Jacob Miller left the PM role at Figma to build Diffui, a new way to approach the design to dev process with AI. In this thread, he compares designs generated by his tool and Claude Design. One is more expressive and diverse, another is more polished and organized. The point is not that one is better than another, but how can we combine different approaches and tools to get to the most interesting result.

Paul Stamatiou with the first impression most experienced designers will relate to: Claude Design didn’t land on first try, but the trajectory outlined by Sam Henri Gold is unmistakable. Lately, I’ve been working in pretty much the same way: ​“So much of my iteration happens directly in the code, Figma is where the direction gets sorted out, then it gets a million iterations and refinements in code. The last thing a designer on a team moving at hyperspeed wants to do is backport designs in code back to Figma to maintain a single source of truth.”

Anthropic launches Claude Design, a new product that lets you collaborate with Claude to create designs, prototypes, slides, and more. Powered by Claude Opus 4.7, it reads your codebase and design files during onboarding to build your team’s design system automatically, then applies it to every project. This release kicked off many interesting conversations in the community, some of which I gathered below.

Rasmus Andersson, creator of Inter and former principal designer at Figma, draws the sharpest distinction in the launch coverage: ​“This is really neat but it’s not a design tool as much as it’s a design production tool. The practice of design is mostly about what comes before production.”

Karri Saarinen, CEO of Linear, makes a similar point that AI design tools conflate producing interfaces with designing them, leaning on Christopher Alexander’s ​“Notes on the Synthesis of Form” to make the case that real design is the search for fit between form and context, not the generation of form itself. He points to a visible symptom: AI-assisted products that look polished but unravel under use, full of decisions that were never genuinely worked through.

Figma and Anthropic demonstrate the Claude Code roundtrip in both directions. Write to Canvas lets Claude Code create and modify designs directly in Figma; Code to Canvas brings live browser UI back in as editable frames. Worth watching alongside the Agents on Canvas blog post and Figma Skills page for the full picture of what this workflow ecosystem looks like.

Ed Bayes leads design on Codex at OpenAI; Gui Seiz leads AI product design at Figma. Together with Aakash Gupta, they give a rare behind-the-scenes look at what the Codex-to-Figma MCP integration actually changed inside their teams. The workflow is genuinely bidirectional, code and canvas reading from each other directly. The most concrete signal that something shifted: designers are working directly in staging.

Brad Frost and Chromatic cofounder Dominic Nguyen walk through how Storybook’s new MCP exposes design systems for agents to use reliably. The key insight: AI doesn’t invent states your components don’t have — it amplifies what’s documented. Coverage, completeness, and constraints are now load-bearing.

Steve Schoger from Tailwind Labs recorded a step-by-step walkthrough on taking an AI-designed dashboard and turning it into something that looks like it was designed by a pro.

Jenny Wen, who brought FigJam from concept to launch at Figma and is now design lead at Anthropic, talks at the Double Diamond podcast about designing Claude itself. The key difference from traditional software: ​“When you are designing now with these LLMs, you basically can’t map out all those flows. You basically just have these core primitives and these specific states that you want the model to get to, but the possibilities in which the user can actually interact with the model are just basically endless.”

Luis on what the ​“shadcn-ification” debate is actually about — not the visual uniformity, but the organizational misread: ​“The mistake isn’t in the ingredient. It’s in thinking that having access to good ingredients is the same as knowing how to cook.”

Stakeholders are concluding that the design system infrastructure is done because a great foundation exists. The teams that have spent years practicing design systems understand exactly why that conclusion is dangerous.

TK Kong shares a detailed guide to his workflow with Claude Code and Paper, the design tool built on native HTML/CSS rather than a WebGL canvas. The workflow of agent writing HTML into Paper frames, designer editing on canvas, and agent implementing code is similar to the Figma MCP workflow covered above, but also allows working with existing designs.

The Paper Snapshot Chrome plugin — which copies live web UIs directly into Paper as editable layers — is exactly what I wanted while wondering why Figma won’t make ​“a universal ​“Send to Figma” browser extension”.

The Claude Code version of Figma’s ​“Code to Canvas” tutorial. Clear and short, covers the same workflow as the above.

Figma’s official walkthrough for the Codex-to-canvas workflow: pull coded designs into Figma as editable frames, iterate on the canvas, push changes back to code.

Gui Seiz and Alex Kern from Figma walk through the exact workflow they use to keep design and code in continuous sync using Figma’s MCP, Claude Code, and Codex. Their demo shows the full round-trip: pull a running web app into Figma as editable frames, make design changes on the canvas, push them back to code via Claude Code. If you’d rather read than watch the full video, the newsletter summary of this How I AI episode captures the key takeaways.

Steve Schoger is a design cofounder of Tailwind CSS and a recent Claude Code convert. In this walkthrough, he is using Claude Code as his main design tool to turn a generic AI-generated marketing page into a polished Tailwind UI, with lots of concrete tweaks to typography, spacing, borders, and layout.

Yarden Katz, Product Manager at Figma, walks through the bidirectional workflow between Codex and Figma’s MCP server. The design-to-code direction is the expected one — copy a Figma frame link, paste it into Codex, and the get_​design_​context tool extracts layouts, styles, and components to implement against. The more interesting direction is code-to-canvas: Codex can capture a live running UI and push it back into Figma as editable frames, letting the design side iterate before syncing changes back to code.

Martin Rariga, Founding Product Designer at Equals, breaks down a practical AI-powered design engineering stack: Claude Code for big refactors and complex builds, Cursor for precise edits, and Figma (via MCP) to reference the new design direction while restyling.

An hour-long firsthand account from a Shopify designer on integrating Claude Code into his day-to-day workflow. Product design at that scale means navigating design systems, production codebases, and cross-functional handoffs, which is a more realistic stress test for agentic coding tools than a clean demo. The shift from ​“designer who writes prompts” to ​“designer who ships code” is happening faster than most predicted.

In this interview, Jay chats with Elad Mizrahi, who is building a working Figma widget in under an hour with Cursor AI. The appeal for designers is obvious: widgets are notoriously finicky to set up from scratch, and using an AI coding agent to handle the boilerplate means you can stay focused on the logic and behavior rather than the scaffolding.