Rising Academies' WhatsApp tutor Rori lifts math scores 0.36 SD

AI system

System: Rori, AI-powered conversational math tutor on WhatsApp
Model: Not assessed
Release: Not assessed
Application developer: Rising Academies
Role: Not assessed
Configuration: Not assessed
Inputs and outputs: Not assessed
Autonomy: Not assessed
Workflow: A chat tutor that runs on basic phones over low-bandwidth networks. One scheduled hour a week of independent use during study hall with a provided phone. A control group kept on the normal timetable in the same school network.
Human oversight: Not assessed
Relation to AI: Rori delivered the extra practice hour itself, so the comparison is Rori time versus a normal study hall. The authors call the result preliminary, year 1 only. The vendor co-authored the preprint.
AI contribution: Rori delivered the extra practice hour itself, so the comparison is Rori time versus a normal study hall. The authors call the result preliminary, year 1 only. The vendor co-authored the preprint.

Studies: Not assessed
Study design: Not assessed
Measurement: Not assessed
Setting and sample: Not assessed
Measures: an effect size of 0.36 (Cohen's d, p < 0.001)
Comparison: control-group students at schools without Rori access who continued regular math instruction
Results: Reference: control group growth score M = 2.12 (SD = 6.30) between baseline and endline. Result: treatment group growth score M = 5.13 (SD = 7.03), an effect size of 0.36 (Cohen's d).
Additional value from AI: Not assessed
Limitations: Not assessed
Denominators: Not assessed
Materials for replication: Not assessed

Participants: Developer: Rising Academies. Operator: Rising Academies (11 schools).
Jurisdictions: Developer: Sierra Leone. Operator: Ghana.
Ownership and control: Not assessed
Dependencies: Not assessed
Cross-border connections: Not assessed
Geopolitical implications: Not assessed

Conditions for replication: Phone and WhatsApp access during school time. Schools accustomed to routine testing (the authors cite this against a Hawthorne effect). Replication outside the Rising Academies network, which the authors say is still needed.
Replication attempts: Not assessed
Later findings: 6 May 2026. By May 2026 Rising Academies was piloting Rori in government schools in Ghana's Eastern Region with World Bank support, had extended the pilot by six months, and was preparing a larger randomized trial in more than 100 public schools from September 2026.
Availability: Not assessed
Institutional decision: Not assessed
Grounds: Not assessed
Action and result: Not assessed
Success criterion: Not assessed

Assessed benefits: People. Organizations.
Depth: Not assessed
Reasons: People: Treated students' math growth exceeded controls' by 0.36 SD (v2 PDF). Organizations: The deploying network reports a marginal cost of about $5 per student (v2 PDF).
Observed or intended: Not assessed
Rubric: Not assessed
Assessor and date: Not assessed
Alternative assessments: Not assessed
Fill: The makers' claim

Kind: Not assessed
Related entries: Not assessed
Field: Education. Primary and junior-secondary math (chat-based tutoring).
Purpose: Rori was built to give extra math practice and feedback through chat. The math gain is that purpose.
Dates: Date basis unassessed: 2023 (precision unassessed). Updated: 22 October 2026.
Stage: Not assessed
Version: SHA-256: a43fdb482c8e…