Corgi: Cognitive Reasoning Interface

Cognitive systems built with artificial intelligence resources (AI-powered systems) can be defined as software systems that learn at scale from their interaction with humans and environments. That kind of system allows people to augment their cognitive potential in order to harvest insights from huge quantities of data to understand complex situations, make accurate predictions about the future, and anticipate the unintended consequences of actions. These systems evolve naturally from such learning, rather than being explicitly programmed In this approach, humans and computers work more interconnected to achieve unexpected insights. In order to be useful, an AI-powered system must be aware of the users' goals, so it can help him/her by bringing contextual information from multiple sources, guiding through the series of tasks associated with the goals. The knowledge structuring is a challenge by itself and it has been the focus of knowledge engineering research. Once the knowledge is structured or organized, the challenge falls on UX researchers to investigate users and their tasks and goals with that structured knowledge. Questions like who the users are, what they want or need to do, in which preferred ways, and what are users' goals can guide UX research on this matter. We argue that an AI-powered system could infer the user's goals by observing his/her interactions with different systems and considering its knowledge base - about the user, the group(s) s/he is part of, the applications' domains, the overall context, etc. Based on fieldwork executed for a project where a knowledge-intensive process is analyzed and discussed with support of an AI-Powered System, we propose the Cognitive Reasoning Interface (CoRgI) framework. This paper presents the fieldwork observation that led to the development of the framework, how we conceptualize the framework, and our initial validation of the framework.