AI Trusty
Personal AI • 2025 • Lead Product Designer
I led the design of AI security and trust features for the platform. Prior to this initiative, there was no AI Trusty-related design in place. As a result, users often mistrusted the AI’s opaque responses. For trainers, the process of addressing issues in documents was tedious, they had to navigate to the Upload Library and manually locate the relevant files for revision.
To address these challenges, I designed an interactive response system that makes AI-human interactions more transparent, thereby enhancing user trust. Additionally, because Personal AI operates under RBAC (Role-Based Access Control), I carefully considered the user experience for multiple roles throughout the process, ensuring that trust and usability are maintained for all types of users.
RBAC(Role-Based Access Control ) Design
With role-based access, the owner decide who sees what. Sensitive AI responses stay private, while shared insights reach the right people.
Data Privacy
Owners can quickly lock files to protect sensitive data and prevent unauthorized access. This enhances data privacy with fewer steps.
File Editing and Citation Navigator
The expandable sidebar streamlines file edits, while the Jump-to button lets trainers swiftly navigate to the chunk and resolve specific issues.
AI Response Interaction
I designed the interaction to ease uncertainty while users wait for AI responses, enhancing transparency and trust. This creates a smoother, more reassuring user experience.
