Anthropic’s playbook for Opus 5.5 is mostly about longer runs: name the finish line, delete ​“think carefully” lines, and let it work. For designers, the section to bookmark is the one on design direction: ​“With no design direction, Opus 5.5 falls back on a few default styles. A general instruction like ​“avoid a generic look” mostly swaps one default for another. A list of specific patterns works much better.” Anthropic’s own example ban list reads like a catalog of today’s AI aesthetic: cream or off-white backgrounds, italic accent words in headings, numbered ​“01 / 02 / 03” section labels, monospace labels, and pill-shaped buttons. Worth copying into your prompts whatever model you use.

Soleio interviews Joel Lewenstein, Head of Design at Anthropic. Their roadmap comes from internal traction on half-baked vibe-coded prototypes rather than top-down planning, and new designers figure that out by pattern matching on who gets respect. Claude Design is a wrapper over Claude Code with a friendlier front end, and his own designers keep going back to the terminal, because the production codebase is the source of truth for the design system and the rules of how things work while Claude Design has to rummage through Google docs that aren’t.

Everything above is agents arriving in Figma, but this one runs the other way. Nate Parrott, the Anthropic designer behind Claude Design, put its artboard canvas inside Claude Code, so options get drawn where the code already lives. One brief, several editable artboards, and then Claude implements the one you pick. /design-sync can load your design system from a repo or your local codebase first. 

Meaghan Choi, lead designer on Claude Code, walks through her actual daily setup at a Dive Club talk in NYC: always in a worktree so parallel Claudes don’t overwrite each other, always in auto mode so the classifier handles permission prompts, and a custom /prototype skill that spins up five HTML variants of any feature and picks one with reasoning before she even looks. She demos it by asking Claude to add autocomplete to Excalidraw with no design spec, then has it open a PR with a screenshot recorded via Claude in Chrome. Her line that lands: she doesn’t review Claude’s terminal output anymore, she reviews the PR.

Kris Puckett, Design Manager at Stripe, spent months building Epilogue, a real iOS app with 14,000 lines of Swift, entirely through conversation with Claude. This essay is a specific and honest account of what the designer-building-with-AI experience actually looks like: what broke, what he learned about asking precise questions, what ​“vague frustration keeps you stuck, specific confusion gets you answers” actually looks like in practice. ​“I realized the bottleneck was never coding ability. It was articulation. The ability to describe what I wanted clearly enough that something else could build it.”

“Designers have always (and will always) answer the question ​‘What’s worth making?’ ” Joel Lewenstein, Head of Design at Anthropic, argues that as the cost of software drops, the most important decisions shift from ​“can we make this?” to ​“should we?” Design, in his framing, is what narrows the possibility space fast enough to keep up with the speed of delivery. He describes Claude Design as a tool for getting ideas ​“good enough to move discussion forward,” cutting idea-to-internal-feedback time from days to hours.

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.”

Sam Henri Gold argues that Figma’s decade of components, variables, and tokens has become an overgrown, pre‑agentic system that no one would design from scratch now that LLMs work directly with code. He frames Claude Design as ​“truth to materials”: HTML/JS-first, tightly coupled to Claude Code, and better aligned with a future where the source of truth moves back into repositories instead of opaque design files. The interesting provocation is his prediction that tooling will split in two—agentic, code-native tools like Claude Design on one side and pure, system-free exploration playgrounds on the other—leaving Figma facing its own ​“Sketch moment” unless it radically rethinks what it’s for.

Ben Blumenrose offers a useful counterpoint to the critical takes: ​“What if it’s not a Claude Design vs. Canva vs. Figma vs. xxx but a ​‘yes and’ as millions more people are exposed to design and use this accessible tool to begin a journey into being better at type, color, composition, effective communication, building great experiences, etc?”

Soleio (designer, angel investor) draws a three-way taxonomy to cut through the noise: production design gets automated on economic grounds; strategic design expands its medium set to include live production experiments iterated by agents; and exploratory design actually grows in importance because humans and machines together can traverse a far larger combinatorial space of novel forms. The real competitive edge, he argues, shifts to ​“problem-finders” who build new systems for channeling desire: ​“The inputs and systems we create to find opportunities will reward the most intrepid problem-finders. Design stops being a method of sitting and ruminating on possible forms or solution spaces. Design becomes active, research-based, and built around speed of discovery and expression.”

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.

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.”

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.

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.

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.

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.

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

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.