Figma Agent Features Redefine AI Design Workflows

Figma Agent Features Arrive at First Config India Event

Figma has announced a set of new Figma agent features at its first Config event in India, giving teams clearer ways to direct how AI agents work across its platform. The updates include a Markdown-based editor, wider access to code layers, and a deeper integration with the Payload headless content management system.

The common goal behind these releases is control. As AI agents take on more design and build tasks, Figma is creating tools that help them follow a brand’s design rules instead of working without guidance.

Figma Specs Defines Your Design Language

The main addition is Figma Specs, a Markdown-based editor that lets users define their design language in a simple format. The resulting document can serve as a shared reference for both teams and agents while designing inside Figma.

Specs can exist as a standalone file or sit within the canvas itself. Beyond acting as a text editor, users can reference other Figma elements, including items on the canvas, and embed FigJam diagrams, code layers, and designs.

Teams can also add more design context, such as design libraries, code libraries, and guidelines that manage context for the design system. Agents can refer to this centralized system to follow established rules.

Why a Single Source of Truth Matters

The feature tackles a familiar problem with AI-assisted design: consistency. When agents and designers work from scattered references, output drifts. A structured, central reference gives humans and agents alike something concrete to follow.

Code Layers Opens to Public Beta

Figma also made its code layers feature available in open beta. This function adds coding to designs on the canvas, enabling more interactive prototypes.

The company first announced code layers in private beta back in June. At its India event, it opened the function to a public beta so more users can test it.

Users can ask the agent to turn a design into code or change part of the code to iterate on a prototype. This shortens the loop between designing an idea and testing it.

Steering AI Toward Predictable Outcomes

Figma’s agent on canvas became available to a wider user base in the past week. Because AI is non-deterministic by nature, the company is offering tools intended to steer it toward more predictable results.

Figma’s chief design officer, Loredana Crisan, framed the shift around how software teams work. “We see Figma as the place where software teams come to decide what they build and ship,” she said. “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.”

Crisan pointed to a gap between how much code is produced and how much actually ships. “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,” she said. “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.”

That distinction helps explain Figma’s focus. Much AI-generated code exists to explore ideas rather than to ship them, which makes governance at the design stage more important.

MCP Support Expands to More Than 20 Tools

Figma said it now supports over 20 new tools through its MCP, including Open Code, Dia, Grok Bot, and Indian AI startup Sarvam. The expansion widens the range of external agents and tools that can connect to Figma workflows.

Payload Integration Comes to Figma Make

Figma acquired the open source headless CMS Payload last year. Now the company is integrating Payload with its Figma Make product, which generates dynamic websites and manages content directly.

According to Figma, Payload’s downloads have increased sixfold over the last 12 months. The integration pairs website generation with content management in a single workflow.

Figma’s Growing Bet on India

Figma opened its first office in India late last year, staffing it with sales, partnership, go-to-market, and product support functions. The company said India is its biggest market in terms of users outside the United States.

Figma also noted that its platform works with 40% of India’s top 100 companies listed on the Bombay Stock Exchange. Holding its first Config event in the country reflects that footprint.

What These Figma Agent Features Mean for Teams

For design and engineering teams, the practical takeaway is more structure around AI assistance:

• Defined design rules through Figma Specs, so agents have a reference to follow

• Design-to-code iteration through code layers in open beta

• Broader tool connections through MCP support for more than 20 tools

• Content and site generation through the Payload integration in Figma Make

Together, these updates suggest Figma wants agents to operate inside guardrails rather than alongside them. Whether that leads to more predictable output will depend on how teams adopt Specs and how well agents interpret the context they receive.

For now, the direction is clear: as AI takes on more design and build work, the platform layer that defines the rules may matter as much as the agents themselves.