Skip to content

EIDU learning app lifts pre-primary scores in a Kenyan trial

In a randomized trial in 291 pre-primary schools in Murang'a County, Kenya, in 2022-23, EdTech Hub found that EIDU's classroom-integrated tool raised learning by 0.534 standard deviations.

  • 2 for a person

    Learners in treatment schools scored 0.534 standard deviations higher on the IDELA assessment of early learning.

Depth runs from 1, a convenience or time saved, to 5, a life or a livelihood preserved.

Status
Reported benefit.
Evidence

foundstudiedreportedclaimed, the grade of this record

Only the evaluators support the benefit.

Compared with

Control schools that had not yet received the EIDU model and kept teaching the non-digitized curriculum. Measured.

The system’s part
Not isolated. Treatment schools received the app together with digitized Tayari lesson plans, teacher training and support. Control schools received none of these, so the app's own share is unknown. The trial protocol says that the app chooses each learner's next unit from their learning history, without describing a model trained on data.
Not yet checked
LimitsCosts and harmsLearns from dataLater outcome
Benefit type
Improved Learning
System
EIDU digital personalised learning (DPL) tool on low-cost Android devices
Made by
EIDU
Used by
EIDU with the Murang'a County government (291 pre-primary schools in the trial)
Where
Murang'a County, Kenya
Stage
Expanding
Date
Kind
Aggregate result
Broad benefit
Training and Teaching Others, Judging the Qualities of Objects, Services, or People
Collections
Cross-border records
Last revised
1 November 2026

Sources

  1. Report, by an evaluator that the makers or users commissioned.

    EdTech Hub. Digital Personalised Learning to Improve Literacy and Numeracy Outcomes in Kenyan Classrooms. Case study and project page, study team led by Louis Major (University of Manchester), accessed 1 November 2026. EdTech Hub ran the study in collaboration with EIDU, and donors funded the work through EIDU.

    The findings indicate that EIDU's classroom-integrated DPL tool had a statistically significant effect on overall learning (0.534 SD, p < 0.001).
  2. Report, by an evaluator that the makers or users commissioned. Context or contrary evidence.

    Major L, Daltry R, Otieno M, Otieno K, Zhao A, Hinks J, Sun C, Friedburg A. Randomised Controlled Trial Protocol: Digital personalised learning to improve literacy and numeracy outcomes in early grade Kenyan classrooms. EdTech Hub, October 2023 (updated version), section 1.4.1. doi:10.53832/edtechhub.0176. Describes the trial design without reporting results.

    EIDU's classroom-integrated implementation approach combines a DPL tool with structured pedagogy (SP) - henceforth called the EIDU 'DPL-SP' model.

Details

AI system

Workflow

Each classroom received low-cost Android devices with the EIDU app, shared among learners during the school day. Teachers received training on the Tayari program and its digitized lesson plans, with support from county early childhood development officers. The exercises were mapped to Kenya's competency-based curriculum and approved by the Kenya Institute of Curriculum Development.

Follow-up

Conditions for replication

Digital content must align with the national curriculum and with what teachers teach that day. County governments must pay at least part of the cost of the devices.

Entry details

Sector

Education.

Purpose

EIDU built its app to give pre-primary learners personalized literacy and numeracy exercises on shared classroom devices and to give teachers digitized lesson plans.

31 more questions not yet checked

model, release, provider, role, configuration, inputs and outputs, autonomy, human oversight, AI contribution, beneficiaries, reach, distribution and access, duration, every measurement question, every money question, ownership and control, dependencies, cross-border connections, geopolitical implications, replication attempts, availability, institutional decision, grounds, action and result, success criterion, every evidence question, observed or intended, alternative assessments, related entries, other identifiers, category mappings.

Cite this record

Peter H. Vartanian. (2026). EIDU learning app lifts pre-primary scores in a Kenyan trial (AIBD-1156). Artificial Intelligence Benefits Database, edition of 1 November 2026. https://petervartanian.xyz/aibd/records/AIBD-1156.html (archived at https://doi.org/10.7910/DVN/AADSII, version 7.0)

BibTeX Data Field definitions