Patrick Morgan makes a clean distinction that vibe-coding discourse keeps blurring: prototype code is for exploration, production code is for endurance. He is building a protected prototyping environment using Claude Code, a place where his team can move fast and then deliberately port the right assets across the boundary into production.

There is a clear parallel with how the design team at Notion works. In the recent episode of How I AI, Brian Lovin showed their collaborative ​“prototype playground,” where the entire team can create, share, and iterate on functional prototypes.

That also reminded me of how my team worked a decade ago, back when front-end development was a tad simpler. We had a separate ​“mockups” directory inside the Rails monorepo, where designers prepared static HTML mockups with production-ready CSS and JS. By the time designs were handed off to engineers in a feature branch, all polish and design details were already baked in. The design team must be fairly technical, but there is no going back to handing off Figma files after working this way.

The new Workflow Lab format, showing an end-to-end process, is a smart way to frame the new AI image tools in context. The three new tools (erase object, isolate object, expand image) are genuinely useful for anyone who’s had to leave Figma to do basic cleanup in Photoshop, and Vectorize finally removes a step that’s been a quiet annoyance for years.

FigJam is now available in Notion as a pre-configured MCP integration.

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

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.”