Figma Expands AI Capabilities with Design Rules and Code Tools

Figma is expanding its AI capabilities with new tools to help companies guide AI agents in design, code generation, and product building. The updates include Figma Specs, a Markdown-based editor for documenting design systems, and the public beta of Code Layers. These features are designed to give AI agents more context about a company’s brand, design standards, and existing code, helping them produce work that aligns more closely with how teams build and ship software. The goal is to reduce the gap between what a team intends to build and what an AI agent actually produces.

Figma Specs allows teams to document their design language in a format that both people and AI agents can reference. This gives teams a central place to describe the rules and conventions that should guide their work. For example, a company could document its brand colours, typography, interface components, and design principles. An AI agent could then use that information as a reference when generating a new interface or modifying an existing design.

Figma is also expanding access to Code Layers, a feature that allows users to add code to designs on the canvas to create more interactive prototypes. With Code Layers, users can ask Figma’s AI agent to turn a design into code or modify specific parts of the code to refine a prototype.