Types of artificial intelligence tools and systems and their functions

Adaptive AI tools tailor content to each student's needs, prior knowledge, pace, and learning style. The system continuously analyses learning behaviour and progress and, using machine learning algorithms, automatically adjusts the type, difficulty, or presentation of material in real time.

The goal of adaptive tools is to create a personalised learning path that reduces students' cognitive load while increasing motivation and performance.

This approach is especially useful in higher education environments with large and diverse groups of students, where individualised support is challenging. Adaptive tools can detect difficulties promptly and automatically suggest content that best meets the student's current needs.

Key technical characteristics of adaptive tools include:

• Monitoring user behaviour and learning progress
• Algorithmic personalisation of content and tasks
• Real-time adaptation to student performance
• Analytics and recommendations for students and teachers
• Varied presentation modalities that adapt to learning strategies.

Examples of adaptive tools and AI systems in education:

• Adaptemy
  • Functionality: Adaptemy is an adaptive learning system powered by artificial intelligence that analyses students' responses and behaviour to build a detailed profile of their knowledge, difficulties, and typical errors. The system adjusts the order of content, difficulty level, number of repetitions, and type of feedback in real time, creating a personalised learning path for each student.
  • Relevance for education: It is primarily intended for educational institutions that want to enhance their digital textbooks and courses with an adaptive layer, without developing their own artificial intelligence system. Adaptemy integrates with existing LMSs and platforms and is available through commercial licenses, so it is most often implemented at the institutional level rather than by individual teachers.
  • Pedagogical potential: Adaptemy supports differentiated instruction and formative assessment by giving teachers insight into the specific concepts students struggle with and common error patterns. At the same time, it offers students customised tasks and explanations, reducing cognitive load.
  • Practical example: A faculty integrates Adaptemy into existing e-courses. Students solve tasks, and the system detects that some students consistently make mistakes in understanding certain content. Adaptemy provides these students with additional visual examples, simpler tasks, and guided solution steps, while those who perform well receive more complex problems that require combining multiple concepts. The teacher reviews the distribution of errors in the report and plans targeted explanations in class.
• Realizeit
  • Functionality: Realizeit is an adaptive learning platform that uses AI-based models to create personalised learning paths. The system monitors students' interactions with content and tasks, assesses the probability that certain concepts have been mastered, and adjusts subsequent activities accordingly: what material the student will see, which tasks to solve, and what type of feedback to receive.
  • Relevance to Education: Realizeit is used in both higher education and corporate learning. It is an institutional solution implemented through contracts with organisations and integrated with the LMS, requiring a strategic decision and management support, but enabling in-depth analytics at the course, study, or program level.
  • Pedagogical Potential: Realizeit enables the transition to individualised learning paths. Using data-driven approaches, teachers receive overview dashboards that show the level of mastery of learning outcomes and identify learning risk points, allowing timely intervention (additional clarifications, workshops, differentiated activities). This can be challenging for students, which may increase motivation and reduce dropout rates.
  • Case Study: A higher education institution implements Realizeit to deliver online or hybrid classes. Realizeit identifies students with sufficient prior knowledge and offers them faster progression through basic topics and more problem-based tasks, while providing students with less prior knowledge more detailed explanations, additional repetitions, and simpler exercises. It helps teachers plan additional workshops for groups of students who are lagging behind in mastering the material, based on analytics.
• SC Training (formerly EdApp)
  • Functionality: SC Training (formerly EdApp) is a mobile LMS solution for microlearning that uses AI algorithms to generate, organise, and customise short lessons. The system offers spaced repetition, task adaptation based on student performance, and built-in gamification elements. Through AI-based features, it can automatically suggest content and questions based on a given topic.
  • Educational relevance: SC Training is primarily focused on corporate learning and employee training, but is also relevant for higher education, especially for short online modules, introductory content, repetition, and self-study. Basic functionalities are free, while more advanced features and support are available through paid plans. It is therefore suitable as an illustrative example of adaptive microlearning supported by AI.
  • Pedagogical potential: SC Training enables the design of short, focused lessons that can be customised based on student performance and usage frequency. AI-based content and repetition recommendations can support the acquisition of knowledge, procedural skills (step-by-step execution of a procedure), and just-in-time skills. Gamification (badges, points, rankings) and mobile access further support motivation and participation, while pedagogical quality and alignment with learning outcomes still depend on the teacher or instructional designer.
  • Practical example: At a higher education institution introducing a mandatory online module on digital security for all new students, teachers use SC Training to create a series of short lessons (5–10 minutes) on topics such as password management, phishing detection, and personal data protection. Students take short, adaptive quizzes on their mobile phones; those who make mistakes in certain areas receive additional mini-lessons and follow-up questions. Analytics show which areas are most problematic, so teachers organise a short joint lecture focused on these topics, combining adaptive online microlearning with live teaching.