From design system documentation and PRDs to user research and feedback, Make can now pull in context from across your product ecosystem. Figma added new featured connectors for Amplitude, Box, Dovetail, Granola, Marvin, and zeroheight. You can also connect Make to any remote MCP server by setting up a custom connector.

Once you’ve installed and authorized a Make connector, just hit @ in your Make file and start typing the connector name to pull external context directly into your prototype.

Alex Barashkov is disappointed by this release, and I have to agree with some of his points. I spend more time in Cursor than Figma lately, and returning to a workspace without AI agents is always hard. In the most recent and relevant example, after importing a few screens from code to Figma, I had to manually replace fonts (no ​“Selection fonts” for bulk edits, so first had to test a few plugins) and colors (a bit easier but still cumbersome), then abstract repetitive elements into components. While doing this, I kept asking myself why I have to waste time on this when bots can do it in minutes.

The State of the Designer report explores how designers around the world are upleveling their skills, keeping craft high, and turning new pressures into creative momentum. ​“For some designers, AI’s impact on product design can feel destabilizing, but beneath that uncertainty is an undercurrent of optimism—89% say they’re working faster, and 80% say they’re collaborating better. And despite fears that AI slop might degrade craft and quality, designers are actually finding the opposite to be true: 91% say that new AI tools improve their designs.”

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.”

“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.”

Greg Huntoon: ​“Every prompt needs clarity, context, and constraints. I’ve been building my own prompt framework, and this TC-EBC structure — Task, Context, Elements, Behavior, Constraints — has served me well. This kind of structure doesn’t just help you get better results — it’s aligned with what prompt engineers and system designers are converging on across disciplines.”

Siddhant Khare: ​“When each task takes less time, you don’t do fewer tasks. You do more tasks. Your capacity appears to expand, so the work expands to fill it. And then some. Your manager sees you shipping faster, so the expectations adjust. You see yourself shipping faster, so your own expectations adjust. The baseline moves. […] This is the paradox: AI reduces the cost of production but increases the cost of coordination, review, and decision-making. And those costs fall entirely on the human.”

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.

Brett argues that while Twitter is full of advice to ​“get out of Figma” and learn AI tools, the people actually making money right now are visual designers who doubled down on craft, speed, and positioning rather than trying to vibe‑code products. He frames the explosion of AI and no‑code tools as a demand driver: when thousands of functional products ship every day, the only durable differentiator becomes craft. ​“In a world where everyone can build, the people who can make it beautiful will be the most valuable people in the room.”

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.

With the Figma MCP app in Claude, designers, developers, and product managers can now create AI-generated FigJam diagrams.

On a recent livestream, Product Designer Megan Bednarczyk and Software Engineer Nile Phillips from Figma demonstrated how PDE teams can use AI-powered diagramming to tackle complex problems and visualize the bigger picture.

“Join Nikolas Klein (Product Manager, Figma) and Peter Ng (Product Designer, Figma) in the first episode of Design Roulette, where we challenge designers to create designs with no preparation. The twist? They’ll also have to spin the wheel and incorporate the chosen random design prompt into their design. In this episode, they’ll conceptualize ads for the mythical hot sauce, Véloce, using Figma’s new AI image editing tools.”

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

Jakub Krehel shows how he uses AI every day as a design engineer. My process is very similar, but I still picked up a few things!

Admins on Organization and Enterprise plans can now view historical AI credit usage data to better plan for future costs.

I wrote about Vercel’s Web Interface Guidelines in the past, but now they’re available as a skill/​command for your agent.

Great conversation between Ridd and Kyle Zantos on how designers can actually build things with AI using Claude Code. Many tips are tactical and transferable to other tools like Cursor. A few things I’m going to try after listening to this episode are using Leva for playing with parameters and building skills encoding best practices from top design engineers. After this episode went live, Kyle published Design Motion Principles, a Claude Code skill for motion and interaction design audits, trained on Emil Kowalski, Jakub Krehel, and Jhey Tompkins.