This is the webpage for the Generative AI-powered Educational Applications course, a PhD-level elective course that I taught at MBZUAI in Spring 2026.

Contents:

Overview

This course covers a range of applications empowered by AI – from writing assistants to dialogue-based intelligent tutoring systems – across a range of subject domains, including but not limited to language learning and STEM subjects. We will cover topics surrounding content and feedback generation using generative AI, adaptation and personalization of AI-driven educational systems, multi-modal interactive approaches (including not only text-based but also speech and visual systems), agentic AI approaches to educational applications, generative AI model alignment with educational, age- and subject-specific aspects, and novel human-computer interaction opportunities in this domain. In addition to such novel opportunities, the course will delve into emerging challenges, focusing on ethical issues, societal impact and real-world integration of this technology, and evaluation.

[To the top]

Course outline

  • Week 1: Introduction, core tasks, fundamental concepts [go to Week1]
  • Week 2: AI for writing assistance and language learning [go to Week2]
  • Week 3: Intelligent Tutoring Systems [go to Week3]
  • Week 4: Learner analytics and personalization [go to Week4]
  • Week 5: LLM alignment for educational applications [go to Week5]
  • Week 6: Agentic AI for educational applications [go to Week6]
  • Week 7: Human-computer interaction and real-life applications [go to Week7]

[To the top]

Reading list

[To the top]

Week 1: Introduction, core tasks, fundamental concepts

Overview:

  • Introduction and overview of the field and the core tasks
  • Introduction to fundamental concepts (including Bloom’s taxonomy, scaffolding, etc.), techniques and theories (including knowledge tracing and item response theory, among others) from the learning sciences
  • Overview of the key AI techniques used in education
  • Overview of the core tasks
  • AI in education in academic and industrial contexts (including OpenAI’s educational models, Google’s LearnLM, Khan Academy’s Khanmigo, etc.)

Learning materials:

[To the top]

Week 2: AI for writing assistance and language learning

Overview:

  • Overview of the core tasks: writing assistants, grammatical error detection (GED) and correction (GEC)
  • LLM-empowered writing assistance and assessment
  • State-of-the-art AI-based approaches to GEC, GED, and grammatical error explanation (GEE)
  • Language learning across modalities (from text to speech) and languages

Learning materials:

[To the top]

Week 3: Intelligent Tutoring Systems

Overview:

  • Introduction into the theory and practice of building Intelligent Tutoring Systems (ITSs)
  • From traditional ITSs to modern, AI-powered systems – what generative AI can do for us?
  • ITSs across domains and subject areas
  • Evaluation of ITS – from purely intrinsic metrics to extrinsic (i.e., learner-based) evaluation

Learning materials:

[To the top]

Week 4: Learner analytics and personalization

Overview:

  • Tracking learner knowledge via Bayesian Knowledge Tracing (BKT) and its variants (e.g., Deep Knowledge Tracing)
  • Testing learning material appropriateness via Item Response Theory (IRT)

Learning materials:

[To the top]

Week 5: LLM alignment for educational applications

Overview:

  • Overview of the learning sciences principles
  • Pedagogical alignment of LLMs
  • Techniques applied in the educational contexts
  • Evaluation of pedagogical properties of educationally oriented models

Learning materials:

[To the top]

Week 6: Agentic AI for educational applications

Overview:

  • Applications of agentic AI to education
  • Mechanisms of multi-agent collaboration in educational contexts

Learning materials:

[To the top]

Week 7: Human-computer interaction and real-life applications

Overview:

  • Human-computer interaction (HCI) aspects in AI-for-education
  • Real-life integration
  • Ethical considerations

Learning materials:

[To the top]