Project · Applied AI Systems

PreBinary

An AI-driven intelligent learning ecosystem, private by deployment.

About the project

PreBinary is built by a team of professors, researchers, students and AI experts. It adapts to specialised domains, brings several intelligence engines together and safeguards information through isolated deployments, so an institution can switch on the capabilities it needs and keep its data in its own hands.

Instead of tying every feature to one model, PreBinary lets an organisation pick a different model for each feature, run secure independent models with full privacy, and build custom large language models for its own needs.

PreBinary AI learning platform: features for faculty, students and administrators

Preview of the live demo. Open it in a new tab ↗

Features

Features by role

Faculty

Dual-mode exam creator for online or in-class assessments · Grading assistant · Reinvented online learning · RAG teaching resources · Research proposal writing assistant · Accessibility hub

Students

Adaptive exam preparation · Reinvented LMS · Student wellness hub for mental and academic wellbeing · Student advisor for academic and career guidance

Admin & staff

Proposal review · Staff training · Automated rubric-based reports assessment · Knowledge retrieval (RAG) for efficient operations

How it works

Platform principles

  1. Secure, independent private models

    Models run in isolated deployments with full privacy.

  2. Custom LLMs

    Large language models built and tuned for an institution’s needs.

  3. Feature-based model selection

    A different model can power each feature.

  4. Multi-model support

    Several generative AI models available in one place.

Team

Collaborators and sponsors

Dr. Ghazanfar Latif

Computing Science, Thompson Rivers University, Canada

Dr. Jaafar Alghazo

Software Engineering, University of Minnesota, USA

Dr. Nazeeruddin Mohammad

Cyber Security, The University of Adelaide, Australia

Dr. Runna Alghazo

Department of Education, University of North Dakota, USA

Canadian Association for Artificial Intelligence and Future Studies

Non-profit sponsor

Inspire Academic Press Inc.

Sponsor, Canada

More from the lab

Other projects

Indigenous CommunitiesLive demo

Living Heritage

A community-governed platform to preserve, teach and celebrate Secwépemc language and culture, with other languages in their own homes. Nothing is shown until a person from the community approves it.

Defence & SecurityLive prototype

WildfireIQ Kamloops

A live 3D map that combines an in-house AI risk model with active fires, satellite hotspots, evacuation zones, fire weather and smoke forecasts for the Thompson-Okanagan region.

Health & HealingLive demo

Wellness Hub

The flagship of AI for Health & Healing: goal setting, tracking, insights and an AI coach across five wellness domains, with private data. Demonstrated live to BC’s Minister of State for AI.

Assistive & EducationPreview build

PLAR Platform

One secure home for the Competency-based Portfolio journey at TRU Open Learning, from a student’s first readiness check to credit on their transcript.

Health & HealingDemo (sign-in)

Dermixa

An AI skin-check app that turns a short chat and photos into a clear four-level result with self-care plans and hospital referral, managed through a clinician console.

Interested in collaborating on PreBinary?

AIRL works with universities, public bodies, communities and industry through Mitacs, tri-council programs and direct partnerships.

Start a conversation