An official catalogue of agentic tools supporting context from the new Figma MCP server.

Thomas Lowry, Director of Advocacy at Figma, shares three best practices for designers to give developers—and the AI agents they use—the context they need to go from design to production.

Kris Rasmussen, CTO of Figma: ​“Today we’re announcing updates to the Figma MCP server and Code Connect that make it possible to bring Figma design context anywhere you work—whether it’s in your IDE, your AI agent, or your prototypes. These updates make your design context—context about how your design system is structured, how your codebase is written, and how your team builds products—more portable and powerful, helping you move from idea to product with less friction.”

This update includes three major releases. Remote access to the Figma MCP server from your IDE, an AI coding agent, or a browser-based model. Bring the underlying code from a Figma Make file to your codebase using the Figma MCP server. Code Connect’s new in-app mapping experience lets you browse components inside Figma, map them to the right code and file, and see which are linked or missing.

Speaking of Cursor, Lee Robinson recorded a six-part video series on AI foundations. It’s designed for beginners to learn concepts like tokens, context, and agents. The entire course is free and just 1 hour long.

Peter Yang interviews Meaghan Choi, a design lead for Claude Code, about her Figma-to-code workflow and the top 3 design use cases for Claude Code.

Figma announced early access to the limited alpha of editing designs using text prompts on the canvas. I’m stoked about this release as it will make experimenting, trying new ideas, and exploring alternatives so much faster.

“You can now attach up to 6 reference images when prompting AI to make or edit an image. This can help match brand style, add specific objects, or create similar images based on existing assets.”

Design Engineer Carmen Ansio on the change coming to translating visual ideas into solid code: ​“We’re on the edge of a massive shift, thanks to three things coming together: smart design systems in Figma, an AI-native code editor called Cursor, and a data bridge called the Model Context Protocol (MCP). We’re not just translating pictures anymore. We’re building machine-readable systems that an AI can understand and build from directly. This guide is for you, the person on the ground, showing you not just how to use this new workflow, but how to think about it.”

In this webinar, Yarden Katz (Product Manager for MCP) and Peter McCarron (PMM for Dev Tools) walk through some best practices for how to structure your design files to ensure better design-to-code translation, use annotations and rules to align outputs with your codebase, and provide other tips & tricks for optimizing your MCP outputs.

Matt Wierzbicki shows how to turn Figma designs made with shadcn/​ui into production‑ready code by setting up Cursor to use shadcn/​ui and Figma MCPs.

In the first episode of a free Figma AI course by The Cutting Edge School, you’ll learn how to turn static designs into working web apps using Figma Make, without writing a single line of code. It explores the interface, attaching design files, styling components, adding a backend with Supabase, and finally previewing and publishing a live prototype. This is a beginner-friendly lesson that covers Figma Sites, Dev Mode, and how to use Claude-powered AI to generate functional apps faster than ever.

Maggie Appleton argues today’s chatbots drift toward sycophancy — undercutting Enlightenment habits of skeptical, reader-engaging discourse — and suggests giving users explicit ​“critique modes,” routing to tougher personas, and training methods beyond RLHF (reinforcement learning from human feedback) so assistants challenge us, not flatter us.

A fun chatbot made by Max Schoening from Notion. Reading The Grug Brained Developer first is recommended, but ​“What Grug know” is a good primer on simplicity and avoiding pain.

Updates to AI-powered image editing features across all products — remove background or boost resolution for up to 25 images at once, and choose between Gemini 2.0 Flash and GPT Image 1 to get results that best match your prompt.

Starting July 24th, Figma Make and all Figma AI features, including Code Layers, Rename Layers, Make/​Edit Image, etc., are now in general availability, and Figma Make is available for everyone to try. All plans and seat types include AI credits that are shared across all Figma AI features and products.

Anthropic Product Designer Meaghan Choi and Figma Developer Advocate Akbar Mirza show how Anthropic goes from design to prototype to production with Claude Code and Figma’s Dev Mode MCP server.

Ana Boyer: ​“Just as design systems help design and engineering teams understand brand guidelines, best practices, patterns, and code, they give AI agents the context they need to produce not just any output, but the right output. And when AI agents can build with your design context, they create a flywheel effect: AI strengthens your design system, which powers better AI code generation.”

Great analogy: ​“Asking an AI agent to generate code without design system context is like asking a new engineer to start shipping code before onboarding. It might technically work—but it won’t align with how your team actually builds.”

Joey Banks shares a free lesson from his course with Dive readers on how to use Figma’s MCP Server. 

Dan Saffer makes a clear case that AI doesn’t kill UI — it raises the bar for it. A single chat box won’t cut it, and direct manipulation plus visual affordances make AI legible, accessible, and trustworthy.

Zeh Fernandes revisits David Krakauer’s ​“complementary vs. competitive” framework — think abacus vs. calculator, GPS as a skill-eroder — and argues that AI tools should teach as well as do. ​”Often, we don’t want to be better navigators, or our use of math is so trivial it doesn’t justify constant practice. And that’s fine. So long as it’s a deliberate choice. But in digital product design, the emphasis tends to fall on outcomes alone: getting the job done, removing friction, making everything feel effortless. In the short term, we gain speed. Over time, though, we risk dulling the very skills we once actively cultivated.”