AIX (AI Experience)
Definition
A framework defined by Diana Wolosin (Indeed) that extends UX design to treat AI agents as first-class users of design systems. Core principle: 'Just as UX shapes how humans behave in a system, the structure of a design system shapes how AI behaves when generating interfaces.' AIX posits that better structure = more consistent AI behavior. Three-layer metadata architecture: WHAT (raw assets → structured, machine-readable metadata), HOW (implementation rules, prop types, accessibility, interaction states), WHY (strategic intent, usage guidelines, decision rationale). Three-layer MCP configuration: Visual (Figma MCP), Implementation (Design System MCP), Bridge (Code Connect). Powered thousands of AI-generated prototypes at Indeed with impressive component selection accuracy.
Builder Context
AIX is the mental model shift that makes design systems work for agents. Most design systems are documented for human consumption — Figma files, Storybook stories, markdown guidelines. AIX says: your design system needs a machine-readable layer too. Practically, this means: (1) expose your component catalog via Storybook MCP (machine-readable JSON, not just visual stories); (2) expose your design tokens via a Design System MCP; (3) bridge visual and code layers via Figma's Code Connect; (4) include the WHY layer — not just 'use this token' but 'use this token because buttons need 4:1 contrast ratio.' The teams doing this (monday.com, Indeed) report that agents select the correct component and variant 90%+ of the time.