Published 10 September 2026 · Source dated 27 August 2026
As MCP-connected agents generate assets straight from a prompt, tools are being sold on how well they 'follow your brand kit' — meaning your tokens, components and naming now double as machine-readable rules, not just a Figma library.
One AI design-tool vendor's pitch this year is explicit: describe what you want in plain English, and the AI Design Agent builds it 'with your brand kit' — every output following the design system automatically, no manual tweaking.
That's a shift in what a design system is *for*. It's not just a reference for humans anymore; it's the constraint file an agent reads before it generates anything. Messy naming, undocumented exceptions and 'just eyeball it' tokens become AI's problem too — and AI is less forgiving of ambiguity than a human teammate.
**Why adoption:** this is a live product feature being marketed now, not a future promise.
Coach
pick one component in your Figma or Penpot library and check whether its naming and constraints are clear enough that an AI — or a new hire — could use it without guessing.
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.
