Design Workflow Optimization

How To Make Sure Teams Follow Design Guidelines? (https://lnkd.in/ewF4F4a8), an interesting case study by Linzi Berry on how the Lyft team enforces design quality by clearing time for designers, distributing ownership and pushing design QA early in the process. Key takeaways: 🚫 Often sprints are 100% packed with features, without time for QA. 🚫 Following guidelines takes time that designers often don’t have. 🚫 If guidelines are launch requirements, they aren’t prioritized early. 🚫 Some guidelines will always be missing in the design system. 🚫 Checklists often gather dust on the forgotten fringes of Sharepoint. ✅ Guidelines shouldn’t be recommendations but ways of working. ✅ People ignore guidelines created without their involvement. ✅ Checklists work if PMs protect designer’s time to do them. ✅ Guidelines must be embedded early in the design process. ✅ Best guidelines live within UI components themselves. ✅ Set guidelines as ready-to-use-templates and examples. ✅ Better sprints: 80% time for tasks, 20% for quality improvements. ✅ Sprinkle a bit of design QA over your product teams. I do see many teams trying to mandate design guidelines by blocking launch unless the design meets every single criteria on a 4-pages-long checklist. While this might work to ensure consistency, often it breaks the team’s spirit as guidelines feel heavily, rigorously enforced — often without exceptions. Instead, I try to make sure that designers have a strong sense of ownership over the guidelines that they personally shape and develop. These guidelines are seen as an evolving document that everybody is encourage to contribute to. Naturally everybody then shares the accountability for following the guidelines. Ultimately, the guidelines shouldn’t be a compliance check at the end of the process. The earlier guidelines are a part of design conversations, the more likely they are to be considered in early review sessions. And most importantly: make time and space for designers to set and follow the guidelines. They might not need stricter rules or mandates; they need time, trust and autonomy to make good decisions on their own. Useful resources: Why Design Systems Fail, by Karen VanHouten https://lnkd.in/eMYjfTzh How To Keep Your Design Documentation Alive, by Slava Shestopalov https://lnkd.in/gfvKgCwj What Is Design Debt and Why You Should Treat It Seriously, by Michal Mazur https://lnkd.in/dJq8ZG7U Paying Off Design Debt, by Alicja Suska https://lnkd.in/eGHtuWf5 How To Align Stakeholders and Designers With Guidelines, by Daniël de Wit https://lnkd.in/eJXY-akC #ux #design #documentation

Everyone's building AI agents, but few understand the Agentic frameworks that power them. These two distinct frameworks are the most used frameworks in 2025, and they aren't competitors but complementary approaches to agent development: 𝗻𝟴𝗻 (𝗩𝗶𝘀𝘂𝗮𝗹 𝗪𝗼𝗿𝗸𝗳𝗹𝗼𝘄 𝗔𝘂𝘁𝗼𝗺𝗮𝘁𝗶𝗼𝗻) - Creates visual connections between AI agents and business tools - Flow: Trigger → AI Agent → Tools/APIs → Action - Solves integration complexity and enables rapid deployment - Think of it as the visual orchestrator connecting AI to your entire tech stack 𝗟𝗮𝗻𝗴𝗚𝗿𝗮𝗽𝗵 (𝗚𝗿𝗮𝗽𝗵-𝗯𝗮𝘀𝗲𝗱 𝗔𝗴𝗲𝗻𝘁 𝗢𝗿𝗰𝗵𝗲𝘀𝘁𝗿𝗮𝘁𝗶𝗼𝗻) by LangChain - Enables stateful, cyclical agent workflows with precise control - Flow: State → Agents → Conditional Logic → State (cycles) - Solves complex reasoning and multi-step agent coordination - Think of it as the brain that manages sophisticated agent decision-making Beyond technicality, each framework has its core strengths. 𝗪𝗵𝗲𝗻 𝘁𝗼 𝘂𝘀𝗲 𝗻𝟴𝗻: - Integrating AI agents with existing business tools - Building customer support automation - Creating no-code AI workflows for teams - Needing quick deployment with 700+ integrations 𝗪𝗵𝗲𝗻 𝘁𝗼 𝘂𝘀𝗲 𝗟𝗮𝗻𝗴𝗚𝗿𝗮𝗽𝗵: - Building complex multi-agent reasoning systems - Creating enterprise-grade AI applications - Developing agents with cyclical workflows - Needing fine-grained state management Both frameworks are gaining significant traction: 𝗻𝟴𝗻 𝗘𝗰𝗼𝘀𝘆𝘀𝘁𝗲𝗺: - Visual workflow builder for non-developers - Self-hostable open-source option - Strong business automation community 𝗟𝗮𝗻𝗴𝗚𝗿𝗮𝗽𝗵 𝗘𝗰𝗼𝘀𝘆𝘀𝘁𝗲𝗺: - Full LangChain ecosystem integration - LangSmith observability and debugging - Advanced state persistence capabilities Top AI solutions integrate both n8n and LangGraph to maximize their potential. - Use n8n for visual orchestration and business tool integration - Use LangGraph for complex agent logic and state management - Think in layers: business automation AND sophisticated reasoning Over to you: What AI agent use case would you build - one that needs visual simplicity (n8n) or complex orchestration (LangGraph)?

AI isn't going to take ux designers' job, but it's changing what we do. Here's a new workflow that saves loads of time 👇 Take a hand-crafted ui designHave Figma Make recreate it in codePrompt it for a new ux design pattern or user flowImport that into Figma Design to make it pixel perfect Let's break it down: Take a ui design you already have in Figma. Head to Figma Make and paste in the frame then ask it to recreate it pixel perfect. The ai generated ui was was almost exact for me and it only took 15 seconds and fully functional. Now here's where the magic happens 🪄 Ask Make for a new flow and direct it to generate a button in the current ui design that will send to that flow. Be as specific as you can be wit user persona and how it fits into the product. It will generate some code that has the new flows in it within a few minutes. But I think that's where most designers stop. AI is not just a mood boarding tool though! See, you can publish that project, then go to the url and use the html.to.design plugin to capture the screen and import it back into Figma design--it even has Auto Layout so it's easy to work with. So in minutes, you have an interactive flow that you can edit and refine in Figma. This is a huge new workflow that I think product designers will be using daily in the near future and it's where I bet Figma Make is headed: generate new flows in seconds, refine those pixel by pixel before doing it all over again. Have you tried this workflow? #uiux #figmadesign #productdesigner

"Graphic design is dead" they said. AI just killed another industry. But after 18 months creating with AI tools daily? The opposite is true. Design isn't dying. It's evolving at warp speed. Yesterday's workflow: ☒ 3 hours sketching concepts ☒ 2 hours in Photoshop ☒ 1 hour tweaking colors ☒ Endless client revisions Today's AI-powered reality: ☑︎ 20 concepts in 20 seconds ☑︎ Instant color palettes ☑︎ One-click variations ☑︎ Real-time collaboration Here's what most people miss about AI design: AI handles output. You handle outcomes. Tools like Ideogram can generate 100 logos. ↳ But which one tells your brand story? Adobe Firefly creates perfect palettes. ↳ But which one triggers the right emotion? Figma AI builds responsive layouts. ↳ But which one guides user behavior? The gap between AI output and human insight? ↳ That's where designers thrive in 2025. My AI + Design workflow: 1 → Start with strategy What problem are we solving? AI can't answer this. You can. 2 → Generate variations fast Prompt: "Modern tech logo, blue accent, minimal" Get 20 options in seconds. 3 → Curate with taste Pick 3-5 that align with brand values. Your eye matters more than ever. 4 → Refine with precision Take AI drafts into your core tools. Add the human touches AI misses. 5 → Test with real users AI can't predict emotional response. Only humans understand humans. The tools crushing it right now: ✦ Ideogram – Logo concepts at light speed ✦ Midjourney – Brand visuals that pop ✦ Adobe Firefly – Integrated AI magic ✦ Canva Magic – Templates on steroids ✦ ChatGPT – Concept art instantly Lazy designers? Yes, they're toast. Strategic designers? They're 10x more valuable. Clients don't pay for pixels. They pay for: • Visual strategy • Brand coherence • Cultural context • Emotional impact AI can't hop on a discovery call. AI can't understand business goals. AI can't feel what resonates. The new designer toolkit isn't just Adobe anymore. Now it's: → Prompt engineering → AI tool mastery → Strategic thinking → Rapid iteration → Human insight The best designers won't fight AI. They'll ride it like a rocket. More output. Better strategy. Happier clients. The creative process just got an upgrade. And designers who embrace it will thrive. Graphic design isn't dead. It just learned to fly. Follow Charlie and Sana for more AI insights. ♻️ Repost if AI is changing how you create.

Prototyping is proven to have the potential to transform the speed, quality & impact of instructional design: can AI finally make prototyping a standard part of our process? For years, studies have shown that rapid prototyping in instructional design: 📊 Significantly shortens development cycles (Gerber & Carroll, 2012) 📊 Improves instructional quality (Daugherty et al., 2007) 📊 Enhances the quality of stakeholder collaboration (Nixon & Lee, 2001) Despite 20+ years of evidence & tools like Balsamiq and Figma, instructional design has remained stuck in waterfall workflows with little if any testing & iteration. The question I've been exploring this week is, will AI prototyping tools change this? In this week's blog post I share what I learned prototyping a recent training design using AI. TLDR: → AI tools like Claude, Vercel & Loveable are finally making rapid prototyping in instructional design practical, fast, and accessible—transforming abstract learning concepts into testable, shareable experiences in minutes → While AI isn’t a silver bullet (it struggles with complex visuals and multi-page journeys), it does a good job of generating realistic, evidence-based scenarios, assessments, and case studies—*provided* the designer brings strong instructional expertise and prompt precision → The future of L&D lies in combining deep pedagogical expertise with AI fluency. Check out my full guide to AI prototyping for L&D, complete with prompts you can try for yourself, using the link in comments. Happy innovating! Phil 👋

What has changed in the 10 years since PM legend Dan Olsen published "The Lean Product Playbook"? AI, of course. PMs need to cover entirely new workflows: 1. AI prototyping 2. AI-powered user research 3. A new era of design + UXR collaboration In today's episode, we give you a tactical masterclass - and cut through the BS hype. 🎬 Watch now: https://lnkd.in/ezqdZhDm Available everywhere: Spotify: https://lnkd.in/eyt7agKj Apple: https://lnkd.in/eAEVwr3u Newsletter (with transcript): https://lnkd.in/eEUvYBmm 🏆 Brought to you by: - WorkOS: Your app, enterprise ready - https://lnkd.in/eBTFz6cs - Jira Product Discovery: Plan with purpose, ship with confidence - https://lnkd.in/ecr-6F7w - The AI Evals Course for PMs & Engineers: https://lnkd.in/ek9ixfDR - You get $800 off with this link. - Product Faculty: Get $500 off the AI PM certification with code AAKASH25 - https://lnkd.in/ewuAKVUQ ✍️ Here were my favorite takeaways: 1. AI hasn't changed the fundamentals. You still need to understand customers, identify problems, and prioritize opportunities. AI can't tell you about your customers or validate market needs for you. 2. Prototyping is the biggest unlock. What used to take weeks (text → sketches → wireframes → Figma → code) now happens in minutes (text → live prototype). This is where AI truly transforms PM work. 3. Start with Lovable/Bolt, graduate to Cursor. Lovable and Bolt are perfect for quick prototyping without code. Cursor gives you more control and learning opportunities for serious AI PMs willing to touch code. 4. The design gap is closing. AI tools have moved every team up 1-2 levels in UX maturity. Teams without designers can now create professional prototypes, but still need humans for breakthrough innovation. 5. Match research method to uncertainty. New product/market = in-person research. Existing product usability = remote unmoderated. The more uncertain you are, the more human interaction you need. 6. Good usability ≠ product-market fit. Always ask "How likely are you to use this?" at the end. Dan learned this the hard way - zero complaints doesn't mean people want your product. 7. Protect discovery time. If your PM-to-dev ratio is above 1:8, you're probably a Jira jockey. Use Dan's 4 D's: Discover → Define → Design → Develop. Spend meaningful time in all four. 8. Collaborate, don't replace designers. Be upfront: "This prototype is directional, not pixel-perfect." Use AI for quick validation, bring designers in for differentiated experiences and innovation. Check out the episode for all the details!

One of the most frustrating parts of early-stage design? You spend more time managing tools than testing ideas. I’d have SketchUp open for massing, GIS for overlays, and Excel for calculations - all running at once. It was clunky, slow, and completely broke my design flow. Recently, I tried Giraffe Technology on a project, and it turned out to be one of the most useful upgrades to my workflow. 🚀 I tested three different design options in one sitting. No switching tools. No reformatting. No waiting. Here’s what stood out: ✅ Instant site analysis with contextual overlays ✅ Real-time solar radiation and shadow studies ✅ Rapid conceptual designs with built-in flexibility ✅ Live yield and area metrics ✅ Export-ready reports ✅ Seamless collaboration with team members My personal favorites? 👉 The Site Analysis Annotations : it pulled together zoning, setbacks, and overlays in one neat layer. 👉 And the Solar Radiation Tool - gave me intuitive, visual insights that usually take hours to compile. If you’re working on anything that involves early-stage planning or site strategy, Giraffe Technology is worth exploring. ✨ Watch the tutorial attached to see how I used it.

GenCAD - Turning Images into Editable 3D Designs Creating CAD models is still slow, manual, and often frustrating - especially when dealing with complex geometries. That’s why a team at MIT developed GenCAD, a new AI-powered system that generates parametric, editable CAD models directly from images. 👉 Instead of working with meshes or point clouds (which are hard to edit), GenCAD focuses on real-world engineering needs: - Modifiability - Manufacturability - Cross-modal generation (image → CAD) 🔍 How it works: GenCAD combines: - Autoregressive transformers (to model CAD command sequences) - Contrastive learning (to align images with CAD representations) - Latent diffusion (for high-quality generation) 📄 Paper: https://lnkd.in/eahBwEfC 🔗 Website: https://gencad.github.io/ 💻 Code: https://lnkd.in/eJgrNBqs

Happy Friday! This week in #learnwithmz, let’s explore how AI is transforming UX and Product Design: From prototyping to research to testing. Top AI Design Tools - Uizard Turn sketches or text into wireframes https://uizard.io - Stitch (previously Galileo AI acquired by Google) Generate polished UI layouts, export to Figma https://lnkd.in/giqThC-Y https://www.usegalileo.ai - Figma AI First Draft, Rename Layers, Smart Layout https://lnkd.in/gJVVHwc4 Magician for Figma https://lnkd.in/gNFVaV82 - Penpot (recent favorite) AI suggestions for layouts/components https://penpot.app Visual Design & Assets - Midjourney Generate moodboards and visuals https://www.midjourney.com - Adobe Firefly Generative fill and variations inside Creative Cloud https://lnkd.in/gtcpuCCR - Canva AI Visualize ideas, generate compelling copy, and turn your thoughts into stunning, fully editable designs https://lnkd.in/gsd5wi7n Takeaways for PMs & Designers - AI really shines at the grunt work In my own workflows, the biggest win has been cutting out repetitive tasks renaming, generating placeholder copy, auto-cleaning designs. It’s not glamorous, but it buys you back hours every week. - Speed is a gift, but refinement is non-negotiable AI can get you a “good enough” starting point in seconds. But the best outcomes still come from layering human judgment making sure the design aligns with your system, brand, and real user needs. - We’re seeing deeper integration into core tools Figma, Adobe, Notion… AI isn’t an add-on anymore, it’s inside the workflows we already use. That makes adoption easier but also means teams should stay intentional about how and when to lean on it. - The open-source and no-code ecosystem is catching up fast I’ve been impressed by tools like Penpot with options like Self-host . They make AI design assistance accessible beyond big enterprises so smaller teams and startups can experiment without huge budgets. How are you using AI in your product design workflow? Which tool has surprised you the most? #AI #ProductDesign #UX #Prototyping #AIDesign #learnwithmz PS. the video was created with Google Veo with one line prompt in 2 minutes (next week's post on video generation)

I built an automated AI game design team with multi-agents 🤯 That helps you design game concepts from start to finish. Each AI agent has a specific role: 1. Story Agent  ↳ Creates compelling narratives and characters ↳ It builds entire worlds and storylines automatically 2. Gameplay Agent  ↳ Designs core mechanics ↳ It balances fun and challenge perfectly 3. Visual Agent  ↳ Handles all art direction ↳ From UI design to character aesthetics 4. Tech Agent  ↳ Plans the technical architecture ↳ It knows exactly what tools to use Led by a Task Agent that coordinates everything: ↳ Ensures all ideas work together  ↳ Manages the creative flow  ↳ Keeps the vision cohesive Think of it like a real game studio: The Task Agent is your project lead, Making sure everyone's ideas align with the vision. When the Story Agent pitches an epic narrative, The Task Agent checks if it fits the gameplay goals. When the Tech Agent suggests an engine, The Task Agent ensures it supports the art direction. It's like having a virtual game design director. Just input your requirements: → Game type → Target audience → Art style → Technical constraints And watch as the Task Agent orchestrates the design process. This isn't about replacing game designers. It's about enhancing the creative process. Small studios can explore ideas faster. Independent developers can validate concepts. Students can learn game design principles. The future of game design is collaborative. Want to try it yourself? Link to the tutorial and GitHub repo in the comments. P.S. I create these tutorials and opensource them for free. Your 👍 like and ♻️ repost helps keep me going. Don't forget to follow me Shubham Saboo for daily tips and tutorials on LLMs, RAG and AI Agents.