Published 26 August 2026 · Source dated 8 August 2026
As AI agents start reading design files directly, tidy tokens and naming are becoming a new kind of documentation. A messy system doesn't just confuse humans anymore — it confuses agents too.
Design systems chatter has been circling one idea: tokens and component naming aren't just for designers and devs anymore — they're also the data an AI agent reads to understand a system. A token layer a human could squint through and figure out is a much bigger problem when an agent is trying to map it to code.
This isn't a brand new skill, it's an old one (structure, naming, clear documentation) getting a fresh reason to matter. Teams that already keep their systems tidy are finding it pays off twice over: cleaner for humans, and it actually works with AI tooling too.
Follow the ongoing conversation on design systems feeds if you want to track how this settles.
Call this adoption: it builds on established practice, with a new incentive attached.
Coach
Open your component library and rename one vaguely-labelled token or layer (like "Frame 42") into something a stranger — human or AI — could actually understand.
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.
