AI Tutor Built on trusted knowledge.
A reusable learning platform that connects grounded AI tutoring, adaptive practice, and learning analytics in one intelligent loop.
Reusable infrastructure for better professional learning.
AI Tutor explores how generative AI, structured retrieval, learner modelling, and analytics can support professional education at scale.
One core platform can support multiple domain-specific learning applications while keeping content, learner evidence, and programme governance connected.
Teach from what the programme trusts.
Ground instruction in programme-approved curriculum and learning resources, so explanations remain connected to the source material.
Focus effort where it matters.
Use learner signals to guide practice, difficulty, review, and next steps.
Improve with learning evidence.
Give education and research teams clearer analytics, feedback, and controls.
One connected learning workspace.
Move through the platform capabilities to see how trusted content becomes guided learning, targeted practice, and actionable insight.
One learning core. Many applications.
AI Tutor is designed as reusable education infrastructure. FinTutor is one application of this core, with the same pattern extendable to insurance, regulatory learning, research, career development, and future domains.
Built for organisations. Designed for learners.
One platform creates value on both sides of the learning experience: giving organisations greater reach and visibility while helping every learner move forward with confidence.
Launch trusted learning experiences
Turn approved materials into an AI-supported learning environment.
Personalise at scale
Support different learner needs without adding proportional instructor workload.
See learning progress
Understand engagement, performance, and areas requiring support.
Govern and grow
Manage content updates and reuse the platform across programmes.
Research behind the product.
These papers document work in AI-supported financial education, higher-order assessment, and model evaluation.
Fin-Agent-QG: A Collaborative Multi-Agent Framework for Higher-Order Cognitive and Difficulty-Aware Financial Exam Question Generation
AAAI Workshop on Agentic AI in Financial Services, 2026, Singapore.
A collaborative multi-agent framework for financial exam questions aligned with higher-order cognitive skills, calibrated difficulty, and professional assessment requirements.
View full paper (PDF)
Evaluating Large Language Models for Financial Reasoning: A CFA-Based Benchmark Study
ICAIF 2025 | AI for Finance Symposium
An evaluation of state-of-the-art language models on CFA-based reasoning tasks, comparing zero-shot performance with retrieval grounded in official curriculum content.
View full paper (PDF)Research meets real-world learning.
The project brings together AI research, learning design, domain expertise, and product engineering to turn research ideas into usable education infrastructure.
Yao Xuan
Senior Research Fellow
Li Sirui Ricky
Research Associate
Zhang Zefan
Research Engineer
Zhou Yi
Research Analyst
Dai Yang
Research EngineerMei Xianle & Zhang Ruiyang
Research Team InternsFrom research to the real world.
Selected showcases, demonstrations, research milestones, and project updates.
Singapore FinTech Festival
AI Tutor was showcased as an AI-assisted platform for professional learning, highlighting grounded tutoring, adaptive practice, and learning analytics.
Explore what AI Tutor could do for your learning programme.
For demonstrations, collaboration enquiries, or future deployment discussions, contact the AI Tutor project team.