# Figma agent

Figma agent is a conversational AI tool used within Figma files to generate designs, make edits, apply design systems, provide feedback, and handle busywork.

This is one page of public article previews, not the complete archive. Follow Next page to continue. Summaries are not the original full articles.

## How 3D transforms and Figma's agent brought a launch video to life

DevFeed: [How 3D transforms and Figma's agent brought a launch video to life](<https://devfeed.tech/articles/how-3d-transforms-and-figma-s-agent-brought-a-launch-video-to-life-130450.md>)

Original publisher: [Read original article](<https://www.figma.com/blog/how-3d-transforms-and-figmas-agent-brought-a-launch-video-to-life/>)

Author: Chad Colby

Published: 2026-11-12T14:00:00Z

Content type: article

Language: en

Sources: [Figma Blog](<https://devfeed.tech/sources/figma-blog.md>)

Topics: [3D](<https://devfeed.tech/topics/3d.md>), [Figma agent](<https://devfeed.tech/topics/figma-agent.md>), [generative plugins](<https://devfeed.tech/topics/generative-plugins.md>), [Figma](<https://devfeed.tech/topics/figma.md>)

Tags: [3d-design](<https://devfeed.tech/tags/3d-design.md>), [agent](<https://devfeed.tech/tags/agent.md>), [animation](<https://devfeed.tech/tags/animation.md>), [brand](<https://devfeed.tech/tags/brand.md>), [canvas](<https://devfeed.tech/tags/canvas.md>), [css](<https://devfeed.tech/tags/css.md>), [figma](<https://devfeed.tech/tags/figma.md>), [launch](<https://devfeed.tech/tags/launch.md>), [motion](<https://devfeed.tech/tags/motion.md>), [plugins](<https://devfeed.tech/tags/plugins.md>), [shaders](<https://devfeed.tech/tags/shaders.md>), [studio](<https://devfeed.tech/tags/studio.md>), [video](<https://devfeed.tech/tags/video.md>)

### AI overview

Figma's Brand Studio used 3D transforms to explore spatial layouts in motion while keeping underlying artwork editable. The Figma agent helped repeat typography along the Z axis and construct geometry; an agent-built generative plugin arranged objects in grids, helixes, rings, or randomized scatters, avoiding manual placement. Designers compared variations on the canvas, then refined artwork, colors, and gradients through components even after animation began. Shaders added color, texture, and light sweeps, while Figma Motion let the team test and adjust movement alongside art direction. The excerpt says 3D transforms are in open beta for Full seat users, map to CSS, and can be inspected and copied in Dev Mode; coding agents can read and create 3D designs through the Figma MCP server.

### Source excerpt

See how Figma's Brand Studio team combined 3D design, agent-built plugins, shaders, and motion to create a video together on the canvas.

## 6 easy ways to use the Figma agent right now

DevFeed: [6 easy ways to use the Figma agent right now](<https://devfeed.tech/articles/6-easy-ways-to-use-the-figma-agent-right-now-126351.md>)

Original publisher: [Read original article](<https://www.figma.com/blog/6-easy-ways-to-use-the-figma-agent-right-now/>)

Author: Emma Webster

Published: 2026-11-09T21:46:00Z

Content type: tutorial

Language: en

Sources: [Figma Blog](<https://devfeed.tech/sources/figma-blog.md>)

Topics: [Figma agent](<https://devfeed.tech/topics/figma-agent.md>), [Figma](<https://devfeed.tech/topics/figma.md>), [User interface design](<https://devfeed.tech/topics/ui-design.md>)

Tags: [agent](<https://devfeed.tech/tags/agent.md>), [animate](<https://devfeed.tech/tags/animate.md>), [animation](<https://devfeed.tech/tags/animation.md>), [apply](<https://devfeed.tech/tags/apply.md>), [canvas](<https://devfeed.tech/tags/canvas.md>), [card](<https://devfeed.tech/tags/card.md>), [code](<https://devfeed.tech/tags/code.md>), [compare](<https://devfeed.tech/tags/compare.md>), [components](<https://devfeed.tech/tags/components.md>), [connectors](<https://devfeed.tech/tags/connectors.md>), [custom](<https://devfeed.tech/tags/custom.md>), [design](<https://devfeed.tech/tags/design.md>), [designers](<https://devfeed.tech/tags/designers.md>), [designs](<https://devfeed.tech/tags/designs.md>), [dev](<https://devfeed.tech/tags/dev.md>), [drive](<https://devfeed.tech/tags/drive.md>), [effect](<https://devfeed.tech/tags/effect.md>), [exploring](<https://devfeed.tech/tags/exploring.md>), [figma](<https://devfeed.tech/tags/figma.md>), [figma-agent](<https://devfeed.tech/tags/figma-agent.md>)

### AI overview

The Figma agent can help turn design feedback into actions and speed up exploration on the canvas. The excerpt describes six workflows: annotate designs using meeting transcripts connected from Granola, Notion, or Google Drive; summarize file comments and suggest or apply updates, with reusable skills for organizing them; create and reuse custom shaders; generate multiple screen variations using a selected design library; build code-backed interactive prototypes; and create and compare motion variations. The examples give prompts and setup steps, such as selecting frames or a library, connecting a source, and using the Motion toolbar to play animations. The agent is available on Starter, Professional, Organization, Enterprise, and higher education plans; Collab, Dev, and View seats can use it in drafts.

### Source excerpt

From making designs more expressive and automating busywork, to exploring more possibilities on the canvas, here are six ways to push designers further with the Figma agent.

## Workflow lab: Test ideas with code layers and the Figma agent

DevFeed: [Workflow lab: Test ideas with code layers and the Figma agent](<https://devfeed.tech/articles/workflow-lab-test-ideas-with-code-layers-and-the-figma-agent-118944.md>)

Original publisher: [Read original article](<https://www.figma.com/blog/workflow-lab-build-with-code-on-the-canvas-using-the-figma-agent-and-code-layers/>)

Author: Mari Kong

Published: 2026-11-04T22:12:00Z

Content type: tutorial

Language: en

Sources: [Figma Blog](<https://devfeed.tech/sources/figma-blog.md>)

Topics: [Figma agent](<https://devfeed.tech/topics/figma-agent.md>), [Figma](<https://devfeed.tech/topics/figma.md>), [User interface design](<https://devfeed.tech/topics/ui-design.md>), [Code review](<https://devfeed.tech/topics/code-review.md>)

Tags: [3](<https://devfeed.tech/tags/3.md>), [agent](<https://devfeed.tech/tags/agent.md>), [alternatives](<https://devfeed.tech/tags/alternatives.md>), [api](<https://devfeed.tech/tags/api.md>), [app](<https://devfeed.tech/tags/app.md>), [canvas](<https://devfeed.tech/tags/canvas.md>), [code](<https://devfeed.tech/tags/code.md>), [compare](<https://devfeed.tech/tags/compare.md>), [designer](<https://devfeed.tech/tags/designer.md>), [explore](<https://devfeed.tech/tags/explore.md>), [feature](<https://devfeed.tech/tags/feature.md>), [figma](<https://devfeed.tech/tags/figma.md>), [figma-agent](<https://devfeed.tech/tags/figma-agent.md>), [ideas](<https://devfeed.tech/tags/ideas.md>), [lab](<https://devfeed.tech/tags/lab.md>), [layers](<https://devfeed.tech/tags/layers.md>), [new-feature](<https://devfeed.tech/tags/new-feature.md>), [prototypes](<https://devfeed.tech/tags/prototypes.md>), [teams](<https://devfeed.tech/tags/teams.md>), [workflow](<https://devfeed.tech/tags/workflow.md>)

### AI overview

Figma code layers let teams bring an existing app onto the canvas, generate interactive alternatives with the Figma agent, compare them side by side, and combine work. In the Pickup example, a designer clones a connected GitHub repository, asks the agent for three delivery-address options, then duplicates and manually edits a version. They can extract the prototype as editable design layers, record its screens as frames, and send design changes back to the code layer. The designer then combines the delivery flow with a teammate's map-grid exploration and asks the agent to describe changes and flag technical implications for developer review. The resulting prototype and spec support review before implementation and release; the article notes code layers are in open beta.

### Source excerpt

Bringing code onto the canvas gives teams a shared space to compare working prototypes side by side, refine a direction, and collaborate on ideas with teammates. This workflow shows how a designer uses code layers and the Figma agent to explore a new feature.

## How we're training a Figma-fluent editing model

DevFeed: [How we're training a Figma-fluent editing model](<https://devfeed.tech/articles/how-we-re-training-a-figma-fluent-editing-model-107194.md>)

Original publisher: [Read original article](<https://www.figma.com/blog/training-a-figma-fluent-editing-model/>)

Author: Josh Clemm

Published: 2026-10-29T21:00:00Z

Content type: article

Language: en

Sources: [Figma Blog](<https://devfeed.tech/sources/figma-blog.md>)

Topics: [post-training](<https://devfeed.tech/topics/post-training.md>), [Figma agent](<https://devfeed.tech/topics/figma-agent.md>), [Figma](<https://devfeed.tech/topics/figma.md>), [rlvr](<https://devfeed.tech/topics/rlvr.md>), [Frontier AI](<https://devfeed.tech/topics/frontier-ai.md>), [Image](<https://devfeed.tech/topics/image.md>)

Tags: [design](<https://devfeed.tech/tags/design.md>), [figma](<https://devfeed.tech/tags/figma.md>), [post-training](<https://devfeed.tech/tags/post-training.md>), [research](<https://devfeed.tech/tags/research.md>), [training](<https://devfeed.tech/tags/training.md>)

### AI overview

Figma's editing model is trained to make canvas changes in Figma's native file format, enabling outputs to be applied directly to designs. The team used supervised fine-tuning on synthetic edit requests paired with successful examples; teacher models generated candidate edits, which deterministic validators and visual judges checked and could send back for revision. The article says SFT alone can limit generalization and requires many examples, so the latest recipe also invests in reinforcement learning, more diverse training examples, reward models, and expert-written criteria. Internal evaluations assess instruction following and edit usefulness alongside speed and cost, combining structural checks, visual judges, and expert review. Figma reports typical tasks are about 20% faster since beta, and the new agent beats or matches its previous production agent in 62% of head-to-head tests with expert designers. These gains reflect improvements across the agent, including models, tools, and harness; the editing model is one part of that progress.

### Source excerpt

We've increasingly seen that specialized post-training can compete with frontier models. Here, we're sharing the research behind how we're translating that to design editing workflows.

## What is Figma?

DevFeed: [What is Figma?](<https://devfeed.tech/articles/what-is-figma-102446.md>)

Original publisher: [Read original article](<https://zapier.com/blog/what-is-figma>)

Author: Jessica Lau

Published: 2026-10-27T04:00:00Z

Content type: article

Language: en

Sources: [Zapier](<https://devfeed.tech/sources/zapier.md>)

Topics: [Figma](<https://devfeed.tech/topics/figma.md>), [User interface design](<https://devfeed.tech/topics/ui-design.md>), [Tool](<https://devfeed.tech/topics/tool.md>), [Figma AI](<https://devfeed.tech/topics/figma-ai.md>), [Figma agent](<https://devfeed.tech/topics/figma-agent.md>)

Tags: [about](<https://devfeed.tech/tags/about.md>), [am](<https://devfeed.tech/tags/am.md>), [basic](<https://devfeed.tech/tags/basic.md>), [bits](<https://devfeed.tech/tags/bits.md>), [but](<https://devfeed.tech/tags/but.md>), [can](<https://devfeed.tech/tags/can.md>), [career](<https://devfeed.tech/tags/career.md>), [designers](<https://devfeed.tech/tags/designers.md>), [figma](<https://devfeed.tech/tags/figma.md>), [i](<https://devfeed.tech/tags/i.md>), [imagination](<https://devfeed.tech/tags/imagination.md>), [look](<https://devfeed.tech/tags/look.md>), [me](<https://devfeed.tech/tags/me.md>), [one](<https://devfeed.tech/tags/one.md>), [productivity](<https://devfeed.tech/tags/productivity.md>), [skills](<https://devfeed.tech/tags/skills.md>), [stretch](<https://devfeed.tech/tags/stretch.md>), [team](<https://devfeed.tech/tags/team.md>), [time](<https://devfeed.tech/tags/time.md>), [up](<https://devfeed.tech/tags/up.md>), [what-is](<https://devfeed.tech/tags/what-is.md>)

### AI overview

Figma is a browser-based collaborative design workspace built around shared files and frames, with tools for interface design, whiteboarding, presentations, developer handoff, marketing assets, and website publishing. Teams use it to create designs and clickable prototypes, map user flows, inspect measurements and code snippets, and leave feedback on shared files. A basic workflow is to create frames, add shapes, text, or images, then use auto layout to arrange responsive groups, components to reuse linked elements, and prototypes to connect screens for review. The free Starter plan includes unlimited drafts, unlimited viewers, templates, and limited AI credits; editing access and fuller collaboration require paid seats. The article notes a learning curve, while Community templates and tutorials can help beginners get started.

### Source excerpt

There's a chance that I may have once stretched the truth about my Figma proficiency only to have my skills tested in real time--in front of a team of designers. (How you're imagining that went is exactly how it went.) Not a shining career moment by any stretch of the imagination, but one of those "it made me who I am today" bits where I can now confidently--and honestly--say that I can whip you up a basic wireframe in Figma if you needed one. (How aesthetically pleasing that wireframe would look i

## How to put your design system to work with the Figma agent

DevFeed: [How to put your design system to work with the Figma agent](<https://devfeed.tech/articles/how-to-put-your-design-system-to-work-with-the-figma-agent-96373.md>)

Original publisher: [Read original article](<https://www.figma.com/blog/how-to-put-your-design-system-to-work-with-the-figma-agent/>)

Author: Wayne Lin

Published: 2026-10-22T22:23:42.427453Z

Content type: tutorial

Language: en

Sources: [Figma Blog](<https://devfeed.tech/sources/figma-blog.md>)

Topics: [Figma agent](<https://devfeed.tech/topics/figma-agent.md>), [Design system](<https://devfeed.tech/topics/design-system.md>), [Figma](<https://devfeed.tech/topics/figma.md>), [AI interaction best practices](<https://devfeed.tech/topics/ai-interaction-best-practices.md>)

Tags: [accessibility](<https://devfeed.tech/tags/accessibility.md>), [agent](<https://devfeed.tech/tags/agent.md>), [ai](<https://devfeed.tech/tags/ai.md>), [context](<https://devfeed.tech/tags/context.md>), [define](<https://devfeed.tech/tags/define.md>), [design](<https://devfeed.tech/tags/design.md>), [design-system](<https://devfeed.tech/tags/design-system.md>), [figma](<https://devfeed.tech/tags/figma.md>), [figma-agent](<https://devfeed.tech/tags/figma-agent.md>), [guidelines](<https://devfeed.tech/tags/guidelines.md>), [how-to](<https://devfeed.tech/tags/how-to.md>)

### AI overview

The Figma agent can use a published design library to select approved components and tokens; meaningful names, variants, properties, variables, and reusable patterns help it identify how assets should be used. Attach library guidelines for standing rules, exceptions, and component choices; they apply automatically when a library is enabled, though the article says their use in edits to existing designs is still being improved. Provide examples for reusable patterns by publishing designs on an `Examples` page or naming them with `_example` (both conventions are case-sensitive); attach task-specific references directly to a prompt. Skills can encode repeatable processes such as design system audits. Review the agent's output, correct issues on the canvas, and improve the library, guidelines, or examples if mistakes recur.

### Source excerpt

Your design system can help the Figma agent understand the principles and guidelines that define your product. Here's how to make that context useful to the agent.

## 3 ways product designers use the Figma agent for craft, speed, and creative expression

DevFeed: [3 ways product designers use the Figma agent for craft, speed, and creative expression](<https://devfeed.tech/articles/3-ways-product-designers-use-the-figma-agent-for-craft-speed-and-creative-expression-65614.md>)

Original publisher: [Read original article](<https://www.figma.com/blog/3-ways-product-designers-use-the-figma-agent/>)

Author: Jenny Xie

Published: 2026-10-06T14:00:00Z

Content type: article

Language: en

Sources: [Figma Blog](<https://devfeed.tech/sources/figma-blog.md>)

Topics: [Figma agent](<https://devfeed.tech/topics/figma-agent.md>), [Figma](<https://devfeed.tech/topics/figma.md>), [User interface design](<https://devfeed.tech/topics/ui-design.md>), [Documentation](<https://devfeed.tech/topics/documentation.md>), [Figma AI](<https://devfeed.tech/topics/figma-ai.md>), [generative plugins](<https://devfeed.tech/topics/generative-plugins.md>)

Tags: [agent](<https://devfeed.tech/tags/agent.md>), [culture](<https://devfeed.tech/tags/culture.md>), [designers](<https://devfeed.tech/tags/designers.md>), [figma](<https://devfeed.tech/tags/figma.md>), [figma-agent](<https://devfeed.tech/tags/figma-agent.md>), [product](<https://devfeed.tech/tags/product.md>), [speed](<https://devfeed.tech/tags/speed.md>)

### AI overview

The article describes how product design teams at Uber, Granola, and Atlassian use the Figma agent to document design systems, iterate on designs, incorporate feedback, and create reusable motion assets. It says the agent is generally available and reports that Uber's documentation workflow reduced work that previously took multiple people months to a single designer's afternoon.

### Source excerpt

Here's how teams at Uber, Granola, and Atlassian support high-quality, fast-moving work with the Figma agent, now generally available.

## Figma agent vs. one button: shipping design tokens to npm

DevFeed: [Figma agent vs. one button: shipping design tokens to npm](<https://devfeed.tech/articles/figma-agent-vs-one-button-shipping-design-tokens-to-npm-51303.md>)

Original publisher: [Read original article](<https://blog.gitbutler.com/design-tokens-ai-agent-vs-button>)

Author: noreply@gitbutler.com (Pavel Laptev)

Published: 2026-09-07T10:00:00Z

Content type: opinion

Language: en

Sources: [Butler's Log](<https://devfeed.tech/sources/butler-s-log.md>)

Topics: [Design system](<https://devfeed.tech/topics/design-system.md>), [Figma](<https://devfeed.tech/topics/figma.md>), [Figma agent](<https://devfeed.tech/topics/figma-agent.md>), [Artificial Intelligence](<https://devfeed.tech/topics/ai.md>), [npm](<https://devfeed.tech/topics/npm.md>)

Tags: [agents](<https://devfeed.tech/tags/agents.md>), [ai](<https://devfeed.tech/tags/ai.md>), [ai-agents](<https://devfeed.tech/tags/ai-agents.md>), [ai-coding](<https://devfeed.tech/tags/ai-coding.md>), [claude](<https://devfeed.tech/tags/claude.md>), [design](<https://devfeed.tech/tags/design.md>), [design-tokens](<https://devfeed.tech/tags/design-tokens.md>), [design-tokens-figma-agents-ai-coding-github-actions](<https://devfeed.tech/tags/design-tokens-figma-agents-ai-coding-github-actions.md>), [developer-tools](<https://devfeed.tech/tags/developer-tools.md>), [figma](<https://devfeed.tech/tags/figma.md>), [figma-agent](<https://devfeed.tech/tags/figma-agent.md>), [git](<https://devfeed.tech/tags/git.md>), [gitbutler](<https://devfeed.tech/tags/gitbutler.md>), [github-actions](<https://devfeed.tech/tags/github-actions.md>), [npm](<https://devfeed.tech/tags/npm.md>), [programming](<https://devfeed.tech/tags/programming.md>), [software-development](<https://devfeed.tech/tags/software-development.md>), [technology](<https://devfeed.tech/tags/technology.md>), [version-control](<https://devfeed.tech/tags/version-control.md>)

### AI overview

A first-person account of automating a design-token release pipeline with Claude Code and the Figma agent. The author finds that a simple existing plugin button is faster than the multi-step AI-assisted workflow.

### Source excerpt

I automated our design tokens release with two AI agents. It took six minutes per run. A button my plugin has had for years takes seconds.

## 10 Figma agent skills featured by Figma

DevFeed: [10 Figma agent skills featured by Figma](<https://devfeed.tech/articles/try-these-10-skills-and-show-off-your-own-10171.md>)

Original publisher: [Read original article](<https://www.figma.com/blog/try-these-10-skills-and-show-off-your-own/>)

Author: Miggi Cardona

Published: 2026-08-13T16:00:00Z

Content type: article

Language: en

Sources: [Figma Blog](<https://devfeed.tech/sources/figma-blog.md>)

Topics: [Figma](<https://devfeed.tech/topics/figma.md>), [Figma agent](<https://devfeed.tech/topics/figma-agent.md>), [Design system](<https://devfeed.tech/topics/design-system.md>), [recommendation systems](<https://devfeed.tech/topics/recommendation-systems.md>)

Tags: [design-system](<https://devfeed.tech/tags/design-system.md>), [figma](<https://devfeed.tech/tags/figma.md>), [figma-agent](<https://devfeed.tech/tags/figma-agent.md>), [figma-community](<https://devfeed.tech/tags/figma-community.md>), [recommendations](<https://devfeed.tech/tags/recommendations.md>)

### AI overview

Figma explains how users can author skills for its agent directly in Figma, preview and edit them, and iterate on them through testing. The article highlights 10 skills from the Figma Community, including examples for generating radiographs and reviewing animation opportunities.

### Source excerpt

Now you can author skills for our agent, directly in Figma, to put your point of view to work. Here are 10 of our favorites to get you started.

## Code on the Figma canvas

DevFeed: [Code on the Figma canvas](<https://devfeed.tech/articles/code-on-the-figma-canvas-9569.md>)

Original publisher: [Read original article](<https://www.figma.com/blog/code-on-the-figma-canvas/>)

Author: Nikolas Klein

Published: 2026-06-24T14:30:00Z

Content type: release

Language: en

Sources: [Figma Blog](<https://devfeed.tech/sources/figma-blog.md>)

Topics: [Figma](<https://devfeed.tech/topics/figma.md>), [Code](<https://devfeed.tech/topics/code.md>), [GitHub](<https://devfeed.tech/topics/github.md>), [Figma agent](<https://devfeed.tech/topics/figma-agent.md>)

Tags: [agent](<https://devfeed.tech/tags/agent.md>), [code](<https://devfeed.tech/tags/code.md>), [figma](<https://devfeed.tech/tags/figma.md>), [github](<https://devfeed.tech/tags/github.md>), [update](<https://devfeed.tech/tags/update.md>)

### AI overview

Figma introduces code layers in Figma Design, allowing teams to create, import, edit, compare, and refine interactive code directly on the Figma canvas. Code layers can be generated with the Figma agent or Make, connected to GitHub repositories or local folders, converted into editable Figma layers, and pushed back to a repository. The feature is rolling out in closed beta, with early access available by request.

### Source excerpt

With code layers in Figma Design, you can explore multiple directions with code, side by side with your team.

## Introducing Figma Motion: Your canvas now has a timeline

DevFeed: [Introducing Figma Motion: Your canvas now has a timeline](<https://devfeed.tech/articles/introducing-figma-motion-your-canvas-now-has-a-timeline-9894.md>)

Original publisher: [Read original article](<https://www.figma.com/blog/introducing-figma-motion/>)

Author: David Hornsby

Published: 2026-06-24T13:30:00Z

Content type: release

Language: en

Sources: [Figma Blog](<https://devfeed.tech/sources/figma-blog.md>)

Topics: [Figma](<https://devfeed.tech/topics/figma.md>), [Figma agent](<https://devfeed.tech/topics/figma-agent.md>)

Tags: [animation](<https://devfeed.tech/tags/animation.md>), [design](<https://devfeed.tech/tags/design.md>), [dev](<https://devfeed.tech/tags/dev.md>), [figma](<https://devfeed.tech/tags/figma.md>), [figma-agent](<https://devfeed.tech/tags/figma-agent.md>)

### AI overview

Figma introduces Motion, a timeline-based animation layer built into the same canvas as designs, components, variables, and team collaboration. The release includes timeline controls, keyframing, animation styles, time-based comments, and Figma agent assistance for creating motion.

### Source excerpt

Motion now lives on the canvas--in the same file as your components, your variables, and your team--so your designs can come to life from day one.

## 4 ways we're using our MCP server at Figma

DevFeed: [4 ways we're using our MCP server at Figma](<https://devfeed.tech/articles/4-ways-we-re-using-our-mcp-server-at-figma-9467.md>)

Original publisher: [Read original article](<https://www.figma.com/blog/4-ways-were-using-our-mcp-server-at-figma/>)

Author: Mari Kong

Published: 2026-06-16T12:00:00Z

Content type: article

Language: en

Sources: [Figma Blog](<https://devfeed.tech/sources/figma-blog.md>)

Topics: [Figma](<https://devfeed.tech/topics/figma.md>), [Model Context Protocol](<https://devfeed.tech/topics/model-context-protocol.md>), [Figma agent](<https://devfeed.tech/topics/figma-agent.md>), [software-development](<https://devfeed.tech/topics/software-development.md>)

Tags: [agents](<https://devfeed.tech/tags/agents.md>), [design-system](<https://devfeed.tech/tags/design-system.md>), [development](<https://devfeed.tech/tags/development.md>), [figma](<https://devfeed.tech/tags/figma.md>), [figma-agent](<https://devfeed.tech/tags/figma-agent.md>), [mcp](<https://devfeed.tech/tags/mcp.md>), [mcp-server](<https://devfeed.tech/tags/mcp-server.md>), [workflows](<https://devfeed.tech/tags/workflows.md>)

### AI overview

Figma describes four ways its MCP server and related agent capabilities are being used across product development workflows, including updating living decks, creating designs on the Figma canvas, and connecting design decisions with code.

### Source excerpt

The Figma MCP server reaches further across the platform than it ever has. From updating a living deck to shipping a design to production--here's what that looks like in practice.

## The Figma design agent is here

DevFeed: [The Figma design agent is here](<https://devfeed.tech/articles/the-figma-design-agent-is-here-10106.md>)

Original publisher: [Read original article](<https://www.figma.com/blog/the-figma-agent-is-here/>)

Author: Rodrigo Davies; Tammy Taabassum

Published: 2026-05-20T12:00:00Z

Content type: release

Language: en

Sources: [Figma Blog](<https://devfeed.tech/sources/figma-blog.md>)

Topics: [Figma](<https://devfeed.tech/topics/figma.md>), [Figma agent](<https://devfeed.tech/topics/figma-agent.md>), [Artificial Intelligence](<https://devfeed.tech/topics/ai.md>), [Design system](<https://devfeed.tech/topics/design-system.md>), [Model Context Protocol](<https://devfeed.tech/topics/model-context-protocol.md>), [Code](<https://devfeed.tech/topics/code.md>)

Tags: [agentic](<https://devfeed.tech/tags/agentic.md>), [agentic-workflows](<https://devfeed.tech/tags/agentic-workflows.md>), [ai](<https://devfeed.tech/tags/ai.md>), [design-system](<https://devfeed.tech/tags/design-system.md>), [figma](<https://devfeed.tech/tags/figma.md>), [figma-agent](<https://devfeed.tech/tags/figma-agent.md>), [mcp](<https://devfeed.tech/tags/mcp.md>), [tokens](<https://devfeed.tech/tags/tokens.md>), [tools](<https://devfeed.tech/tags/tools.md>), [workflow](<https://devfeed.tech/tags/workflow.md>), [workflows](<https://devfeed.tech/tags/workflows.md>)

### AI overview

Figma announces a purpose-built Figma agent that works directly on the canvas and in the left rail. The agent uses context about components, tokens, standards, and best practices to help teams explore ideas, edit files, and iterate within shared design workflows.

### Source excerpt

Starting today, work with an agent that is built for Figma--directly on the canvas.