Capabilities and Constraints: Modelling what Human and AI Agents Can and Can't Change

With Artificial Intelligence (AI) agents becoming more commonplace across the systems that we use every day, it is becoming increasingly important to document and convey the capabilities and constraints of these agents as interactive partners. In this paper, we extend our existing method for modelling interactive systems to facilitate recording and visualizing several key aspects of human-agent interaction. These include what elements of a system can be changed, who (or what) can observe or change them, who (or what) is able to change the system’s constraints, and more.