Published 17 September 2026 · Source dated 8 September 2026
As canvas agents and coding agents start operating directly on design files, how well-structured your tokens are starts to matter for machines, not just humans. It's early signal, not proven best practice yet.
Design-systems commentary is increasingly focused on tokens as the thing AI agents actually need to interpret a file correctly — colours, spacing and type set up as real styles rather than hardcoded values. The logic: an agent working on canvas or pulling code into Figma can only stay 'grounded' in a system if that system is legible in the first place. There's no hard adoption data yet showing this changes outcomes — treat it as an emerging argument for good token hygiene, not a mandate. The habit was already good practice before AI agents showed up; they're just raising the stakes for skipping it.
Coach
open your current Figma or Penpot file and check whether your colours and spacing are real tokens/styles or just hardcoded hex values — fix one screen's worth.
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.
