Published 12 September 2026 · Source dated 28 August 2026
Loosely named layers and undocumented variables already confuse humans; they confuse AI agents generating or editing UI even more. Teams tidying up token naming are seeing more consistent output from any AI tool pointed at their design system.
**AI agents are only as good as the tokens you feed them.** Loosely named layers and undocumented variables already confuse humans — they confuse AI agents generating or editing UI even more. Teams tidying up their token naming and semantic layers (roles like `color-surface-primary`, not just raw hex values) tend to get far more consistent output from any AI tool pointed at their design system.
This isn't a new design-systems principle — clear naming and semantic tokens have been best practice for years — but it's getting a fresh push now that agents, not just humans, are reading your libraries. Messy systems used to just slow down handoff; now they quietly break automation too.
Coach
audit one component in your Figma or Penpot library — check if its variables are named clearly enough that a stranger (human or AI) could guess what each one is for.
Google's Material Design 3 popularised dynamic, token-based theming back in 2021, and it's still what most design-system setups get measured against. If you're building variables in Figma or tokens in Penpot, M3's structure is worth studying, not because it's new, but because it's proven.
open Material 3's token docs and compare their primitive-vs-role token split against your own Figma or Penpot library — note one gap you could fix this week.
Creative Market's 2026 trend forecast flags 'Glasscore' — blur, glow and translucent layers — as a rising visual style. For teams running token-based design systems, that means more theming flexibility, not just flat colour tokens.
Open your team's (or a starter) design system file and check whether blur/elevation tokens exist — if not, sketch one variant using Figma or Penpot's effect styles.
Some teams are wiring AI coding assistants into their design token workflow, using rules and MCP connections to keep components consistent. It's promising but still fragile in practice.
pick one component in your (or a practice) design system and check whether its tokens are named consistently enough that an AI tool could use them without guessing.
