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.”

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.

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.

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

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”.

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.

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.

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.

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.

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.

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.

“Join Figma designer advocate, Ana Boyer and OpenAI product designer, Ed Bayes as they talk through roundtripping between code and canvas.”

Figma explains how its new MCP server lets Codex generate Figma Design files from live code and, in the other direction, use Figma frames as structured context for agentic code generation.

Ridd walks through a workflow where Paper acts as a visual canvas that Claude can ​“proactively” explore and prototype in. The interesting bit is his framing of Claude Code as a coworker and Paper as a shared whiteboard. That’s exactly what I wanted when last week I commented on missing agents in Figma after spending more time in Cursor.

Jenny Wen leads design for Claude at Anthropic, and in the past, she was Director of Design at Figma, where she led the teams behind FigJam and Slides. At Lenny’s podcast, she lays out how AI is collapsing the classic ​“research → mock → iterate” workflow into two main jobs for designers: supporting rapid implementation alongside engineers, and setting shorter 3–6 month product visions that keep a swarm of agents and builders pointed in a coherent direction. Jenny describes the day-to-day at Anthropic as equal parts surfing internal prototypes, pairing with engineers, and doing last-mile implementation herself. She still sees Figma as critical for exploring many directions and fine visual decisions, but treats Claude as her primary stack for long-running tasks and front-end polish.

“Bringing Claude Code workflows directly into Figma lets developers, designers, and even hobbyists capture a real, functioning UI from a browser — in production, staging, or localhost — and convert it into editable frames on the Figma canvas. Code is powerful for converging — running a build, clicking a path, and arriving at one state at a time. The canvas is powerful for diverging — laying out the full experience, seeing the branches, and shaping direction collectively. Going from code to canvas helps teams move fluidly, so work can narrow when it needs to and open up when it’s time to collaborate.”

My guess is it’s based on the html.to.design technology that Figma acquired last year, which is a huge time saver and an essential part of my toolkit. I haven’t tested Claude Code to Figma yet, but the result in demos looks very similar to what I usually get from the plugin. Which makes me wonder why they limited it to Claude Code instead of making something like a universal ​“Send to Figma” browser extension?

“Ryo Lu pioneered new patterns for collaboration as founding designer at Notion. He now leads design at Cursor, shaping how software gets built through a fusion of design and engineering. In this conversation with Soleio, he explains Cursor’s approach to design and how the product will evolve to empower designers who build.”

Meng To shares a concrete end-to-end workflow where OpenClaw runs as a local ​“agency layer” that talks to files, shell, browser, and Telegram, while Codex acts as the focused coding specialist for real repos and multi-task queues. He replaced tools like Notion, Midjourney, Cursor, and v0 with local Markdown files, Nano Banana Pro API, and four specialized Telegram bots to compress a 3‑month and 5–10 person product cycle into about a week while working solo. This setup is powerful but requires non-trivial security setup, careful prompt and reference management, and still leans heavily on code review and system hygiene rather than ​“hands‑off” autonomy.

Theo shares a 22-minute demo of OpenAI’s new Codex desktop app, pitching it as a ​“Cursor killer” after using it for a week of real work.

Ed Bayes from Open AI shared a 2 minute demo of using the Codex desktop app’s Figma skill to turn designs into front-end code with 1:1 visual parity, including all CSS classes and styling.