Figma 发布新功能,让平台上的 AI Agent 遵循设计规范
Figma announces new features to define how agents work on its platform
- 1Figma 发布 Figma Specs,用 Markdown 编辑器定义设计语言,供团队和 Agent 设计时参照
- 2代码图层功能从 6 月私测转入公测,可让 Agent 把设计转成代码或改代码迭代原型
- 3Figma 的 MCP 新增支持超过 20 款工具,包括 Open Code、Dia、Grok Bot 和印度创企 Sarvam
- 4官方称 Payload 下载量过去 12 个月增长 6 倍,该无头 CMS 已整合进 Figma Make 生成动态网站
Figma 把设计规范做成 Agent 可读取的约束层,AI 生成从自由发挥转向遵循品牌规则,设计系统的文档化成为新基建。
- 影响:设计团队需要把设计语言和组件库整理成 Agent 可读的文档,这会成为新的维护工作;设计到代码与内容管理的链路在 Figma 内打通后,从原型到上线的流程有机会收拢进一个平台。
- 参考:可考虑让设计团队先用 Figma Specs 盘点现有设计规范并整理成文档;代码图层公测期间可选一个高频原型场景试用,对比迭代耗时;再评估 Figma Make 加 Payload 能否替代部分建站流程。
- 依据:新功能发布与开放范围为官方口径,暂无独立验证;代码量增 17 倍而发布量仅增 1.3 倍、Payload 下载量增 6 倍均为 Figma 高管与公司引用的数据。
Design platform Figma announced a new Markdown-based editor to help define a company’s design, bring in design and code libraries, and integrate with the Payload headless content management system during the company’s first Config event in India. Through some of these features, the company aims to provide a definition for its own and third-party agents to adhere to a brand’s design rules better while creating with AI.
The company debuted a new feature called Figma Specs, which is a markdown editor that lets users define their design language in a simple way. The document can serve as a reference for teams and agents while designing in Figma. Specs can exist as a standalone file in Figma or can co-exist within the canvas. Apart from acting as a text editor, users can reference other Figma elements, such as elements on the canvas and embed FigJam diagrams, code layers, and designs.
What’s more, teams can bring in more context about design, including design libraries, code libraries, and guidelines to manage context for the design system. Agents can also refer to this centralized system to adhere to rules.

In the past week, the company made its agent on canvas available to a wider user base. However, given the non-deterministic nature of AI, the company is providing tools to steer it towards more predictable outcomes.
Figma also made its code layers feature, which adds coding to designs on canvas for more interactive prototypes. The company announced this feature in private beta back in June. At its India event this week, the company is making the function available in public beta to let more users test it out. Users can also ask the agent to turn a design into code or change a part of the code to iterate on a prototype.

“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,” Figma’s chief design officer Loredana Crisan told TechCrunch. “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.”
The company said it is also supporting over 20 new tools with its MCP, including Open Code, Dia, Grok Bot, and Indian AI startup Sarvam.
Last year, Figma acquired open-source headless CMS Payload. Now, the company is integrating it with its Figma Make product for generating dynamic websites and directly managing content. The company said that Payload’s downloads have increased sixfold in the last 12 months.
The company opened its first office in India late last year with sales, partnership, go-to-market, and product support functions. Figma said that the country is its biggest market in terms of users outside the United States. The company noted that the platform works with 40% of India’s top 100 companies listed on the Bombay Stock Exchange.
When you purchase through links in our articles, we may earn a small commission. This doesn’t affect our editorial independence.
Ivan covers global consumer tech developments at TechCrunch. He is based out of India and has previously worked at publications including Huffington Post and The Next Web.
You can contact or verify outreach from Ivan by emailing [email protected] or via encrypted message at ivan.42 on Signal.
来源:TechCrunch · AI · techcrunch.com