evidoria

← Back to browse

Good practice

Snappet — AI-adaptive primary school practice in the Netherlands

Netherlands · Utrecht · See the Netherlands profile

AI-adaptive tablet platform for Dutch primary schools (3,000+, ~30% of total). LAK '16 quasi-experiment: grade-4 pupils gained 2.63 skill points (~1.5 months extra) in arithmetic vs. paper control. Grade-2 and language effects mixed.

3,000+ schools, roughly one third of the national total
Dutch primary schools using Snappet daily (2024)
2.63 skill points (approx. 1.5 months additional instructional time)
Grade-4 arithmetic skill gain vs. paper-based control (one school year)
up to 43% higher
Maths scores in Snappet classes (Cito LVS data, vendor-associated)
Snappet — AI-adaptive primary school practice in the Netherlands

Details

Maturity
Established
Promoter
Snappet B.V.
Period
2012–present
Keywords
EdTech, adaptive learning, primary education

Context

Snappet, founded in Utrecht in 2012, embeds tablet-based adaptive practice into primary-school classrooms across mathematics, vocabulary, reading and spelling for all Dutch primary grades. Its adaptive engine, based on the Elo rating system, continuously calibrates exercise difficulty so each pupil works at a level with approximately a 75% chance of success, and a live teacher dashboard shows per-pupil and whole-class performance in real time.

Activities

By 2024 more than 3,000 Dutch primary schools (roughly one third of the national total) used Snappet daily, with further deployments in Belgium, Spain, Germany and the United States.

Results

A 2016 quasi-experimental study (ACM LAK '16) compared arithmetic development over one school year in grades 2 and 4 against paper-based control classes. Grade-4 pupils gained an average of 2.63 skill points, equivalent to approximately 1.5 months of additional instructional time; grade-2 effects were mixed and language-subject gains have been inconsistent across studies. Cito LVS standardised test data cited in Dutch media indicate maths scores up to 43% higher in Snappet classes, though this figure originates from vendor-associated reporting.

Conclusions

Peer-reviewed research at Utrecht University documents that algorithmic dashboard feedback risks narrowing teachers' professional autonomy; studies on spelling and grammar report limited or negative effects, partly attributed to reduced paper-based writing practice; the largest gains consistently accrue to already high-performing pupils, raising equity questions; and as a commercial subscription product, schools in lower-income municipalities may face access barriers.

Implementation

Implementation detail (cost, timeline, staffing, conditions for success) is not yet available for this practice.

Data sources

Where this practice's information was retrieved from, and when.

Attachments

Similar practices you may find useful