In this segment, the speaker outlines a practical workflow for integrating AI coding assistants into UI design work, emphasizing a terminal‑centric setup (tmux, lazy‑git) with a chat pane for agents like Claude Code, Codex, or Cursor. While these agents excel at generating code from prompts, the speaker stresses that they still require concrete design references from tools such as Figma. Designers often capture screenshots of UI components or Figma frames to feed the model, but current computer‑vision‑enabled agents struggle to grasp the higher‑level design intent and to compose a coherent design system from a “10,000‑foot” perspective. The speaker notes that model behavior varies with context depth—more context can improve fidelity but may also lead the model to cut corners. Overall, the talk highlights the gap between low‑level pixel accuracy and holistic design system understanding in today’s AI‑assisted design pipelines.
Chapters
they don't necessarily understand the intention of a given component or how to compose a consistent design system holistically from a 10,000-foot view. A lot of folks have transitioned to using something like a Claude Code or a Codex where they're chatting with the agent. You can even still do that in Cursor. I think most of us at Headway are using a terminal-based workflow with tmux and maybe something like lazy git in a left pane and, and your chat in the right pane. At least that's one of the ways that I'm, I'm doing a lot and I'm in the IDE less and less these days. But if you have an actual design that you're working from and you're not just quote unquote vibe coding or saying, hey, build me this thing and just hoping that it's gonna grab UI somewhere. You do also have to still be in Figma. And I think the next level up from chatting and, and vibe coding is a lot of folks probably take screenshots of either a UI component that they see in a kit somewhere online or maybe of their Figma screen directly. And what zoom are you at in Figma? What did you crop in or out? What particular button or element is visible in that frame or not in Figma? So it can get kind of dicey if you're relying on sort of that computer vision capability of the agents and the current Frontier models. They're good, right? They're really quite good. And they can even measure pixels and figure out the rounding and all of that, but they don't necessarily understand the intention of a given component or how to compose a consistent design system holistically from a 10,000-foot view. They just understand you want this thing achieved. I will do everything I can to achieve it unless my context is high, then I'll cut a few corners, right? Can even fall further down the path there. Even when you have specific Figma files that you're, say, sending a screenshot. [MUSIC] [MUSIC]
