

IRB

Institutional Review Boards (IRBs)

IRB Name

Human Behavioural Research Ethics Committee (HuBREC)

IRB Approval Date

2025-10-13

IRB Approval Number

25/006

Analysis Plan