For complex or nuanced interactions, build small, single-purpose coded tools. These "vibe tools" aren't for building the entire prototype but for tuning specific parameters—like animation easing—to achieve the perfect feel, blending different creation methods for the final result.
Related Insights
To bridge the gap between design and code, use a control panel library like Leva. Ask your AI assistant to implement it, giving you real-time sliders and inputs to fine-tune animation timings, easing curves, and other interaction parameters without constantly rewriting code.
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).
When building his own site, MDS doesn't aim for pixel-perfect Figma files. He gets the design to 85% completion, establishing the core direction, and then moves to code to finalize details like hover states and animations where the interactive "feel" is paramount.
AI coding agents enable "vibe coding," where non-engineers like designers can build functional prototypes without deep technical expertise. This accelerates iteration by allowing designers to translate ideas directly into interactive surfaces for testing.
Instead of creating multiple static mockups, prompt the AI to build a widget directly into a prototype that allows clicking through different design styles. This provides a live, interactive way to evaluate options within the actual user interface.
When working on a complex website, de-risk the development of new, intricate features by building them in a completely separate repository. Use "gray boxing" to nail the feel and get approval on the isolated prototype before attempting to integrate it into the main, complex codebase.
To rapidly iterate on interactive ideas in code, create your own version of "Command D." Instead of hard-coding values, build a simple control panel with variables for parameters like speed or distance, allowing for easy adjustment and testing of multiple variations.
The panel suggests a best practice for AI prototyping tools: focus on pinpointed interactions or small, specific user flows. Once a prototype grows to encompass the entire product, it's more efficient to move directly into the codebase, as you're past the point of exploration.
Instead of starting in Figma, prototype complex web animations using "gray boxing," a technique from game development. By using basic shapes and code (like HTML/CSS/3JS) to define the core flow and feel, you can validate the interaction's energy before investing in detailed visuals.
When exploring an interactive effect, designer MDS built a custom tool to generate bitmap icons and test hover animations. This "tool-making" mindset—creating sliders and controls for variables—accelerates creative exploration far more effectively than manually tweaking code for each iteration.