yancymin

building @artifigAI
maker of @wegic_ai, @Ugic_Ai, | Product Designer, Design Engineer

[yancymin @yancymin]

The future that is happening.

Automation powered by GPT-4o generates Figma designs based on PRD.

@figma

[yancymin @yancymin]

@joshpuckett this is awesome! i'm actually building something very similar
https://t.co/m677w6juNb

[yancymin @yancymin]

messing around with the local font access api recently. built a little tool to manage local fonts and added an llm for recommendations. it’s mostly just an excuse for me to learn more about typography.

will open source it soon. here is a quick look at how it works.

[yancymin @yancymin]

just integrated this mcp into my demo, works really well

[yancymin @yancymin]

@bbssppllvv wow, i’m impressed by how fast the demo responds. super smooth experience. brilliant idea too
https://t.co/QQByrrUoAB

[yancymin @yancymin]

@bbssppllvv wow, i’m impressed by how fast the demo responds. super smooth experience. brilliant idea too
https://t.co/QQByrrUoAB

[Dominik Kandravy @heyiamdk]

What if macOS Stage Manager, Spaces, CMD+Tab, and the Dock were one unified system?

Early prototype using @createwithplay

[yancymin @yancymin]

@chmielwork shipping soon

[yancymin @yancymin]

messing around with the local font access api recently. built a little tool to manage local fonts and added an llm for recommendations. it’s mostly just an excuse for me to learn more about typography.

will open source it soon. here is a quick look at how it works.

[yancymin @yancymin]

a significant milestone in the evolution of design tools

[Cursor @cursor_ai]

You can now design directly in your codebase.

Select elements, modify them visually, and Cursor writes the code.

[yancymin @yancymin]

speechless 🫡

generated a brand style guide pdf in just a few minutes. what's impressive is that the pdf is high-res, and the content is flawless.

[NotebookLM @NotebookLM]

Next up… Slide Decks!

Turn your sources into a detailed deck for reading OR a set of presentation-ready slides. They are fully customizable, so you can tailor them to any audience, level, and style.

Officially rolling out to Pro users now (free users in the coming weeks)!

[yancymin @yancymin]

my dream came true...

[Duy Tran @khanhduytran0]

@LAFadhel Apparently someone did have it working

[yancymin @yancymin]

totally agree. though i’d argue that while simple prompts now yield results far beyond previous LLMs, achieving truly professional-grade quality still requires professional-level descriptions.

for example: "Use GSAP Pinning to lock the screen. As the user scrolls, a 3D soda can rotates, translates, and tilts in the center, showcasing different parts (lid, body, texture) in three phases.
dynamic reference lines: coordinated with CSS animations, lines extend from labels to specific parts of the 3D can."

btw, i think it’ll be a total game-changer once this can be integrated with MCPs from component communities.

i actually dropped "https://t.co/FcdKCTe75R" into a prompt yesterday. even though gemini didn't explicitly browse or retrieve from the link, i suspect it was part of its training data—the final result featured several components that looked identical to ones from https://t.co/yIZRuk42Pw

[issui.txt @issui_ikeda]

gemini-3.0 pro、デザイン文脈だとかなり革命起こしてて衝撃過ぎる。
ほぼポン出しで超ハイクオリティなサイト出てきた。
正直この水準で納品されたらかなりちゃんとしたデザイナーだと思える（AIだと思えない）

[yancymin @yancymin]

elegant 🥲

got gemini 3 to code a webpage generator.
https://t.co/LM5S3qi2J3

[yancymin @yancymin]

curious if the agent has keyboard capabilities yet — Figma really depends on shortcut combos. @bengoodger @chatgpt

[yancymin @yancymin]

not much progress yet. 🤔testing ChatGPT Atlas controlling Figma

⏩4x

[yancymin @yancymin]

gave Claude's computer use full control of Figma AI today. already working but still slow and limited. imagine this in 6 months with 10x speed and precise mouse control - AI orchestrating AI design at human pace...

[yancymin @yancymin]

@ciguleva

[yancymin @yancymin]

@ciguleva Perhaps you should generate it using a text-to-image model and then convert it to vector SVG.

[yancymin @yancymin]

llm input boxes are blank canvases: max possibility, max friction. users don’t need smarter models—they need smarter starting points

[yancymin @yancymin]

@JamesNguyen868 awesome! do you mean the Artifig plugin?

[artifig @artifigAI]

🪄 Shipped Version 75 for Artifig

Two creation modes are now live:
🎛️Generate Plugin—turn plain words into working Figma plugins;
📱Generate UI—instantly create interactive prototypes from prompts or design drafts.

Switch on the fly and validate ideas in minutes!

[artifig @artifigAI]

Thanks for including Artifig!
Want to turn your ideas into a real Figma plugin—no code needed?

👇Try Artifig: https://t.co/P8KbdxMCjJ