AI News · New apps ·
Figma adds Specs editor and design context rules for AI agents
Figma announced Figma Specs, a Markdown-based editor where teams define their design language, along with centralized design context management that agents can follow. Code layers moved to open beta and Figma's MCP gained more than 20 new tools. The features were unveiled at Figma's first Config event in India.
Key points
- Figma Specs is a Markdown-based editor for defining a team's design language.
- Code layers, which add code to designs, are now in open beta.
- Figma's MCP now supports more than 20 new tools, including Dia and Sarvam.
What happened: Figma announced new features at its first Config event in India that give its own agents and third-party agents a set of brand design rules to follow, TechCrunch reported. The centerpiece is Figma Specs, a Markdown-based editor where users define their design language as a standalone file or inside the canvas.
The details: Specs can reference canvas elements and embed FigJam diagrams, code layers and designs, so teams and agents can use it as a reference. A new design context management system lets teams add design libraries, code libraries and guidelines to one central place that agents can follow. Code layers, first shown in private beta in June, are now in open beta and let users ask the agent to turn a design into code. Figma said its MCP now supports more than 20 new tools, including Open Code, Dia, Grok Bot and Indian startup Sarvam. It is also integrating Payload, the open-source CMS it acquired last year, with Figma Make.
Background: Chief design officer Loredana Crisan told TechCrunch that "there are 17-times more lines of code being produced today than in the past." Figma says India is its largest market by users outside the United States.
What to watch: Figma has not disclosed pricing for the new features or a general availability date for Specs. Teams should watch how well agents actually follow the defined rules in practice.
Our take
Design teams using AI agents get a way to give those agents shared brand rules, which can make AI-generated designs more consistent.