“AI designs with you, not instead of you.” Figma’s positioning for useFigma, the new write-capable MCP tool that creates real components, variables, and auto layout on the canvas, not flat images or wireframes. The demo runs the full loop: terminal prompt to first draft, manual polish in Figma, annotations the agent later reads as design context, then back to the terminal to update the codebase. The annotations detail is the most interesting part — they double as machine-readable spec.

Figma Make now supports custom skills — markdown files that capture conventions and workflows you use repeatedly, callable from any prompt with a slash command. Pair /build-from-prd with a Notion connector and any PRD becomes a prototype that matches your standards.

Stephen Haney announces QuiverAI’s SVG generation inside Paper – vector output from text or references, aimed at logos, illustrations, and animations. QuiverAI​’s models have been on my radar since Dann Petty joined the team as a Founding Product Designer.

Paul Bakaus has packaged 23 design commands into a single agent skill that teaches Claude Code, Cursor, Codex, and Gemini CLI how to actually design. Type vocabulary, color systems, motion, spatial logic — the foundations most prompts miss. The Live mode that writes accepted variants back to source is where it gets genuinely interesting.

Figma’s first quarter as a public company: $333.4M in revenue, up 46% year-over-year, accelerating from 40% last quarter. Full-year guidance raised. Dylan Field’s framing in the release — ​“when code is a commodity, design is the competitive edge” — is the line the company will be repeating all year.

Designer advocate Amy Lima walks through a full code-to-canvas-to-code round trip on a sample app: install the MCP in Cursor with /add-plugin, authenticate via OAuth, generate a new screen iteration into Figma, refine it by hand, then prompt the agent to update the codebase and open a PR. Pairs well with the useFigma deep dive below.

Jakub Krehel launched Interfaces, a paid magazine for design engineers built around interactive demos and source code, not text. Initial issues cover gestures in motion, gradients, OKLCH, and shared layout animations.

Hannah Hearth runs a tooling Show and Tell with her team at Vercel and writes up the results: Codex + Claude pair programming, Conductor for parallel agent threads, UI Fork for in-browser variant exploration, and Cleanshot’s Pin tool still earning its place.

Owen Williams, design manager at Stripe, walks Claire Vo through Protodash, the internal prototyping platform he’s been building for 18 months. The V1 was a bundle of Cursor rules plus an MCP server wired to Sail, Stripe’s design system, so any designer can open the repo and build a page without ever touching React or routing. V2 wraps the whole thing in a browser UI running on internal dev boxes, with embedded LLM chat, click-to-annotate feedback, a design review mode, and fidelity toggles (monospace, grayscale) to signal work-in-progress. The same pattern as the Notion and Vercel pieces in this section: production design system plus a thin internal harness, calibrated to one team’s review culture in a way no off-the-shelf tool can be.

Brian Lovin shows the Notion design team’s Prototype Playground, a single Next.js repo on Vercel where every designer gets a namespaced folder and a small set of shared Notion-flavored components. The interesting parts are not the scaffolding but the slash commands and skills layered on top: /figma runs a three-phase loop with the Figma MCP and Chrome DevTools MCP until the build matches the source (~80% on the first try), and a find-icon skill writes its own TypeScript search script after the team got tired of Claude hallucinating ​“search-icon.” See also the Stripe and Vercel pieces below for the same pattern at other companies, as well as another interview with Brian at Dive Club.

A useful baseline study on how people actually use AI well. The most uncomfortable finding for designers: in conversations that produce artifacts (code, UI, documents), users are less likely to question the model’s reasoning. Polished output suppresses critical evaluation, even though that’s exactly when it’s most needed.

Luis Ouriach makes the case against single-number design system adoption metrics. His argument: one number collapses three things that should stay separate, across artifacts (a brand token and a complex data table component need different definitions of ​“used well”), surfaces (a logged-in dashboard component has no business on a sign-up screen), and people (a marketer, a senior product designer, and a front-end engineer all want different things from the same system). The throughline is that compliance with a benchmark is not the same as value, and most design system dashboards are quietly measuring the wrong one.

The May edition is mostly a demo of Figma’s MCP server, with Amy Lima and Anthony DiSpezio walking through three workflows: code-to-canvas import of a vibe-coded prototype, round-tripping a dark mode so variables stay in sync between code and Figma, and using the pre-installed figma-use-scale skill to generate first-pass directions on a production dashboard. The closing update reel includes vector editing up to 10x faster, memory warnings down 92%, macOS eyedropper now samples anywhere on screen, FigJam MCP can read and write boards (ERDs, architecture diagrams), Make Kit packages your design system’s code for Figma Make, and Weave gets a timeline for video.

Config 2026 lands June 24–25 at Moscone. The agenda confirms the obvious: this year is about AI workflows and design systems built for them. Build your schedule now — last year the best talks filled up fast.

“Claude Design can read a design system carefully when the prompt is about the system. When the prompt is about a composition that uses the system, it stops respecting the components and just generates lookalikes.” TJ Pitre spent a few hours testing Claude Design against two real design systems and concludes that the tool references your system, but doesn’t consume it. Claude would happily inline HTML tags with style props instead of importing them from your component library.

“The pitch for Claude Design’s workflow is roughly: I have a design system, I want to generate new product surfaces from it, and I want AI to do most of the lift. That workflow exists today. You can pair Figma with an MCP server like our Figma Console MCP, or with Figma’s own MCP server, or with Code Connect, and then point an AI app generator at it. Lovable, v0, Replit, Figma Make, Claude Code working inside your repo. Your Figma file stays the canonical source. Your codebase stays the production surface. AI does the generation in between.That flow is more linear, more honest about where source of truth lives, and it produces output that actually uses your component library, because the AI is operating inside the repo where the components live.”

Grace Li lists 7 common design smells in GPT 5.5: huge typefaces with tight tracking, lack of textures, bento boxes with unrelated icons, pill-with-dot in hero sections, gradient keywords, grid background, and rounded cards with three nested cards. ​“TLDR: if you’re vibe coding with GPT 5.5, the easiest wins are: loosen the tracking on your headlines, delete the status pill, and pick one accent color instead of a gradient. That’ll get you out of the uncanny valley before the next model release closes the gap on its own.”

GPT 5.5 is strong at programming, but not great at visuals: ​“Across 5,000+ preference pairs, GPT‑5.5 ranks #13 in Website Arena, #16 in UI Component Arena, and #19 in 3D Design Arena. It loses to Claude Opus 4.7 and Sonnet 4.6, to Gemini 3.1, to GLM 5.1, and to Kimi K2.6.”

Figma now lets you add reference images by clicking the new ​“Add reference” button, copy/​paste, or drag-and-drop when generating or editing with AI. Closer to how designers actually work — reach for a moodboard first, prompt second.

“OpenAI’s newest image model, ChatGPT Images 2.0, is now available to use with Make Image and Edit Image in Figma Design, Draw, Slides, Buzz, and FigJam, and also in Figma Weave. ChatGPT Images 2.0 reliably generates high-quality images, and excels at producing smarter visuals like infographics or multilingual generations, executing on better editing and aesthetics, and preserving faces across generations.”

TJ Pitre’s Figma Console MCP is the most ambitious MCP server for Figma I’ve seen — 94+ tools spanning design-system extraction, file and FigJam and Slides creation, plugin debugging, and full-spectrum WCAG accessibility scanning across both design and code, including 13 design-side lint rules and code-side scanning via axe-core. Pair this with TJ’s Claude Design piece in the section above — it’s the same author making the case for what design-systems-aware AI tooling actually looks like.

Figma adds granular AI-credit governance scoped to billing groups on the Enterprise plan.