Contrary to traditional digital design, the modern AI-assisted workflow involves broad, conceptual exploration on canvas-like tools (e.g., Paper) and sweating the final visual details directly in code. Pixel-nudging in design software like Figma is becoming obsolete for last-mile fit and finish.

The debate over designing in code versus a visual canvas is outdated. The modern workflow isn't about choosing one, but fluidly moving between both tools based on the task: canvas for broad exploration and code for deep, interactive prototyping.

In an era of rapidly changing tools, Cursor's design team values core design principles above all. The ability to iterate towards product-market fit is more critical than mastery of specific models or workflows, as the fundamental design process remains the same.

AI-powered "vibe coding" is reversing the design workflow. Instead of starting in Figma, designers now build functional prototypes directly with code-generating tools. Figma has shifted from being the first step (exploration) to the last step (fine-tuning the final 20% of pixel-perfect details).

With advanced AI coding tools and a robust design system, Snap's engineers build functional prototypes so quickly that the traditional design-first workflow is inverted. Instead of waiting for Figma mock-ups, teams now build and show working code to decide which ideas win.

The traditional, linear design process is obsolete. The new way of working is a fluid, 'start anywhere' model where an idea can begin in code, a document, a canvas, or a Slack thread, with creators bouncing between tools as needed to develop the concept.

Instead of creating static mockups in Figma, Cursor's design team prototypes directly in their AI code editor. This allows them to interact with the "life states of the app" and get a more realistic feel for the product, bridging the gap between design and engineering.

AI co-pilots have accelerated engineering velocity to the point where traditional design-led workflows are now the slowest part of product development. In response, some agile teams are flipping the process, having engineers build a functional prototype first and then creating formal Figma designs and UI polish later.

John Bai from Cursor still begins in Figma to quickly visualize concepts and gain conviction. Figma acts as a storyboard and idea repository before he uses AI tools to translate those ideas into high-fidelity, interactive prototypes.