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.

Mallory breaks down how brand designers can use variables to scale brand expression in Figma. Learn what variables are, how they differ from styles, and how they support real brand use cases — from multi-brand systems to scalable templates.

Pablo Stanley: ​“I’m a designer. For years, my world has been Figma, Sketch, Adobe. Nice GUIs with buttons and panels and things I could click. The terminal? That was a black rectangle where the dev team did hacker things. No buttons. No UI. Just a blinking cursor judging you for not knowing what ls ‑la meant. And now? My design tool of choice is the terminal.”

Dylan interviewed post earnings on TBPN: ​“We discuss Figma’s growth, the rise of Figma Make, the shift from linear coding to a visual-first product loop, why taste becomes the real moat in an agent-driven world, and why design is the ultimate differentiator in 2026.”

Dylan Field joins Deirdre Bosa from CNBC for a pre-earnings interview and an announcement of the Code to Canvas partnership with Anthropic. Dylan argues that AI coding tools will dramatically lower the barrier for writing software, but product design and understanding human needs remain essential; AI cannot replace the judgment, taste, and empathy of designers and product teams. Figma is a collaboration and orchestration layer for this new world, where many more people can create software but still need a shared space to ideate, design, and align on what should be built.

Miggi presents the new vector point box transform controls, letting you resize selections of vector points as a box instead of nudging each point manually. This makes symmetry tweaks and proportional adjustments much faster and fills a gap in Figma’s otherwise excellent vector tooling. It’s the kind of unsexy but high‑leverage improvement that will matter more the deeper you are in vector-heavy files.

Rogie King introduces Vectorize, a new AI-powered action in Figma Design and Draw that converts any raster image into fully editable vectors in one click. This feature finally removes the need to use 3rd-party plugins or to redraw assets, while still letting you tweak paths, use color variables, and turn ​“messy” starting points into reusable components.

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.

Tom Johnson outlines a nine-step AI-heavy design workflow where he starts with messy voice transcripts, uses Claude and tools like Willow, Notion, or Granola to structure the problem, then lets AI generate a deliberately bad but functional app as a scaffold. This matters because it reframes AI’s weakness at UX as a feature: a cheap way to explore directions, expose edge cases, and pressure-test scope before committing to real craft in Figma and a proper engineering handoff.

The Glass effect is now generally available, and Miggi introduces a few updates: add Glass to any object, shape, or text; design Glass with non-uniform corners and precisely round each corner radius; use the Splay property to control how light bends around an object’s edges; and apply variables to Glass properties to easily connect to your design system.

Ridd shares his mental model for deciding which tools to reach for when coding with AI. Also available as a Dive Club video.

Nikolas Klein, PM at Figma: ​“Today, we’re introducing the ability to embed Figma Make prototypes into Figma Design, FigJam, and Figma Slides, along with new editing tools that help you build and share your best ideas.”

Joey Banks shares a simple way to get started with variables structure when he is not sure where to begin: ​“One very simple approach that’s worked well for me is separating variables into non-interactive and interactive buckets. […] Non-interactive variables describe the environment. Things like background surfaces, text, icons, and borders that don’t change based on input. Interactive variables describe behavior, such as actions, states, and feedback that do respond to input.”

Marcin Wichary, Design Architect at Figma, started a microblog about software craft and quality. His writing is always wonderful and insightful — instant subscribe.

Speaking of Tom, in this interview with Jay, he shows the DM he sent to Linear’s CEO to get an interview — and later the portfolio and case studies he used to land the job at Vercel.

Tom Johnson: ​“It’s literally faster for me to build a concept inside of the actual codebase than it is to work in Figma. But the amount of versions and breadth of the final result is not up to the quality bar that I usually hold. I’m loving the speed, but the output is sloppy at times. So I’ve got this weird flow of Code → Code → Figma → Code → Figma. Repeat, reorder, etc. The issue is that the transition from Figma → code with their MCP is solid. […] But code → Figma… is a terrible flow.”

I often spend more time recreating a particular screen in Figma than actually designing the change. I’ve been beating on the Code Connect drum for a while as it has huge potential for connecting design and code components. Even though it was built to translate components from Figma to code, I don’t see why it wouldn’t work in reverse. Code Connect was announced almost two years ago (way before LLMs and MCPs got powerful), but because it’s locked behind Organization and Enterprise plans, it’s rarely discussed in the community or considered by plugin and tool makers.

In this talk from Hatch Conference, Jenny Wen, Design Lead at Anthropic and former Director of Design at Figma, explains why the traditional design process is outdated and no longer works for today’s tools and tech: ​“With AI accelerating prototyping, smaller teams doing more, and craft becoming a key differentiator, rigid processes are failing designers. Jenny shares real examples from Figma and Anthropic that show how great work actually gets made today. Starting from solutions, caring deeply about details, building intuition, skipping steps, and designing for delight.”

Jenny’s talk really resonated with me. Quickly trying and discarding solutions, iterating on details, and relying on intuition is how I prefer to work. Still, without formal collateral such as personas or problem statements, it can feel like taking a shortcut. I went through a phase of producing these artifacts, but often found them more useful for justifying decisions than making them. It finally clicked when I read Alan Cooper’s interaction design bible, ​“About Face,” a decade ago: a lot of these processes came from design consultancies. They have to learn a client’s business, do product discovery, solve a problem, and sell it to stakeholders in a short time before moving to the next client. The longer you work on a product, explore the problem space, and listen to users, the stronger your intuition gets, which lets you fast-forward and compress discovery and design process.

“In this episode of In Good Company, Nicolai Tangen speaks with Dylan Field, founder and CEO of Figma, about the ideas behind one of the most influential design platforms in the world. Field shares lessons from founding Figma at 19, navigating years of iteration before launch, and scaling with a strong product culture. They discuss taste, craft, and community, how AI is changing the creative process, and what it means to lead with optimism in a rapidly evolving tech landscape.”

MDS recorded a Figma tutorial video dissecting why Anthropic’s Claude app icons feel so satisfying and explaining how to recreate these animated icon components in Figma using Smart Animate.