{"id":58313,"date":"2026-02-26T09:00:12","date_gmt":"2026-02-26T17:00:12","guid":{"rendered":"https:\/\/www.uxpin.com\/studio\/?p=58313"},"modified":"2026-02-26T20:27:43","modified_gmt":"2026-02-27T04:27:43","slug":"figma-openai-codex-design-to-code-workflows","status":"publish","type":"post","link":"https:\/\/www.uxpin.com\/studio\/blog\/figma-openai-codex-design-to-code-workflows\/","title":{"rendered":"Figma integrates OpenAI Codex. The design-to-code gap still exists."},"content":{"rendered":"

Figma<\/a> has unveiled a new integration with OpenAI<\/a>\u2019s Codex, enabling users to move between design files and code implementation through Figma’s MCP server. Engineers can iterate visually inside Figma. Designers can engage more closely with implementation without becoming full-time coders. On paper, it sounds like the handoff problem is solved.<\/p>\n

\n
\n

It isn’t. But the announcement tells you a lot about where the industry is heading \u2014 and where the real gap still lives.<\/p>\n<\/div>\n<\/div>\n

A tool for both designers and developers<\/p>\n

One of the standout aspects of this integration is its ability to cater to both designers and engineers without requiring either to step fully into the other’s domain. Alexander Embiricos, Codex product lead, explained, “The integration makes Codex powerful for a much broader range of builders and businesses because it doesn\u2019t assume you\u2019re \u2018a designer\u2019 or \u2018an engineer\u2019 first. Engineers can iterate visually without leaving their flow, and designers can work closer to real implementation without becoming full-time coders.”<\/p>\n

This dual-purpose functionality is expected to enhance collaboration by allowing engineers to contribute visually and designers to engage more closely with implementation.<\/p>\n

Good timing \u2014 this news is perfect fodder for Pillar 3 messaging. Here’s the rewritten post:<\/p>\n

What the Figma-Codex integration actually does<\/h2>\n

The integration works through Figma’s MCP server, connecting Figma’s canvas \u2014 design files, Figma Make, or FigJam \u2014 to Codex for code implementation. The goal, as Codex product lead Alexander Embiricos put it, is to serve builders who don’t want to be forced to identify as “a designer” or “an engineer” first.<\/p>\n

Figma’s chief design officer Loredan Crisan framed it as a way for teams to “build on their best ideas \u2014 not just their first idea \u2014 by combining the best of code with the creativity, collaboration, and craft that comes with Figma’s infinite canvas.”<\/p>\n

It builds on an already deep relationship between the two companies. Figma was among the first to launch an app in ChatGPT back in October 2025, and its earlier collaboration with Anthropic to incorporate Claude Code signalled a broader strategy of weaving AI tools into the design workflow.<\/p>\n

This Codex integration continues that direction. It’s real, it’s useful, and for teams without existing design systems, it meaningfully closes the distance between design and development.<\/p>\n

What Figma + Codes doesn’t solve<\/h2>\n

Here’s the thing about Figma’s MCP server: it exposes visual layer data. Frames, layers, colours, positions. It tells Codex what things look like<\/em>.<\/p>\n

It doesn’t tell Codex what things are<\/em>.<\/p>\n

When Codex receives that visual data and generates code, it’s interpreting pixels \u2014 making educated guesses about what component to use, what props to set, what your team actually calls things in your codebase. For greenfield projects, that’s fine. For enterprise teams with existing design systems \u2014 with their own Button components, their own Card variants, their own design tokens \u2014 the gap between “what Figma shows” and “what our codebase expects” doesn’t disappear. It just moves.<\/p>\n

The handoff problem doesn’t live in the design tool anymore. It lives in the translation step between visual output and production code. Figma + Codex makes that translation faster. It doesn’t eliminate it.<\/p>\n

How UXPin Forge AI approaches the same problem differently<\/h2>\n

Forge AI doesn’t start from visuals and work toward code. It starts from code and works toward design.<\/p>\n

When you prompt Forge AI to generate a dashboard, it doesn’t draw rectangles that look like your Button component. It places your actual Button component \u2014 from your production React library, with your prop structure, your variants, your states. The canvas renders real components, not approximations of them.<\/p>\n

This matters because of what it changes downstream.<\/p>\n

What Figma’s MCP server exposes to Codex:<\/strong> visual layer data \u2014 frames, colours, positions that Codex must interpret and convert to code.<\/p>\n

What UXPin’s component API exposes:<\/strong> actual component data \u2014 prop names, accepted values, variant options, state definitions \u2014 that developers can use directly.<\/p>\n

The difference isn’t speed. Both are fast. The difference is fidelity<\/em>. One gives AI a picture of your UI and asks it to reverse-engineer your codebase. The other gives AI your codebase and asks it to build UI from it.<\/p>\n

\n\n\n\n\n\n\n\n\n\n\n
<\/th>\nFigma + Codex<\/th>\nUXPin Forge AI<\/th>\n<\/tr>\n<\/thead>\n
What AI works from<\/strong><\/td>\nVisual layers from canvas<\/td>\nYour actual React components<\/td>\n<\/tr>\n
MCP server exposes<\/strong><\/td>\nPixel and layer data<\/td>\nComponent props, variants, states<\/td>\n<\/tr>\n
After generation<\/strong><\/td>\nCodex interprets visuals \u2192 code<\/td>\nJSX references your existing library<\/td>\n<\/tr>\n
Design system awareness<\/strong><\/td>\nAdvisory \u2014 Codex infers<\/td>\nEnforced \u2014 Forge generates within it<\/td>\n<\/tr>\n
Post-generation editing<\/strong><\/td>\nBack to design canvas or code editor<\/td>\nProfessional design tools on the same canvas<\/td>\n<\/tr>\n
Output fidelity<\/strong><\/td>\nCodex approximation<\/td>\nYour component names, your prop structure<\/td>\n<\/tr>\n<\/tbody>\n<\/table>\n<\/div>\n

<\/h2>\n

The Design to Code workflow no other tool provides<\/h2>\n

Forge AI isn’t just a generation tool. After it generates, you have a complete professional design environment on the same canvas \u2014 pixel-level layout control, component property adjustment, responsive breakpoints, variant exploration, real-time collaboration. The refinement happens on the same code-backed components Forge placed.<\/p>\n

And when you’re done, the export is JSX that references your actual component library. Your engineers receive code they can integrate immediately. Nothing to translate. Nothing to rebuild.<\/p>\n

    \n
  1. Prompt<\/strong> \u2014 describe the UI you need<\/li>\n
  2. Forge generates<\/strong> \u2014 real components from your library, correct props and variants<\/li>\n
  3. Refine visually<\/strong> \u2014 professional design tools on the same canvas<\/li>\n
  4. Iterate with AI<\/strong> \u2014 conversational modifications, not regeneration from scratch<\/li>\n
  5. Export<\/strong> \u2014 production-ready JSX using your actual component library<\/li>\n
  6. Ship<\/strong> \u2014 engineers integrate directly<\/li>\n<\/ol>\n

    The bottom line<\/h2>\n

    Figma’s Codex integration is a meaningful step. For teams starting from scratch, it genuinely accelerates the path from idea to implementation. The partnership between two of the most widely-used tools in design and development will matter.<\/p>\n

    But for enterprise teams with existing design systems \u2014 where brand consistency, governance, and codebase alignment aren’t optional \u2014 the gap between visual output and production code remains. Making that translation faster isn’t the same as eliminating it.<\/p>\n

    Forge AI was built to eliminate it.<\/p>\n

    Want to see the difference?<\/strong> Try Forge AI with your own component library – MUI, shadcn\/ui, Ant Design, or your custom system via Git. Generate a real UI in under five minutes and export the JSX.<\/p>\n

    Start your free trial<\/a> today, or learn <\/strong>Learn more about Forge AI works with your design system<\/a><\/strong><\/p>\n

    Read the source<\/a><\/em><\/p>\n

    \n

    FAQs<\/h2>\n
    \n
    \n

    Q: What does Figma’s OpenAI Codex integration actually do?<\/strong> Figma’s Codex integration connects Figma’s canvas to OpenAI Codex via Figma’s MCP server. Designers and engineers can move between Figma design files and code implementation without switching tools. Codex receives visual layer data from Figma and generates code based on that output \u2014 removing the need to manually translate designs into a development environment.<\/p>\n<\/div>\n<\/div>\n

    \n
    \n

    Q: Does Figma’s Codex integration work with existing design systems?<\/strong> Figma’s Codex integration works with any Figma file, but Codex generates code by interpreting visual layers rather than reading your actual component library. For teams with existing design systems, Codex must infer which components to use and how to structure the output. That inference is the remaining gap \u2014 faster than before, but not eliminated.<\/p>\n<\/div>\n<\/div>\n

    \n
    \n

    Q: What is the difference between Figma’s MCP server and UXPin’s component API?<\/strong> Figma’s MCP server exposes visual layer data \u2014 frames, positions, and colours \u2014 that AI must interpret to generate code. UXPin’s component API exposes actual component data: prop names, accepted values, variant options, and state definitions from your production React library. One gives AI a picture of your UI. The other gives AI your codebase.<\/p>\n<\/div>\n<\/div>\n

    \n
    \n

    Q: What is Forge AI and how is it different from Figma + Codex?<\/strong> Forge AI is UXPin’s AI design assistant. Rather than starting from visuals and generating toward code, Forge starts from your production component library and works outward. It generates UI using your actual React components \u2014 with their real props, variants, and states \u2014 on a professional design canvas. The output is JSX that maps directly to your codebase. Developers receive code they can integrate immediately, with nothing to interpret or rebuild.<\/p>\n<\/div>\n<\/div>\n

    \n
    \n

    Q: Which design systems and component libraries does Forge AI support?<\/strong> Forge AI supports any React-based component library. Built-in support is available for MUI, shadcn\/ui, Ant Design, Bootstrap, Tailwind UI, Microsoft Fluent, and IBM Carbon. Custom proprietary systems connect via Git repository, npm package, or Storybook sync.<\/p>\n<\/div>\n<\/div>\n

    \n
    \n

    Q: Does Forge AI replace professional design tools?<\/strong> No \u2014 Forge AI handles the 0\u201380% generation problem. After generation, UXPin provides a complete professional design environment on the same canvas: pixel-level layout control, component property adjustment, variant exploration, responsive breakpoints, and real-time collaboration. The refinement happens on the same code-backed components Forge placed, not on vectors that need to be rebuilt separately.<\/p>\n<\/div>\n<\/div>\n

    \n
    \n

    Q: What does “production-ready JSX” mean in practice?<\/strong> When Forge AI exports JSX, it references the actual component names and prop structures from your library. If your library has a <Card><\/code> component that accepts a padding<\/code> prop, the export reads <Card padding=\"lg\"><\/code> \u2014 not a generic approximation. Your engineers receive code that maps directly to their codebase with no translation step required.<\/p>\n<\/div>\n<\/div>\n","protected":false},"excerpt":{"rendered":"

    Figma integrates OpenAI’s Codex via its MCP server to turn designs into code and bridge design-engineering workflows.<\/p>\n","protected":false},"author":231,"featured_media":58314,"comment_status":"closed","ping_status":"closed","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[3],"tags":[],"class_list":["post-58313","post","type-post","status-publish","format-standard","has-post-thumbnail","hentry","category-blog"],"yoast_title":"Figma + OpenAI Codex: Design-to-Code Gap Still Exists","yoast_metadesc":"Figma's Codex integration is fast. But visual layers aren't your component library. Here's what the gap still costs enterprise design system teams.","acf":[],"yoast_head":"\nFigma + OpenAI Codex: Design-to-Code Gap Still Exists<\/title>\n<meta name=\"description\" content=\"Figma's Codex integration is fast. But visual layers aren't your component library. Here's what the gap still costs enterprise design system teams.\" \/>\n<meta name=\"robots\" content=\"index, follow, max-snippet:-1, max-image-preview:large, max-video-preview:-1\" \/>\n<link rel=\"canonical\" href=\"https:\/\/www.uxpin.com\/studio\/blog\/figma-openai-codex-design-to-code-workflows\/\" \/>\n<meta property=\"og:locale\" content=\"en_US\" \/>\n<meta property=\"og:type\" content=\"article\" \/>\n<meta property=\"og:title\" content=\"Figma integrates OpenAI Codex. The design-to-code gap still exists.\" \/>\n<meta property=\"og:description\" content=\"Figma's Codex integration is fast. But visual layers aren't your component library. Here's what the gap still costs enterprise design system teams.\" \/>\n<meta property=\"og:url\" content=\"https:\/\/www.uxpin.com\/studio\/blog\/figma-openai-codex-design-to-code-workflows\/\" \/>\n<meta property=\"og:site_name\" content=\"Studio by UXPin\" \/>\n<meta property=\"article:published_time\" content=\"2026-02-26T17:00:12+00:00\" \/>\n<meta property=\"article:modified_time\" content=\"2026-02-27T04:27:43+00:00\" \/>\n<meta property=\"og:image\" content=\"https:\/\/www.uxpin.com\/studio\/wp-content\/uploads\/2026\/02\/image_c3ba05eef29991009b26ed639d5c7c37.jpeg\" \/>\n\t<meta property=\"og:image:width\" content=\"1536\" \/>\n\t<meta property=\"og:image:height\" content=\"1024\" \/>\n\t<meta property=\"og:image:type\" content=\"image\/jpeg\" \/>\n<meta name=\"author\" content=\"Andrew Martin\" \/>\n<meta name=\"twitter:card\" content=\"summary_large_image\" \/>\n<meta name=\"twitter:creator\" content=\"@andrewSaaS\" \/>\n<meta name=\"twitter:label1\" content=\"Written by\" \/>\n\t<meta name=\"twitter:data1\" content=\"Andrew Martin\" \/>\n\t<meta name=\"twitter:label2\" content=\"Est. reading time\" \/>\n\t<meta name=\"twitter:data2\" content=\"7 minutes\" \/>\n<script type=\"application\/ld+json\" class=\"yoast-schema-graph\">{\"@context\":\"https:\\\/\\\/schema.org\",\"@graph\":[{\"@type\":\"Article\",\"@id\":\"https:\\\/\\\/www.uxpin.com\\\/studio\\\/blog\\\/figma-openai-codex-design-to-code-workflows\\\/#article\",\"isPartOf\":{\"@id\":\"https:\\\/\\\/www.uxpin.com\\\/studio\\\/blog\\\/figma-openai-codex-design-to-code-workflows\\\/\"},\"author\":{\"name\":\"Andrew Martin\",\"@id\":\"https:\\\/\\\/www.uxpin.com\\\/studio\\\/#\\\/schema\\\/person\\\/ac635ff03bf09bee5701f6f38ce9b16b\"},\"headline\":\"Figma integrates OpenAI Codex. The design-to-code gap still exists.\",\"datePublished\":\"2026-02-26T17:00:12+00:00\",\"dateModified\":\"2026-02-27T04:27:43+00:00\",\"mainEntityOfPage\":{\"@id\":\"https:\\\/\\\/www.uxpin.com\\\/studio\\\/blog\\\/figma-openai-codex-design-to-code-workflows\\\/\"},\"wordCount\":1505,\"image\":{\"@id\":\"https:\\\/\\\/www.uxpin.com\\\/studio\\\/blog\\\/figma-openai-codex-design-to-code-workflows\\\/#primaryimage\"},\"thumbnailUrl\":\"https:\\\/\\\/www.uxpin.com\\\/studio\\\/wp-content\\\/uploads\\\/2026\\\/02\\\/image_c3ba05eef29991009b26ed639d5c7c37.jpeg\",\"articleSection\":[\"Blog\"],\"inLanguage\":\"en-US\"},{\"@type\":\"WebPage\",\"@id\":\"https:\\\/\\\/www.uxpin.com\\\/studio\\\/blog\\\/figma-openai-codex-design-to-code-workflows\\\/\",\"url\":\"https:\\\/\\\/www.uxpin.com\\\/studio\\\/blog\\\/figma-openai-codex-design-to-code-workflows\\\/\",\"name\":\"Figma + OpenAI Codex: Design-to-Code Gap Still Exists\",\"isPartOf\":{\"@id\":\"https:\\\/\\\/www.uxpin.com\\\/studio\\\/#website\"},\"primaryImageOfPage\":{\"@id\":\"https:\\\/\\\/www.uxpin.com\\\/studio\\\/blog\\\/figma-openai-codex-design-to-code-workflows\\\/#primaryimage\"},\"image\":{\"@id\":\"https:\\\/\\\/www.uxpin.com\\\/studio\\\/blog\\\/figma-openai-codex-design-to-code-workflows\\\/#primaryimage\"},\"thumbnailUrl\":\"https:\\\/\\\/www.uxpin.com\\\/studio\\\/wp-content\\\/uploads\\\/2026\\\/02\\\/image_c3ba05eef29991009b26ed639d5c7c37.jpeg\",\"datePublished\":\"2026-02-26T17:00:12+00:00\",\"dateModified\":\"2026-02-27T04:27:43+00:00\",\"author\":{\"@id\":\"https:\\\/\\\/www.uxpin.com\\\/studio\\\/#\\\/schema\\\/person\\\/ac635ff03bf09bee5701f6f38ce9b16b\"},\"description\":\"Figma's Codex integration is fast. But visual layers aren't your component library. Here's what the gap still costs enterprise design system teams.\",\"breadcrumb\":{\"@id\":\"https:\\\/\\\/www.uxpin.com\\\/studio\\\/blog\\\/figma-openai-codex-design-to-code-workflows\\\/#breadcrumb\"},\"inLanguage\":\"en-US\",\"potentialAction\":[{\"@type\":\"ReadAction\",\"target\":[\"https:\\\/\\\/www.uxpin.com\\\/studio\\\/blog\\\/figma-openai-codex-design-to-code-workflows\\\/\"]}]},{\"@type\":\"ImageObject\",\"inLanguage\":\"en-US\",\"@id\":\"https:\\\/\\\/www.uxpin.com\\\/studio\\\/blog\\\/figma-openai-codex-design-to-code-workflows\\\/#primaryimage\",\"url\":\"https:\\\/\\\/www.uxpin.com\\\/studio\\\/wp-content\\\/uploads\\\/2026\\\/02\\\/image_c3ba05eef29991009b26ed639d5c7c37.jpeg\",\"contentUrl\":\"https:\\\/\\\/www.uxpin.com\\\/studio\\\/wp-content\\\/uploads\\\/2026\\\/02\\\/image_c3ba05eef29991009b26ed639d5c7c37.jpeg\",\"width\":1536,\"height\":1024,\"caption\":\"Figma integrates OpenAI Codex to streamline design-to-code workflows\"},{\"@type\":\"BreadcrumbList\",\"@id\":\"https:\\\/\\\/www.uxpin.com\\\/studio\\\/blog\\\/figma-openai-codex-design-to-code-workflows\\\/#breadcrumb\",\"itemListElement\":[{\"@type\":\"ListItem\",\"position\":1,\"name\":\"Home\",\"item\":\"https:\\\/\\\/www.uxpin.com\\\/studio\\\/\"},{\"@type\":\"ListItem\",\"position\":2,\"name\":\"Figma integrates OpenAI Codex. The design-to-code gap still exists.\"}]},{\"@type\":\"WebSite\",\"@id\":\"https:\\\/\\\/www.uxpin.com\\\/studio\\\/#website\",\"url\":\"https:\\\/\\\/www.uxpin.com\\\/studio\\\/\",\"name\":\"Studio by UXPin\",\"description\":\"\",\"potentialAction\":[{\"@type\":\"SearchAction\",\"target\":{\"@type\":\"EntryPoint\",\"urlTemplate\":\"https:\\\/\\\/www.uxpin.com\\\/studio\\\/?s={search_term_string}\"},\"query-input\":{\"@type\":\"PropertyValueSpecification\",\"valueRequired\":true,\"valueName\":\"search_term_string\"}}],\"inLanguage\":\"en-US\"},{\"@type\":\"Person\",\"@id\":\"https:\\\/\\\/www.uxpin.com\\\/studio\\\/#\\\/schema\\\/person\\\/ac635ff03bf09bee5701f6f38ce9b16b\",\"name\":\"Andrew Martin\",\"description\":\"Andrew is the CEO of UXPin, leading its product vision for design-to-code workflows used by product and engineering teams worldwide. He writes about responsive design, design systems, and prototyping with real components to help teams ship consistent, performant interfaces faster.\",\"sameAs\":[\"https:\\\/\\\/x.com\\\/andrewSaaS\"],\"url\":\"https:\\\/\\\/www.uxpin.com\\\/studio\\\/author\\\/andrewuxpin\\\/\"}]}<\/script>\n<!-- \/ Yoast SEO Premium plugin. -->","yoast_head_json":{"title":"Figma + OpenAI Codex: Design-to-Code Gap Still Exists","description":"Figma's Codex integration is fast. But visual layers aren't your component library. Here's what the gap still costs enterprise design system teams.","robots":{"index":"index","follow":"follow","max-snippet":"max-snippet:-1","max-image-preview":"max-image-preview:large","max-video-preview":"max-video-preview:-1"},"canonical":"https:\/\/www.uxpin.com\/studio\/blog\/figma-openai-codex-design-to-code-workflows\/","og_locale":"en_US","og_type":"article","og_title":"Figma integrates OpenAI Codex. The design-to-code gap still exists.","og_description":"Figma's Codex integration is fast. But visual layers aren't your component library. Here's what the gap still costs enterprise design system teams.","og_url":"https:\/\/www.uxpin.com\/studio\/blog\/figma-openai-codex-design-to-code-workflows\/","og_site_name":"Studio by UXPin","article_published_time":"2026-02-26T17:00:12+00:00","article_modified_time":"2026-02-27T04:27:43+00:00","og_image":[{"width":1536,"height":1024,"url":"https:\/\/www.uxpin.com\/studio\/wp-content\/uploads\/2026\/02\/image_c3ba05eef29991009b26ed639d5c7c37.jpeg","type":"image\/jpeg"}],"author":"Andrew Martin","twitter_card":"summary_large_image","twitter_creator":"@andrewSaaS","twitter_misc":{"Written by":"Andrew Martin","Est. reading time":"7 minutes"},"schema":{"@context":"https:\/\/schema.org","@graph":[{"@type":"Article","@id":"https:\/\/www.uxpin.com\/studio\/blog\/figma-openai-codex-design-to-code-workflows\/#article","isPartOf":{"@id":"https:\/\/www.uxpin.com\/studio\/blog\/figma-openai-codex-design-to-code-workflows\/"},"author":{"name":"Andrew Martin","@id":"https:\/\/www.uxpin.com\/studio\/#\/schema\/person\/ac635ff03bf09bee5701f6f38ce9b16b"},"headline":"Figma integrates OpenAI Codex. The design-to-code gap still exists.","datePublished":"2026-02-26T17:00:12+00:00","dateModified":"2026-02-27T04:27:43+00:00","mainEntityOfPage":{"@id":"https:\/\/www.uxpin.com\/studio\/blog\/figma-openai-codex-design-to-code-workflows\/"},"wordCount":1505,"image":{"@id":"https:\/\/www.uxpin.com\/studio\/blog\/figma-openai-codex-design-to-code-workflows\/#primaryimage"},"thumbnailUrl":"https:\/\/www.uxpin.com\/studio\/wp-content\/uploads\/2026\/02\/image_c3ba05eef29991009b26ed639d5c7c37.jpeg","articleSection":["Blog"],"inLanguage":"en-US"},{"@type":"WebPage","@id":"https:\/\/www.uxpin.com\/studio\/blog\/figma-openai-codex-design-to-code-workflows\/","url":"https:\/\/www.uxpin.com\/studio\/blog\/figma-openai-codex-design-to-code-workflows\/","name":"Figma + OpenAI Codex: Design-to-Code Gap Still Exists","isPartOf":{"@id":"https:\/\/www.uxpin.com\/studio\/#website"},"primaryImageOfPage":{"@id":"https:\/\/www.uxpin.com\/studio\/blog\/figma-openai-codex-design-to-code-workflows\/#primaryimage"},"image":{"@id":"https:\/\/www.uxpin.com\/studio\/blog\/figma-openai-codex-design-to-code-workflows\/#primaryimage"},"thumbnailUrl":"https:\/\/www.uxpin.com\/studio\/wp-content\/uploads\/2026\/02\/image_c3ba05eef29991009b26ed639d5c7c37.jpeg","datePublished":"2026-02-26T17:00:12+00:00","dateModified":"2026-02-27T04:27:43+00:00","author":{"@id":"https:\/\/www.uxpin.com\/studio\/#\/schema\/person\/ac635ff03bf09bee5701f6f38ce9b16b"},"description":"Figma's Codex integration is fast. But visual layers aren't your component library. Here's what the gap still costs enterprise design system teams.","breadcrumb":{"@id":"https:\/\/www.uxpin.com\/studio\/blog\/figma-openai-codex-design-to-code-workflows\/#breadcrumb"},"inLanguage":"en-US","potentialAction":[{"@type":"ReadAction","target":["https:\/\/www.uxpin.com\/studio\/blog\/figma-openai-codex-design-to-code-workflows\/"]}]},{"@type":"ImageObject","inLanguage":"en-US","@id":"https:\/\/www.uxpin.com\/studio\/blog\/figma-openai-codex-design-to-code-workflows\/#primaryimage","url":"https:\/\/www.uxpin.com\/studio\/wp-content\/uploads\/2026\/02\/image_c3ba05eef29991009b26ed639d5c7c37.jpeg","contentUrl":"https:\/\/www.uxpin.com\/studio\/wp-content\/uploads\/2026\/02\/image_c3ba05eef29991009b26ed639d5c7c37.jpeg","width":1536,"height":1024,"caption":"Figma integrates OpenAI Codex to streamline design-to-code workflows"},{"@type":"BreadcrumbList","@id":"https:\/\/www.uxpin.com\/studio\/blog\/figma-openai-codex-design-to-code-workflows\/#breadcrumb","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https:\/\/www.uxpin.com\/studio\/"},{"@type":"ListItem","position":2,"name":"Figma integrates OpenAI Codex. The design-to-code gap still exists."}]},{"@type":"WebSite","@id":"https:\/\/www.uxpin.com\/studio\/#website","url":"https:\/\/www.uxpin.com\/studio\/","name":"Studio by UXPin","description":"","potentialAction":[{"@type":"SearchAction","target":{"@type":"EntryPoint","urlTemplate":"https:\/\/www.uxpin.com\/studio\/?s={search_term_string}"},"query-input":{"@type":"PropertyValueSpecification","valueRequired":true,"valueName":"search_term_string"}}],"inLanguage":"en-US"},{"@type":"Person","@id":"https:\/\/www.uxpin.com\/studio\/#\/schema\/person\/ac635ff03bf09bee5701f6f38ce9b16b","name":"Andrew Martin","description":"Andrew is the CEO of UXPin, leading its product vision for design-to-code workflows used by product and engineering teams worldwide. He writes about responsive design, design systems, and prototyping with real components to help teams ship consistent, performant interfaces faster.","sameAs":["https:\/\/x.com\/andrewSaaS"],"url":"https:\/\/www.uxpin.com\/studio\/author\/andrewuxpin\/"}]}},"_links":{"self":[{"href":"https:\/\/www.uxpin.com\/studio\/wp-json\/wp\/v2\/posts\/58313","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/www.uxpin.com\/studio\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/www.uxpin.com\/studio\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/www.uxpin.com\/studio\/wp-json\/wp\/v2\/users\/231"}],"replies":[{"embeddable":true,"href":"https:\/\/www.uxpin.com\/studio\/wp-json\/wp\/v2\/comments?post=58313"}],"version-history":[{"count":6,"href":"https:\/\/www.uxpin.com\/studio\/wp-json\/wp\/v2\/posts\/58313\/revisions"}],"predecessor-version":[{"id":58338,"href":"https:\/\/www.uxpin.com\/studio\/wp-json\/wp\/v2\/posts\/58313\/revisions\/58338"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/www.uxpin.com\/studio\/wp-json\/wp\/v2\/media\/58314"}],"wp:attachment":[{"href":"https:\/\/www.uxpin.com\/studio\/wp-json\/wp\/v2\/media?parent=58313"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/www.uxpin.com\/studio\/wp-json\/wp\/v2\/categories?post=58313"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/www.uxpin.com\/studio\/wp-json\/wp\/v2\/tags?post=58313"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}