https://www.figma.com/blog/the-figma-agent-is-here/

Looks pretty good, anyone use it yet?

---

Claude summary:

Figma's design agent launched today — it lives directly on the canvas and in the left rail, no separate setup required.

It's design-system-aware — the agent has deep context on your components, tokens, variables, and standards, unlike third-party tools that lack that native access.

Key canvas interactions: start a prompt from any design layer, run parallel prompts to explore multiple ideas simultaneously, and make manual edits while the agent iterates alongside you.

Explore directions faster — generate multiple stylistic approaches or information architectures at once; steer outputs by `@`-mentioning specific tokens, variables, or components.

Automate bulk busywork — rename variables, swap components across screens, repeat padding changes across flows, populate frames with realistic content, convert screens to dark mode.

Design system maintenance — bulk-update descriptions, tags, naming conventions, and auto-document components with all their states and variants.

Works with feedback — summarize comments, identify themes, model stakeholder perspectives, distill long comment threads into action plans.

MCP server relationship: the agent is for canvas work; the MCP server + `use_figma` is for moving work between code and Figma.

Currently in beta rollout — no credits consumed during beta; AI credits apply at GA. Available for Full seat users on Professional, Organization, and Enterprise plans.

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

From exploring new directions to making bulk edits and implementing feedback, here's how Figma's agent will fit into your design workflow today.

I used to spend hours on briefs, planning, and file setup before designing.

Now, my AI-powered design workflow takes me from idea to design in 4 steps:

Step 1: Voice → Structured brief

I do a 2-3 min voice brain dump using Whisper Flow. It captures everything and sends it to Notion. No typing, no formatting. Just talk and it's documented.

Step 2: Brief → Tasks → Daily focus

Notion AI then breaks the brief into tasks and keeps everything in one dashboard: tasks, notes, docs, links and even daily todos. No app switching, no scattered files. Stays focused without oversight.

Step 3: Layout → Final design

Figma Make generates initial layouts quickly. I pull in styling from my library so everything stays on-brand. Then I continue polishing it in Figma: typography, spacing, alignment and all the details that make it feel polished.

Step 4: Design → Critique

Before calling it done, I screenshot and drop it into Claude. It analyzes layout pros and cons, identifies ambiguous language, and reduces wordiness so the message is sharp.

This is how I use AI to work smarter and faster while keeping creative decisions in human hands.

What does your AI workflow look like? I'd love to hear what's working for you 👇

Everyone is talking about AI replacing designers. I think we need to have an honest conversation.

I am not anti-AI. In fact, I think tools like Claude and MCP services have genuinely changed how designers work, automating repetitive tasks, speeding up component generation, and helping early-stage teams move faster. That's real value, and I won't dismiss it.

But let's stop pretending there are no trade-offs.


a𝗧𝗵𝗲 𝗰𝗼𝘀𝘁 𝗿𝗲𝗮𝗹𝗶𝘁𝘆 nobody talks about
Every serious AI workflow runs on credits. Token costs add up fast, especially when you're iterating, generating variants, or running MCP pipelines at scale. Anyone telling you AI is free either hasn't used it extensively or doesn't understand how the credit system works.


𝗔𝗜 𝗻𝗲𝗲𝗱𝘀 𝘆𝗼𝘂𝗿 𝗱𝗲𝘀𝗶𝗴𝗻 𝘀𝘆𝘀𝘁𝗲𝗺 𝘁𝗼 𝗯𝗲 𝘂𝘀𝗲𝗳𝘂𝗹
AI doesn't generate consistency on its own. To get reliable, on-brand output you need to feed it your design tokens, component logic, and spacing rules first. Ironically, you need a designer to build the foundation that makes AI useful for design. For early-stage products, this workflow can be powerful. For large, distributed teams with an established brand identity, the gaps become harder to ignore.


𝗧𝗵𝗲 𝗰𝗿𝗲𝗮𝘁𝗶𝘃𝗶𝘁𝘆 𝗰𝗲𝗶𝗹𝗶𝗻𝗴 𝗶𝘀 𝗿𝗲𝗮𝗹
AI learns from what exists on the web. It recombines, it optimises, it executes, but it doesn't invent. If you want your product to look like every other modern SaaS tool in the market, AI will serve you well. But if differentiated visual identity and brand depth matter to you, AI output will feel generic without significant human direction.

Image and video generation? Impressive. Building a product that feels genuinely personalised and distinct? We are still far from that.


𝗧𝗵𝗲 𝗯𝗼𝘁𝘁𝗼𝗺 𝗹𝗶𝗻𝗲
AI is a powerful tool in the right hands. The designer who understands how to direct it will always outperform the one who blindly follows the hype — or the one who refuses to engage with it at all.

The future isn't AI replacing designers. It's designers who understand AI, replacing those who don't.

What's your experience been working with AI in your design workflow?

Let’s be honest... the sheer volume of noise surrounding Artificial Intelligence right now is exhausting and all over the place. Every tool has a “generate” button, and social media (LinkedIn especially) is full of people proclaiming the end of traditional design jobs.

As a product designer, I initially approached this wave with skepticism. I enjoy designing. I like solving complex problems. I was not looking for a machine to do my job for me.

However, almost two years has passed since those early iterations and ignoring AI is no longer an option. Instead of viewing it as a replacement, I have spent my recent time treating AI as a very fast and somewhat literal-minded supporter. The goal is not to let it design the final product. The goal is to clear the path so I have more time for actual critical thinking.

Here is a look at how I have started integrating these tools into my daily workflow:

Dear junior designers: AI is not your competition.

I’ve been thinking about this a lot lately. There are so many conversations about what AI means for early-career designers. I understand the anxiety. Big shifts in our craft can feel unsettling.

I use AI every day now and hasn’t made me feel replaceable. If anything, it's made me more focused. And it can be that for you too.

On a recent project, instead of spending hours manually exploring layout variations or refining early drafts, I used AI to prototype and build interactions in real time which gave me more space to focus on what actually moves the work forward:
• Direction
• Systems thinking
• Clarity
• Storytelling

AI felt like an assistant not the designer.

And here’s what I want you to hear:
Your value was never just in knowing the tools. Tools will continue to evolve. They always have.

What matters is how you think. How you see. How you care about the people on the other side of the screen.

This moment might actually give you an advantage, instead of spending years only executing, you can:
• Explore more ideas, faster
• Participate in strategic conversations earlier
• Develop judgment through iteration
• Build a stronger point of view

That’s growth.

Yes, this is a new chapter for design. It can feel uncomfortable.
But evolution in our craft is not a signal to step back. It is an invitation to step up.

If you are graduating or still building your foundation, keep going.
Stay curious.
Learn the tools.
Ask better questions.
Pay attention to what makes work meaningful.

AI will change workflows.
It will not replace empathy, taste, discernment, or care.

Design has always been about solving real problems for real people.
That hasn’t changed. If anything, you now have more leverage to practice that sooner.

And that is something to feel hopeful about.

Figma AI just went from “cool beta feature” to “everywhere in my workflow.” As a Designer, this changes how we design, review and ship interfaces.

In early 2026, Figma rolled out full AI features to all users. You can now generate layouts from prompts, tweak visuals with AI and even create prototypes without touching a frame first.

Last week I rebuilt part of my UI process around it. Here is what actually worked:

𝟭. 𝗜 𝘀𝘁𝗼𝗽𝗽𝗲𝗱 𝘀𝘁𝗮𝗿𝘁𝗶𝗻𝗴 𝗮𝘁 𝗯𝗹𝗮𝗻𝗸 𝗰𝗮𝗻𝘃𝗮𝘀𝗲𝘀
 • I now start with a prompt like
 • “Create a mobile dashboard for a fintech app with cards for balance, recent transactions and quick actions.”
 • Figma AI gives me 3 to 5 starting points that I refine instead of drawing rectangles for 30 minutes.

𝟮. 𝗜 𝘂𝘀𝗲 𝗔𝗜 𝗳𝗼𝗿 “𝘄𝗵𝗮𝘁 𝗶𝗳” 𝗲𝘅𝗽𝗹𝗼𝗿𝗮𝘁𝗶𝗼𝗻
 • Instead of 10 manual variants, I ask
 • “Try a more minimal style” or “Push this towards a dark, high contrast theme.”
 • It is perfect for exploring extremes while I stay focused on information architecture and flows.

𝟯. 𝗜 𝘁𝗿𝗲𝗮𝘁 𝗔𝗜 𝗮𝘀 𝗮 𝗷𝘂𝗻𝗶𝗼𝗿 𝗱𝗲𝘀𝗶𝗴𝗻𝗲𝗿, 𝗻𝗼𝘁 𝗮 𝘀𝗲𝗻𝗶𝗼𝗿 𝗼𝗻𝗲
 • It is great at speeding up layout, components and visual polish.
 • It is bad at understanding edge cases, accessibility trade offs and product strategy. That is still my job.

𝟰. 𝗖𝗼𝗹𝗹𝗮𝗯𝗼𝗿𝗮𝘁𝗶𝗼𝗻 𝗶𝘀 𝗴𝗲𝘁𝘁𝗶𝗻𝗴 𝗳𝗮𝘀𝘁𝗲𝗿
 • Developers can react to AI generated screens earlier.
 • Stakeholders react better to “something real” instead of low fidelity boxes, which shortens the feedback loop.

𝗧𝗮𝗸𝗲𝗮𝘄𝗮𝘆

AI inside Figma is not replacing my UX work. It is removing the mechanical parts so I can spend more time on research, flows and interaction details.

If you are a UX or product designer
Would you let AI handle your first draft layouts or do you still prefer starting from scratch

Reply with “AI first” or “Manual first” and tell me why.

What if your AI could talk directly to your design tool?

I connected Claude to Figma using MCP, and the results are wild.

In this video, I walk through how I'm using Claude to automate design tasks inside Figma in real time. From creating components to manipulating layers, it's like having a design assistant that actually understands your file.

This isn't about replacing designers. It's about commanding your tools more efficiently.

If you want to know how to set this up yourself, DM me or drop a comment below. Happy to share the workflow.