Automating Graphic Design Workflows

Don't need to comment, like, or connect. Download it. Read it. Use it. Learn with it. Over the last weeks I kept seeing the same pattern. Designers were curious about MCP, but stuck. The path was unclear. Setup felt intimidating. Real use cases were missing. So I built the Design MCP Adoption Toolkit. A practical guide for using MCP inside a real Figma workflow. No theory. No hype. Just execution. Inside you will find: → What MCP is in plain language. → The three MCPs that matter for design work. → The mental model for Anthropic Claude Code to Figma, OpenAI Codex to Figma, and Figma Console MCP by Southleft, LLC and TJ Pitre. → The full setup in nine clear steps. → Nine real workflows you can test this week: Accessibility audits. Ticket validation before handoff. Token migration. Multi platform component handoff. Component documentation generation and more. Our roles are evolving. We are moving closer to that old Webmaster model where design, systems, structure, and technology connect. The designer who understands systems and automation will have leverage. This toolkit is my contribution to that transition. Consume it. Test it. Break things. Ask questions. Explore your own use cases. These are exciting times, and we move faster when we learn together. If you build something interesting with it, share it. Concrete examples help the whole community level up.

I redesigned my entire UX/UI process with AI. It’s not about “use ChatGPT to brainstorm.” I mean, I rebuilt the whole pipeline. From product idea to prototype. What used to take months? Now gets done in days. Here’s what it looks like step-by-step: 1. Instant User Flows I drop rough product ideas into ChatGPT. (It's not the public one; it's a custom GPT trained on how I think.) It gives me: - Sitemap - User journey - Logic flows All in less time than it takes to make coffee. 2. Wireframes Without Drawing I stopped sketching. I describe the layout in plain English, and Magician does the rest. "Hero. CTA. Testimonials." Boom. Wireframe. No more dragging boxes like it’s 2015. 3. AI-Built Design System Spacing? Typography? Button styles? I just describe the vibe. Tools like Relume and Uizard take that and build me a full design system. This used to take WEEKS. Now it’s done before lunch. 4. Smarter Figma Time Now everything moves to Figma. But I don’t waste time pixel-pushing. AI plugins handle: - spacing - responsiveness - and accessibility. I just make the ideas click. 5. Prototyping = Auto-On Final step? Auto-connect flows with Figma’s AI tools. Clickable. Shareable. Client-ready. Dev-approved. No extra buttons. No guesswork. Here’s the real punchline: AI didn’t replace my work. It replaced the boring parts, so I can focus on design thinking. It’s not about working faster. It’s about designing smarter. We’re not in 2015 anymore. Let’s build like it’s 2030. What part of your UX workflow do you still do manually? Curious to hear.

This is the kind of use case that makes me smile. Someone just used Figma Console MCP to generate a fully token-aligned slide deck. Not a product. Not a marketing site. Not a component library refactor. Slides. They imported a random Figma template. It had its own colors, fonts, and styles. Total mismatch with their design system. So instead of manually re-styling 40+ slides… They: → Asked Figma Console MCP to map the template styles to their foundation tokens → Generated slide components with variants for every layout → Connected everything back to their variables → Automated the whole thing Now their slide deck is literally wired into their design system. Change a color in foundations → the entire deck updates. That’s wildly creative! I love this because it has nothing to do with “design-to-code/code-to-design” hype or building some flashy product demo. It’s someone looking at a boring, repetitive workflow and saying, “There has to be a smarter way.” And then building it. This is what I enjoy most about putting tools like this into the world. Not the expected use cases. The unexpected ones. If you want to see the walkthrough, it’s worth a watch: https://lnkd.in/e_Y3nc3k

Most studios grow by hiring. But the future of design businesses won’t be built on headcount, it will be built on systems. AI doesn’t replace designers. It replaces the repetitive tasks that stop designers from thinking clearly and moving fast. At PROHODOS, we’ve built a workflow where AI handles the execution layer, and we stay focused on strategy, clarity, and product decisions that matter. Here’s the system we use: 1. Meeting → Insight Pipeline Fireflies records client calls. Claude AI turns the transcript into a structured brief. We add direction and make the key decisions. Result: 45-minute meeting → 5-minute review (90% saved) 2. Wireframe → Website Flow Relume generates wireframes from the sitemap. Figma Make structures layouts. Claude drafts first-pass copy. We refine architecture, hierarchy, and narrative. Result: First draft in 30 minutes vs. 8 hours (16× faster) 3. Copywriting Engine Claude creates multiple headline, value prop, and CTA options. We choose, tighten, and align them with the product’s story. Result: Better options in minutes vs. hours (12× faster) 4. Website Visual Engine Midjourney + Nano Banana create branded imagery and conceptual visuals. We adjust direction and maintain consistency across the site. Result: Website-ready visuals in 15 minutes vs. 3 hours (12× faster) 5. Graphic Design Engine Claude generates visual specs. Figma Make builds diagrams, frameworks, and infographics, including the one in this post. Impact: 5 minutes instead of 3 hours (36× faster) What still requires human expertise →Strategic thinking →Business context →Product clarity →Client relationships That’s the model we’ve built at PROHODOS: Manual craft where it matters. Automation where it doesn’t. #DesignSystems #AIAutomation  #ProductDesign #DesignOps

How I Automated Image Creation Using Google Sheets + AI Most teams don’t struggle with ideas. They struggle with execution. Designing images. Writing prompts. Uploading files. Tracking links. Updating sheets. That’s where time disappears. In this video, I walk through a fully automated workflow that removes all of those manual steps. Here’s what this system does: • Reads image ideas directly from a Google Sheet • Runs on a schedule without human input • Filters rows to avoid duplicates or wasted work • Cleans and converts each idea into a clear prompt • Automatically generates images using Google Gemini • Uploads images to Google Drive • Writes the image link back into the same sheet • Keeps ideas, images, links, and status tracked in one place Everything runs quietly in the background. I’m Adnan Ghaffar. I’ve been building software for over a decade and helping businesses automate workflows since 2019. My focus is simple: find the step that slows everything down, fix it once, and let the system run smoothly after that. If your team feels busy but nothing moves fast, this kind of setup can completely change how work gets done. Take a look and see if it fits your workflow. Adnan Ghaffar CEO, CodeAutomation, Chicago, IL, USA http://codeautomation.ai/ #WorkflowAutomation #GoogleSheetsAutomation #AIAutomation #BusinessAutomation #NoCodeAutomation #AIWorkflows #ProcessAutomation #ProductivitySystems #AutomationTools #AdnanGhaffar #adnan

Figma dropped something yesterday that every lean product team needs to see. Claude Code to Figma is live and we're making it our default UI workflow at Fibr. Here's exactly how it works in practice. Prompt Claude Desktop with what you want to build. When the preview looks good, send it straight to Figma with MCP installed. Tweak spacing, colors and variants on the canvas. Describe changes back in Claude or paste a frame link and regenerate. Repeat until it's right. That's the whole loop. No design handoff meeting. No repo cloning. No back and forth over screenshots. The reason this matters for small teams specifically is that the biggest design quality gap was never talent, it was process overhead. Big teams could afford dedicated design reviews, async annotation tools, structured handoffs. Lean teams just moved fast and hoped for the best. This closes that gap. Everyone reacts to the same artifact at the same fidelity. Designers, PMs, engineers, all in one canvas without anyone context switching into the codebase. Code to Canvas to Code. One continuous loop. At Fibr AI we are a small team shipping fast. The teams that set this workflow up now will have a compounding advantage over everyone still treating design and engineering as sequential steps. Worth an hour this week to get MCP installed and try it.

Building in design AI is one of the most complex, interesting and rewarding challenges. And today, after years of work behind the scenes, we finally get to share a vision we’ve been chasing since before it was possible. We imagined a future where you'd just describe what you wanted to make — and it would appear. It would be real, editable and yours. Today, that imagined future is here. Canva AI 2.0 is the most significant shift since we brought design to the browser. Our AI products have already been used 27 billion times, tripling in the last 12 months alone. Here’s what we just shipped: 🗣️ Conversational Design — Imagination is now the starting point. Describe an idea and Canva AI builds a fully editable design from scratch. 🤖 Agentic Orchestration — One prompt leads to a complete campaign. Tell it your goal and it figures out the rest. It selects the right tools, runs the workflow, and delivers a finished result across every format. 🧠 Living Memory — It learns from every design you make. Your brand, style, team preferences — all built into a persistent context that makes every output smarter than the last. 🎯 Object-Based Intelligence — Change one thing and only that thing changes. Swap a headline, update an image, adjust a font without touching anything else. 🔗 Connectors — Pull in live context from Slack, Gmail, Google Drive, Zoom, Notion, and Google Calendar with many more to come. Turn a client email into a pitch deck. Turn a Slack thread into a newsletter seamlessly. ⏰ Scheduled Tasks — Set it and forget it. Canva AI runs recurring workflows in the background even while you're offline with content ready for your review when you’re back online. 🔍 Web Research — Brief it on a topic and it gathers, structures, and drops research directly into your design. From market analysis to business proposals, it is ready to refine and share. 🎨 Brand Intelligence — Every design starts on-brand automatically. Connect your brand kit and Canva AI applies your fonts, colors, and style from the first pixel. 💿 Canva Code 2.0 — Describe any interactive experience and it builds it. Now with HTML importing, you can bring any AI-generated experience into Canva and edit it visually — no rebuilds needed. 📊 Sheets AI — Describe what you need and get a fully structured, beautifully designed spreadsheet populated with real data. Budget trackers, project timelines, research tables — done. ♾️ Template Remix — An infinite library of inspiration. Every template is now a starting point you can reshape into exactly what you need with a single prompt. Want to try it today? Ask Canva AI to “activate superpowers” and let us know what you like the most!

As mentioned in my previous post, over the last few months I’ve been experimenting with something I never thought I’d be doing as a designer: 🤖🎨💻 𝗧𝗿𝘆𝗶𝗻𝗴 𝘁𝗼 𝗯𝘂𝗶𝗹𝗱 𝗮 𝗿𝗲𝗮𝗹, 𝗲𝗻𝗱-𝘁𝗼-𝗲𝗻𝗱 𝗱𝗲𝘀𝗶𝗴𝗻 → 𝗔𝗜 → 𝗰𝗼𝗱𝗲 𝘄𝗼𝗿𝗸𝗳𝗹𝗼𝘄. 🤖🎨💻 Not in a theoretical “AI might replace frontend someday” way.   I mean, actually sitting down with Claude Code, Figma MCP, VS Code, ChatGPT — and seeing how far I could push them to turn real designs into working components. Here’s what surprised me pretty quickly: ⚡ 𝗔𝗜 𝗶𝘀𝗻’𝘁 𝗺𝗮𝗴𝗶𝗰, 𝗯𝘂𝘁 𝗶𝘁 𝗶𝘀 𝗮 𝗺𝘂𝗹𝘁𝗶𝗽𝗹𝗶𝗲𝗿. ⚡ It won’t read your mind.   It won’t give you perfect components from messy designs.   And it definitely won’t replace engineers anytime soon. But if you understand your workflow and the building blocks underneath, it can help you move from idea → prototype → working code faster than anything I’ve used in my career. A few things I’ve learned: 📌 𝗗𝗲𝘀𝗶𝗴𝗻 𝗳𝗶𝗱𝗲𝗹𝗶𝘁𝘆 𝗺𝗮𝘁𝘁𝗲𝗿𝘀.   If your designs aren’t clear, AI will guess — and usually guess wrong.   Structure still beats vibes. 📌 𝗔𝗜 𝘄𝗼𝗿𝗸𝗳𝗹𝗼𝘄𝘀 𝗿𝗲𝗾𝘂𝗶𝗿𝗲 𝘀𝘆𝘀𝘁𝗲𝗺𝘀.   Tokens, naming, constraints… AI thrives on clarity. 📌 𝗖𝗹𝗮𝘂𝗱𝗲 𝗖𝗼𝗱𝗲 + 𝗙𝗶𝗴𝗺𝗮 𝗠𝗖𝗣 𝗳𝗲𝗲𝗹𝘀 𝗹𝗶𝗸𝗲 𝘀𝗼𝗿𝗰𝗲𝗿𝘆 — 𝘂𝗻𝘁𝗶𝗹 𝗶𝘁 𝗶𝘀𝗻’𝘁.   When it works, it’s incredible. When it breaks, you suddenly learn more about OAuth and MCP servers than you ever expected. (Still worth it.) 📌 𝗬𝗼𝘂 𝗻𝗲𝗲𝗱 𝗹𝗶𝗴𝗵𝘁 𝗮𝗿𝗰𝗵𝗶𝘁𝗲𝗰𝘁𝘂𝗿𝗮𝗹 𝗹𝗶𝘁𝗲𝗿𝗮𝗰𝘆.   Not engineer-level depth — just enough to understand what you’re asking AI to generate. 📌 𝗧𝗵𝗲 𝗿𝗲𝗮𝗹 𝗺𝗮𝗴𝗶𝗰 𝗶𝘀 𝗶𝗻 𝘁𝗵𝗲 𝗹𝗼𝗼𝗽.   Design → generate → run → tweak → regenerate.   It teaches you more about your design decisions than static handoff ever will. --- Honestly, this whole experience changed how I see the role of designers. We’re no longer just shipping screens.   We’re shaping workflows.   We’re guiding systems.   We’re using AI not only to design, but to 𝗲𝘅𝗲𝗰𝘂𝘁𝗲 and turn intent into something functional. ⚙️ 𝗧𝗵𝗶𝘀 𝗶𝘀𝗻’𝘁 𝗮𝗯𝗼𝘂𝘁 𝗯𝗲𝗰𝗼𝗺𝗶𝗻𝗴 𝗮𝗻 𝗲𝗻𝗴𝗶𝗻𝗲𝗲𝗿. 𝗜𝘁’𝘀 𝗮𝗯𝗼𝘂𝘁 𝗯𝗲𝗰𝗼𝗺𝗶𝗻𝗴 𝗮 𝗯𝗲𝘁𝘁𝗲𝗿 𝗯𝘂𝗶𝗹𝗱𝗲𝗿. In my next post, I’ll share how I’ve been using multiple AI tools together with ChatGPT for architectural thinking and research and Claude Code for development. The future of AI work feels more like 𝗼𝗿𝗰𝗵𝗲𝘀𝘁𝗿𝗮𝘁𝗶𝗼𝗻 now. If you’re a designer trying to stay relevant in a shifting market, I hope this gives you a bit of encouragement:   🧠✨ 𝗬𝗼𝘂 𝗱𝗼𝗻’𝘁 𝗻𝗲𝗲𝗱 𝗽𝗲𝗿𝗳𝗲𝗰𝘁𝗶𝗼𝗻. 𝗬𝗼𝘂 𝗷𝘂𝘀𝘁 𝗻𝗲𝗲𝗱 𝗰𝘂𝗿𝗶𝗼𝘀𝗶𝘁𝘆. 🧠✨   #AI #design #productdesign #futureofwork #buildinpublic #opentowork

Freepik Spaces Lists let you design, automate, and scale AI-powered creative workflows in one place, turning a single idea into dozens of outputs without jumping between tools. In this advanced Freepik Spaces tutorial, we walk you through how to build end-to-end workflows that generate logos, mockups, image variations, and videos automatically. What you’ll learn in this video: 👉 How Freepik Spaces workflows and nodes work together 👉 Turn one input into multiple variants using Lists 👉 Use assistant nodes to auto-improve prompts with built-in LLMs 👉 Generate industry-aware mockups without manual prompting 👉 Create image variations, storyboards, and videos in bulk 👉 Build scalable systems for agencies, freelancers, and creators This is perfect for designers and creators who want to move beyond manual execution and start building high-leverage AI workflows that save time, cut costs, and scale output effortlessly. You'll find the full video link in the comments.

This might be the most slept-on way to use AI creative tools. It’s called Spaces by Freepik. Spaces is a node based canvas. So you can connect text, image, and video nodes together to build a visual AI workflow. For example, let’s say I wanna make the perfect image of Michael Jordan dunking over a Lamborghini. Before, I’d have to type a text prompt and manually generate 10 different versions, while tweaking the style description every time. But Spaces lets me set up a workflow with 10 different branches that automatically runs this process for me. You can see, I click once, and automatically have 10 different image outputs from all the best image models. When you rig up multiple of these chains together, you basically create an entirely automated system for generating visuals. All we have to do is drop in a single line of text from our script, and this workflow spits out 5 AI generated videos, in our desired style, that are all ready to go in just a few minutes. This type of workflow was super difficult to build before, but with Spaces it’s much much easier. And the beauty of these workflows is that once you build them, you can share a link so that any other users, like your editors, can redownload the entire workflow on their side, in a single click. I think these visual canvases are going to be the future of how people use AI creative tools. Because they make the process feel less like work and more like a video game. If you wanna try this out, check out Spaces on Freepik. Follow Kane K. for more AI creative tips. #ai #artificialintelligence #tech #technology #freepikpartner #design #marketing #aidesign #animation #motiongraphics #productmarketing