We believe in complete transparency about how our AI works, what it can and cannot do, and how we ensure it remains fair, accurate, and beneficial for all students.
AI augments human expertise, never replaces it. All decisions remain with qualified professionals who understand the full context of each student's needs.
We continuously monitor for bias, ensure diverse training data, and regularly audit our models to prevent discrimination based on any protected characteristics.
We explain how predictions are made, what factors influence them, and provide confidence scores so educators can make informed decisions.
Student data is never used for advertising, sold to third parties, or shared without explicit consent. We use privacy-preserving techniques in all AI operations.
We maintain high accuracy standards, clearly communicate uncertainty, and continuously improve our models based on real-world outcomes and feedback.
Our AI is designed to work effectively for all students, regardless of disability, background, or learning style, promoting equity in education.
We continuously monitor our AI systems for fairness across:
Latest Audit: January 2025
Result: No significant bias detected
Next Audit: February 2025
A percentage indicating how certain the AI is about its prediction, helping you gauge reliability.
The top 3-5 factors that influenced the prediction, ranked by importance.
Similar past situations and their outcomes to provide context for the prediction.
Any factors that might reduce accuracy, such as limited data or unusual patterns.
Turn AI features on or off for individual students or globally
Control how conservative or aggressive predictions should be
Mark predictions as helpful or not to improve accuracy
Download all AI-generated insights and predictions for review
Exclude individual students from AI analysis if preferred
Jayaprakash, S. M., Moody, E. W., Lauría, E. J. M., Regan, J. R., & Baron, J. D.
Journal of Learning Analytics
Demonstrates how open-source predictive models built on LMS activity can surface at-risk students weeks in advance, allowing advisors to deliver targeted interventions that lift persistence outcomes.
Heffernan, N. T., & Heffernan, C. L.
International Journal of Artificial Intelligence in Education
Reports large-scale classroom trials showing that AI tutoring features improve math mastery while keeping educators in the loop through real-time reporting and experiment controls.
Holstein, K., McLaren, B. M., & Aleven, V.
Proceedings of the 9th International Conference on Learning Analytics & Knowledge (LAK ’19)
Uses mixed-method classroom studies to show that explainable AI insights paired with teacher agency increase trust and uptake of automated recommendations in live instruction.
We're committed to transparency and welcome all questions about how our AI works.
