Our Methodology
- AI generated personal insight report each month
- Track progress across 7 experience domains
- Opt in to request support from their institution
- 200+ aggregated, anonymised datapoints per cycle
- AI-powered early warning signals and intervention cues
- Class, program and institution-level dashboards with flexible cohort based views
- Identify students actively seeking help
- Full SEI score and domain trend view
- 20 KPIs covering engagement, consistency and belonging
- Month over month progress to track how their child is doing
SEI is powered by a monthly, non-clinical reflection cycle that measures student experience across seven critical domains. Responses are transformed into indicators that reveal focus, engagement, energy, and belonging patterns at scale. Students receive personalised insights, parents track month-over-month progress and domain trends, while institutions see aggregated data.
SEI Score Interpretation
SEI Score Interpretation
SEI scores are interpreted using a dual-frame approach that combines absolute meaning with local, contextual meaning.
Absolute Interpretation
Normalized score ranges can be read as:
Local Norms
Experiences like belonging, engagement, and routines vary a lot by institution. SEI uses local normative distributions:
This keeps interpretation context-aware rather than relying on a single global standard that may not fit every institution.
Acting on SEI Data
Acting on SEI Data
Each SEI administration yields over a hundred data points per institution. This transforms student self-report data into a practical roadmap for creating a more human-centred learning environment.
Predicting & Preventing Dropouts
Predicting & Preventing Dropouts
SEI data doesn't just measure experience; it surfaces early warning patterns that predict disengagement and potential dropout before it happens. By tracking domain trajectories over time, our system identifies students silently drifting away.
From Prediction to Prevention
SEI transforms passive data into proactive care. Institutions receive prioritised risk lists, counsellors get context-rich profiles, and students can opt in to request help, creating a closed loop where no one falls through the cracks silently.