Figma Expands Its Design-to-Code Ecosystem with "Specs," Public Beta for Code Layers, and Payload CMS Integration

NEW DELHI — In a major push to bridge the widening gap between creative vision and production code, collaborative design platform Figma has announced a suite of powerful new developer and AI-centric tools. Unveiled during the company’s inaugural Config event in India—which has swiftly grown to become Figma’s largest user base outside the United States—the updates focus heavily on bringing rigorous structure to the chaotic world of generative artificial intelligence (AI) in design.

At the heart of the announcements is Figma Specs, a native Markdown-based editor designed to help teams codify brand rules, centralize design systems, and steer AI agents toward predictable, brand-compliant outcomes. Alongside Specs, Figma moved its highly anticipated Code Layers feature into public beta and detailed a deep integration with Payload, the open-source headless Content Management System (CMS) it acquired last year.

These updates arrive as the software industry grapples with an unprecedented explosion in AI-generated code, a phenomenon Figma leadership believes is fundamentally shifting the purpose of prototyping.

Main Facts

• Introduction of Figma Specs: A new Markdown-based editor that functions as a single source of truth for design languages, brand guidelines, and rules that both human teams and AI agents can reference.
• Public Beta for Code Layers: First teased in a private beta in June, Code Layers allows designers to embed live code directly onto the canvas, enabling highly interactive prototypes and direct AI-driven code modification.
• Payload CMS Integration: Figma is integrating its recently acquired open-source headless CMS, Payload, directly into the "Figma Make" product to streamline the creation of dynamic, content-managed websites.
• Expanding AI Ecosystem Support: Figma is adding support for over 20 new tools via its Model Context Protocol (MCP), including Open Code, Dia, Grok Bot, and Indian AI startup Sarvam.
• Strategic Focus on India: The announcements were made during Figma’s first-ever Config event in India, reflecting the country’s status as the company’s largest market outside the U.S., where it currently serves 40% of the top 100 companies listed on the Bombay Stock Exchange (BSE).

Chronology of Developments

To understand how Figma arrived at this juncture, it is helpful to trace the platform’s rapid evolution over the past year:

1. Late 2024: Signaling its aggressive international expansion strategy, Figma officially opened its first office in India, establishing dedicated local teams for sales, partnerships, go-to-market strategies, and product support.
2. Late 2024 (Acquisition): Figma strategically acquired Payload, an open-source headless CMS, laying the groundwork for a future where design canvases could dynamically interact with real back-end data architectures. Over the next 12 months, Payload’s downloads would experience a staggering sixfold increase.
3. June 2025: Figma rolled out a private beta for Code Layers, introducing native code support directly onto the design canvas to handle complex animations and interactive prototypes.
4. Early October 2025: Figma expanded the accessibility of its on-canvas AI agent to a much wider user base, empowering creators to generate interface elements and layouts through conversational prompts.
5. Mid-October 2025 (Config India): At its debut Indian Config event, Figma brought Code Layers into public beta, unveiled Figma Specs, integrated Payload CMS with Figma Make, and expanded its MCP ecosystem to support more than 20 external AI tools.

Supporting Data and Technical Architecture

The technical impetus behind Figma’s recent updates lies in a fundamental inefficiency in modern software development. Speaking to TechCrunch, Figma’s Chief Design Officer, Loredana Crisan, highlighted a glaring industry imbalance:

"We see Figma as the place where software teams come to decide what they build and ship. And so for that, I think one of the key things to keep in mind about what AI has changed and what it made available is the ability to build. There are 17-times more lines of code being produced today than in the past. But when you’re looking at releases, only 1.3-times more releases. A lot of that code actually is not necessarily built to ship, but really built to discover what the product is. It’s built to design."

Figma Specs: Taming AI Non-Determinism

Because generative AI models are inherently non-deterministic, they frequently hallucinate or drift away from established brand guidelines, color palettes, and typographic hierarchies. Figma Specs addresses this by giving teams a flexible text editor that can exist either as a standalone document or live directly alongside elements on the canvas.

Specs allows users to seamlessly reference other Figma elements, embed FigJam diagrams, and integrate deep code layers. More importantly, it creates a centralized context repository for design and code libraries. Both Figma’s native on-canvas agent and third-party AI agents can ingest this repository to ensure that every AI-generated component strictly adheres to enterprise design systems.

Code Layers and Prototyping

With Code Layers now entering public beta, the barrier between design and functional code has blurred further. Designers and developers can write or embed actual code segments into the design canvas. During the beta period, users can prompt Figma’s AI agent to instantly transform static visual designs into functional code, or make targeted programmatic tweaks to refine animations and interactions on the fly.

Payload CMS Integration

Following its acquisition, Payload has seen dramatic growth, with downloads multiplying sixfold over the past year. Figma is now tightly coupling Payload with its "Figma Make" product. This integration allows product teams to generate dynamic, data-driven websites within Figma and manage backend content natively, closing the loop between design mockups and live web production.

Furthermore, Figma is broadening its developer ecosystem by supporting over 20 new tools through its Model Context Protocol (MCP). Notable additions include Open Code, Dia, Grok Bot, and Sarvam, an innovative Indian AI startup building foundational models tailored to regional languages and enterprise needs.

Official Responses and Strategic Vision

Figma’s decision to launch these products at its first Indian Config event underscores the region’s mounting influence on global software development. Having established a physical footprint in the country late last year, Figma has cemented its position as an essential tool for domestic enterprises. According to company figures, the platform is currently utilized by 40% of the top 100 companies listed on the Bombay Stock Exchange.

Crisan emphasized that Figma’s ultimate objective is to serve as the singular source of truth where cross-functional product teams—comprising designers, product managers, and software engineers—converge to negotiate, conceptualize, and execute software. By providing robust guardrails for AI through tools like Specs and Code Layers, Figma is positioning itself not just as a visual canvas, but as an intelligent orchestration layer for the entire software development lifecycle.

Implications for the Design and Engineering Industry

The introduction of Figma Specs, open-beta Code Layers, and headless CMS integrations carries profound implications for the future of digital product creation:

• The Rise of "Design Engineering": As Code Layers gains widespread adoption, the traditional silos separating visual designers from front-end developers will continue to dissolve. Designers are increasingly expected to understand state management and basic coding logic, while engineers can leverage AI to iterate visually within production-ready frameworks.
• Controlling AI Chaos: Enterprises have long hesitated to deploy generative AI tools for production-grade design due to compliance and brand integrity risks. By giving organizations the ability to hardcode their design rules into Markdown-based specs that AI agents must read and respect, Figma is effectively offering a governance framework for generative design.
• Consolidation of the Tech Stack: By absorbing Payload CMS and tying it directly into website generation pipelines, Figma is encroaching deeper into the territories traditionally owned by content management systems and no-code website builders. Teams can now design, prototype, code-layer, and content-manage dynamic sites from a single workspace.
• Geographic Shift in Product Innovation: Hosting major global product rollouts in India highlights a broader industry trend: emerging tech hubs in the Global South are no longer just consumer markets, but primary proving grounds for cutting-edge developer tooling and enterprise collaboration software.

As these features roll out to the public beta community, Figma is betting that the key to winning the AI era isn’t just generating more content or code faster—it’s giving human creators the precise governance tools needed to ensure that what gets built is actually worth shipping.