Key points
- Figma Specs is a new Markdown editor for defining design language and brand rules.
- The code layers feature moves from private to public beta, allowing coding on canvas.
- These tools aim to make AI agent outputs more predictable and aligned with design systems.
The short version
- Figma announced Figma Specs, a Markdown editor that lets users define design language for teams and agents.
- The company released code layers into public beta, enabling users to add code to designs for interactive prototypes.
- These features help steer AI agents to adhere to specific brand guidelines and design system contexts.
The details
Design platform Figma announced a new Markdown-based editor called Figma Specs during its first Config event in India, according to TechCrunch. This tool allows users to define their design language in a simple format. The document serves as a reference for both human teams and AI agents while designing within the platform. Users can place Specs as a standalone file or co-locate them within the canvas.
Beyond basic text editing, the Specs editor lets users reference other Figma elements. This includes items on the canvas, embedded FigJam diagrams, code layers, and existing designs. Teams can also import additional context, such as design libraries, code libraries, and guidelines. This centralized system helps manage the context for the design system, allowing agents to refer to these rules when generating content.
Figma also expanded access to its code layers feature, which adds coding capabilities to designs on the canvas for more interactive prototypes. The company announced this feature in private beta in June, but made it available in public beta during the India event this week. Users can ask the platform’s agent to turn a design into code or modify specific parts of the code to iterate on a prototype.
The context
Figma has made its agent on canvas available to a wider user base in the past week, according to TechCrunch. The company acknowledges the non-deterministic nature of AI, which can lead to unpredictable results. These new tools are intended to steer the AI toward more predictable outcomes that align with brand standards.
Loredana Crisan, Figma’s chief design officer, told TechCrunch that software teams use the platform to decide what to build and ship. She noted that there are 17 times more lines of code being produced today than in the past, but only 1.3 times more releases. Much of that code is built to discover the product rather than to ship, serving a design purpose.
The company said it is also supporting over 20 new tools with its Model Context Protocol (MCP). These include Open Code, Dia, Grok Bot, and Indian AI startup Sarvam, according to TechCrunch. This expansion aims to integrate third-party agents that adhere to the brand’s design rules better while creating with AI.
What to watch
- Monitor how Figma Specs integrates with existing design system workflows and version control processes.
- Observe the stability and accuracy of the code layers feature as it moves through the public beta phase.
- Track the expansion of MCP support to see which third-party tools become reliable for enterprise design automation.
- Watch for updates on how effectively these tools constrain AI agents to prevent deviations from brand guidelines.
What it means for organisations
Organisations adopting AI-driven design tools need to evaluate how these new features impact their governance and compliance workflows. Teams should assess whether the Specs editor provides sufficient control over brand consistency for automated outputs. Design and engineering leaders must determine if the code layers feature aligns with their development standards and security requirements. It is essential to involve legal and compliance teams early to review how AI agents interpret and apply design rules. Organisations should also plan for training staff on these new controls to ensure consistent usage across departments.
What to do and how to stay safe: Figma
- Review current AI usage policies to see if they cover design platforms and automated code generation.
- Test the Figma Specs editor with a small team to evaluate how well it enforces brand guidelines.
- Assess the security implications of integrating third-party AI agents via the Model Context Protocol.
- Ensure design teams document their brand rules clearly before relying on AI agents to apply them.
Step-by-step guide: Secure Home Routers for Small Business Networks
General security guidance from the TechSec Headlines newsroom. It is not confirmed advice from the organisations named in this story.
Frequently asked questions
What is Figma Specs?
Figma Specs is a Markdown-based editor that lets users define their design language and serve as a reference for teams and AI agents.
Is the code layers feature available to everyone?
Yes, Figma made the code layers feature available in public beta during its Config event in India.
Why is Figma adding these tools for AI agents?
The company aims to provide tools to steer AI towards more predictable outcomes and adhere to brand design rules better.
