NOW ACCEPTING WAITLIST

The AI tutor that teaches,
not just answers.

KAIROS is an open-source K-12 AI math tutoring system built on MC-CPO pedagogical safety constraints and grounded in Bloom's 2-sigma finding, the gold standard of one-on-one tutoring effectiveness.

Built at the Cyber Innovation Lab, University of Southern Mississippi. Grounded in peer-reviewed research published on arXiv.

For educators, researchers, and ed-tech developers only. K-12 student access via IRB-approved pilot, coming soon. No spam, ever.

2
Peer-reviewed arXiv preprints
7
Validated pedagogical safety constraints
2ฯƒ
Bloom's effect size, the gold standard of 1-on-1 tutoring
36mo
Open deployment timeline

What KAIROS solves

Six failure modes. Six constraints. One tutor that actually works.

๐Ÿง C1

Helpful assistant bias

Stops AI from handing over answers, enforces productive struggle and Socratic scaffolding.

๐Ÿ”C2

Misconception detection

Distinguishes conceptual errors from arithmetic slips. Each triggers a different pedagogical response.

๐Ÿ“‰C3

Sycophantic drift

Prevents the tutor from progressively agreeing with wrong answers under student pressure.

๐Ÿ”‡C4

Verbosity control

Enforces concise responses that create space for student thinking, not AI monologues.

๐ŸงฉC5

Student modeling

Bayesian Knowledge Tracing tracks mastery across sessions and personalizes every interaction.

๐Ÿ›กC6โ€“C7

Safety constraint enforcement

All 7 constraints remain enforced even under roleplay, hypotheticals, or language switching.

Research foundation

Grounded in peer-reviewed AI safety research.

arXiv:2604.04237

Formalizing Pedagogical Safety Constraints

The first formal specification of safety constraints for AI tutoring systems, defining C1โ€“C7 to prevent reward hacking and instructional boundary violations.

Read โ†’
arXiv:2604.04251

MC-CPO: Mastery-Conditioned Constrained Policy Optimization

A novel RL framework that conditions policy optimization on student mastery state, formally preventing the helpful assistant bias while maximizing learning outcomes.

Read โ†’
Gates Foundation

K-12 AI Infrastructure Program

The Gates Foundation K-12 AI Infrastructure Program is funding open-source AI models to advance K-12 math tutoring. KAIROS is a direct embodiment of what this program seeks to support.

Read โ†’

Who should join

Built for the people who shape learning.

K-12 TeachersEducation ResearchersEd-Tech DevelopersSchool AdministratorsLearning ScientistsAI / ML Researchers

Be first when KAIROS launches.

We're finalizing our beta environment. Join the waitlist and get early access, research updates, and a voice in what we build next.

For educators, researchers, and ed-tech developers only. K-12 student access via IRB-approved pilot, coming soon. No spam, ever.