Jaime Sonoda
UX Designer Manager, Google
Research Areas
Authored Publications
Sort By
Preview abstract
Responsive user interfaces enable dynamically adjusting user interfaces based on device-specific aspects such as screen size, aspect ratio, display resolution, etc. However, traditional responsive design fails to account for different types of constraints of a user and task criticality of the task being performed via the UI. Misalignment between the UI design, user context and task criticality can lead to user error. This disclosure describes techniques, implemented with user permission, for dynamically modifying the layout, information density, and/or interactive physics of a user interface based on a dual-factor analysis of user cognitive state and task criticality. The user's cognitive state can be inferred from behavioral telematics. Task criticality can be inferred from semantic analysis. The information density and other parameters of a user interface are automatically adjusted based on such analyses. Such adjustments include applying or relaxing restrictions on interactivity and adjusting visual prominence of various UI elements to adjust the information density of the user interface. The adjustments can also include adjusting friction as appropriate, hiding certain aspects of the user interface, or other types of adjustments.
View details
Preview abstract
Configuring and optimizing artificial intelligence (AI) models for specific tasks can be a complex process that may involve deep technical expertise and iterative manual experimentation. This disclosure describes a system, which may be implemented as a self-improving AI agent, that can assist in automating this process by interpreting a user's intent to recommend a suitable AI model and configuration. The agent can analyze available models and propose settings, for example, system instructions, grounding data, and operational parameters. The system can also perform background evaluations to provide empirical data and a rationale for its recommendation. A human-in-the-loop component may be included to present proposed optimizations to a user for approval before the optimizations are implemented. This approach can aid in streamlining AI model optimization for a broader range of users, help align model behavior with user goals, and reduce the likelihood of unintended outcomes through controlled, human-validated improvements.
View details
