A MODEL OF HYBRID INTERACTION WITH AN AI-AGENT-BASED PLATFORM

Abstract

This article presents a conceptual model of hybrid user interaction with a digital platform, in which an AI agent functions as an integrated interface layer—an orchestrator—between the user and the system’s functional modules. The research is prompted by the crisis of classical graphical interfaces in modern SaaS ecosystems, where an excessive density of control elements creates a critical cognitive load and reduces user productivity. The introduction justifies the relevance of the transition from direct manipulation to intent-based interaction and formulates a research problem regarding the lack of architectural approaches that would formalise the transformation of a natural language query into specific system calls, with the result displayed in familiar graphical interface elements. In the context of an analysis of recent research and publications, the evolution of human-computer interaction paradigms, the limitations of classical user interfaces in the context of Hick’s Law, and the concept of a generative interface are examined, and a fundamental difference between the proposed approach and typical dialogue systems and chatbots is identified. The results section describes a three-tier architecture comprising a graphical user interface as an entry point and active context sensor, an intelligent interface layer with modules for intent analysis, action planning and explanation generation, and a server core with modules for searching, filtering and comparing objects. A logical diagram of query processing, a sequence diagram, and a component-based model of the platform are proposed, which systematically describe the full cycle from the formulation of the user’s intent in natural language to the automatic state transition of graphical components via Backend API calls. Separately, as part of the research, a hierarchical classification has been developed covering six successive levels of artificial intelligence integration into the digital platform, where each subsequent level involves deeper AI involvement in the system’s operation, and the highest level corresponds to a full-fledged interface layer-orchestrator, which takes on the coordination of all interactions between the user and the platform. The conclusions demonstrate that the proposed conceptual model combines the intuitiveness of natural language with the transparency and controllability of a graphical interface, minimises operational friction, and establishes a methodological foundation for the design of next-generation information applications.