Figma Launches Specs to Guide AI Agents With Design Rules and Expands Code Layers at Config India

Figma Specs Gives AI Agents a Design Rulebook

Figma introduced Specs, a Markdown editor designed to help teams document their design language and provide clear guidelines for AI agents working on the platform1

1

2

2

. The announcement came at the company's first Config India event in Bengaluru, marking a significant shift in how AI-driven design workflows operate. Figma Specs allows users to define their design systems in a simple, structured way that both human teams and AI agents can reference while creating designs4

4

. The document can exist as a standalone file in Figma or co-exist within the canvas, providing flexibility in how teams organize their design context1

1

.

What sets Specs apart from traditional documentation is its ability to reference other Figma elements directly. Users can embed FigJam diagrams, code layers, and designs right within the Specs document, ensuring text and visual explorations sit side by side instead of living in screenshots or outdated links3

3

. Teams can bring design libraries, code libraries, and guidelines into this centralized system to manage context for their design system1

1

. This matters because AI agents can now consult these materials to adhere to brand design rules more consistently when creating content2

2

.

Code Layers Opens for Wider Testing

Figma moved Code Layers into public beta after introducing the feature in private beta back in June1

1

4

4

. Code Layers adds coding to designs on canvas, enabling teams to build, explore, edit, and compare code-backed prototypes directly on the Figma Design canvas and push them all the way to production3

3

. Teams can create code layers by prompting the Figma agent, pulling from their GitHub repository, or from a coding agent via Model Context Protocol3

3

.

Users can ask the agent to turn a design into code or change part of the code to iterate on a prototype1

1

2

2

. Derek Onay, lead product designer at Rocket Money, used the Figma agent to rebuild an existing design in code using his team's exact design system component names. "With code layers, the real value is in having the ability to better communicate ideas and gain stakeholder alignment. I can share a working prototype and meet my team where they already are, in Figma," Onay said3

3

. This brings design and development closer together on the full-stack creative canvas, potentially reducing the back-and-forth involved in testing an idea before building the final product4

4

.

AI Integrations Expand With 20+ New Partners

Figma announced support for over 20 new tools through its Model Context Protocol, including OpenCode, Dia, Grok Bot, and Indian AI startup Sarvam1

1

4

4

. Dr. Pratyush Kumar, CEO and co-founder of Sarvam AI, highlighted the partnership: "We're excited to partner with Figma in an India-first AI collaboration. By combining our expertise in building AI for India with Figma's rich design context, we can help teams build higher quality products, reduce rework, and accelerate overall product development"3

3

. These AI integrations expand the platform's capabilities to guide AI with design rules across different tools and workflows.

Payload Integration Enables Dynamic Websites

Figma is integrating Payload, the open-source headless CMS it acquired last year, with Figma Make for generating dynamic websites and directly managing content1

1

4

4

. The integration enables users to build dynamic websites and manage content within the same workflow, allowing teams to ship websites and internal tools backed by real data3

3

. Figma reported that Payload downloads have increased sixfold over the past 12 months1

1

2

2

.

What This Means for Product Teams

Figma Chief Design Officer Loredana Crisan explained the broader context: "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"1

1

. She noted that 17 times as many lines of code are being produced today compared to the past, while releases have increased only 1.3 times. "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," Crisan said2

2

.

CEO Dylan Field emphasized the shift in how teams work: "Customers often tell us they prefer working together with their teams on the canvas rather than alone with coding agents in a terminal or IDE. Figma was the first to introduce the multiplayer canvas for teams to design together. The next evolution is a full-stack creative canvas where teams and agents can build together, from idea to ship, in a visual-first way"3

3

. These announcements came one week after Figma launched its on-canvas agent into general availability1

1

3

3

.

Figma opened its first office in India late last year with sales, partnership, go-to-market, and product support functions1

1

. India is now Figma's largest market by users outside the United States, with the platform used by 40% of India's top 100 companies listed on the Bombay Stock Exchange2

2

. Watch how these AI-powered features reshape collaboration between designers, developers, and AI agents in the coming months.