Why Agents Keep Getting Lost in Your Design System

26 Jun 2026 · 1 min

Watch on YouTube

0:41

In this segment, the speaker argues that traditional design systems, while still valuable, lack a dedicated layer that enables autonomous agents to navigate them effectively. He highlights three core shortcomings: (1) composition libraries and documentation are often interpretive and not explicitly structured for machine consumption; (2) naming conventions and composition logic are insufficiently explicit, leaving agents unable to discern how to use components; and (3) agents lose contextual information across sessions and resets, unlike human designers who can retain long‑term context. The speaker calls for clearer, agent‑friendly documentation, stricter naming rules, and mechanisms to preserve agent context throughout workflows.

Chapters

it's not that design systems don't matter anymore. It's just that we need to add another layer so really agents can find their way. So we need to make sure that our composition libraries and documents, which tend to be a little bit interpretive and not clearly laid out, are very clearly laid out and written in a way that agents can understand. Maybe our naming and composition logic isn't as explicit as it needs to be. We might have lack of naming rules. That when agents look at things, they don't really understand how to use those different elements. We might have things that we can retain easily because we can remember things for a long time, but an agent is going to lose that context all the way through the different various working sessions and different resets.