Requirements for Verification Results of Educational Materials Generated by AI

Abstract

Aim. To present a set of requirements helping to visualise AI results for monitoring the compliance of educational materials with regulatory requirements, ensuring their effective integration into the practical activities of a teacher. Methodology. The research is based on the analysis of regulatory legal documents, as well as on the theoretical understanding of approaches and principles outlined in works devoted to Explainable artificial intelligence (XAI), the digital educational environment, and pedagogical design. The key method was system analysis, which made it possible to synthesise requirements for the interface of the educational content verification system from various sources. Results. A set of requirements for displaying the results of educational materials verification has been formulated and substantiated, including: a multi-window interface for simultaneously displaying the lesson plan, identified inconsistencies, regulatory references, and AI recommendations, high-precision rendering of mathematical expressions, transparent visualization of AI (XAI) logic to enhance teacher trust, integrated symbolic and spatial representation of educational content, cognitive load management through visual analytics, and engagement monitoring features and risk management indicators. Research implications. The theoretical significance of the work lies in the systematisation and adaptation of XAI requirements and provisions of national standards for the design of educational products with AI algorithms to the task of constructing user interfaces for educational systems using AI technologies. The practical significance consists in the development of a set of specific parameters (resolution, pixel density, colour space, etc.) that can be used in the creation and selection of hardware and software tools for the implementation of intelligent systems in the educational process, increasing their transparency and , the level of trust on the part of teachers as a consequence. Conclusions. The level of compliance of educational materials developed on the basis of artificial intelligence systems and the effectiveness of their application in the educational process are determined not only by the quality of their algorithms, but also by the thoughtfulness of the user interface. The work formulates and substantiates a set of requirements for the visualisation of the results of such systems, integrating the provisions of Explainable AI, national standards for the use of AI in education, and modern principles of pedagogical design. This set can serve as a regulatory basis for the design of interfaces of educational AI systems.