Real-Time Design Feedback Systems

Some of you disagreed with my last post. Fair. Let's talk. Let me explain the topic a bit more and give you a deep dive into how I see the new process. The old way: Think → Research → Wireframe → Design → Spec → Hand off → Build → Test → Iterate Weeks. Sometimes months. Before anyone touches real code. The new way: 👉 Step 1: Start with a problem, not a doc. I don't need a full PRD. I need one thing. Example: "𝘗𝘦𝘰𝘱𝘭𝘦 𝘴𝘵𝘳𝘶𝘨𝘨𝘭𝘦 𝘵𝘰 𝘨𝘦𝘵 𝘩𝘰𝘯𝘦𝘴𝘵 𝘧𝘦𝘦𝘥𝘣𝘢𝘤𝘬 𝘰𝘯 𝘵𝘩𝘦𝘪𝘳 𝘱𝘰𝘳𝘵𝘧𝘰𝘭𝘪𝘰." That's it. That's the brief. 👉 Step 2: Build the ugliest working version. I open Lovable or Cursor and prompt my way to a prototype. Not a mockup. Not a Figma file. A real, clickable, functional thing. 30 minutes. Maybe an hour. 👉 Step 3: Use it. Don't refine it. Don't show it to anyone yet. Use it yourself like a real user would. Click every button. Try to break it. Feel where it's awkward. 👉 Step 4: Now design. This is where design skill actually matters. You're not guessing what the experience should feel like. You already know because you felt it. Now you fix what's broken, remove what's unnecessary, and polish what works. Maybe pivot or try other solutions. 👉 Step 5: Show it, don't spec it. Instead of a 20-page spec, I send a link. "Here, try this. What's confusing?" Real feedback on a real thing beats hypothetical feedback on a hypothetical thing every single time. 👉 Step 6: Iterate in minutes, not weeks. Here's where this workflow really pulls ahead. Someone says, "This flow is confusing." You don't update a Figma file, write a ticket, and wait for the next sprint. You open Cursor, fix it, and send a new link. Same conversation. Same day. The feedback loop goes from weeks to hours. Sometimes minutes. And each round gets sharper because you're iterating on something real. 3-4 rounds of this, and you have something more validated than most products get after months of traditional process. 👉 Step 7: Document what you built, not what you plan to build. Documentation becomes a record, not a prediction. It's accurate because the thing already exists. You can do it at the end or during the process. Why this works: You make decisions with information instead of assumptions. You eliminate 80% of the back-and-forth. You design from experience, not imagination. And you iterate at the speed of conversation, not the speed of sprints. Why it feels wrong at first: Because we were trained to think before we build. And thinking first felt responsible. But we did that because we couldn't build. Now we can. And I don't think it's about ignoring thinking. (𝘔𝘢𝘯𝘺 𝘰𝘧 𝘺𝘰𝘶 𝘢𝘤𝘤𝘶𝘴𝘦𝘥 𝘮𝘦 𝘰𝘧 𝘵𝘩𝘢𝘵) I believe it's about doing it at every step. Refining it based on real feedback. Insights you can get internally and from user testing. If you're still reading this, let me know what you think about it all. ✌️

💡One of the most fun shifts in my workflow lately: using Figma Make not just for rapid prototypes, but for design feedback loops. Instead of waiting until design review, we now ask Make: ✨ “What feels off about this layout?” ✨ “Does the copy flow match the intent?” ✨ “Where might a user struggle with accessibility?” It gives surprisingly actionable feedback — everything from hierarchy tweaks to color-contrast warnings. Not perfect, but often enough to spark better conversations before we pull in our design leads. Shoutout to my colleague Adam Batth 👏 who showed me how he’s been using this. It’s become a lightweight “design critique buddy” for the team and I — accelerating iteration and helping us get to stronger first drafts. As a CPO, this is exactly the kind of AI assist I want my teams leaning on: not replacing judgment, but elevating the baseline so human creativity can shine where it matters most. 👉 Anyone else experimenting with AI in their design review process? Would love to compare notes. #ProductAI

Google just shipped something that matters more than most people realize. Stitch (https://lnkd.in/gqMqinrg) now lets you talk to your design canvas. Not 'voice commands' — an actual conversation. You describe your goal, the agent critiques your work in real-time, and iterates live as you speak. I run a creative studio of 25-30 people. We live in Figma. The bottleneck is never the design — it's the iteration loop. Feedback session → notes → revisions → another round. That cycle eats days. What Stitch is doing isn't replacing designers. It's replacing the dead time between having an idea and seeing it. You direct. It builds. You react. It adjusts. The interface for designing is becoming conversational. Designers who learn to direct — not just execute — will move faster than anyone still pushing pixels manually. The question isn't whether AI replaces designers. It's whether you're learning to direct or still waiting to be told what to click.

Real-Time Aerodynamics? This Changes the Design Loop Completely. In traditional aerodynamic development, we all know the bottleneck: Geometry change → Meshing → Solver → Post-processing → Decision Hours to days… sometimes weeks. I explored Flexcompute's AutoInsight, and from a CFD + aerodynamics standpoint, it is a very interesting shift in how we approach design. AutoInsight is a simulation-trained inference model that learns from: - Historical CFD simulations, Wind tunnel data - Existing solver outputs (STAR-CCM+, Fluent, Flow360, etc.) It only takes 10-20 samples to train, and once trained it can: ✔ Predict aerodynamic quantities in real time ✔ Evaluate thousands of design variants instantly ✔ Provide feedback without running a full CFD simulation You tweak geometry and get instant drag, lift, flow insights. AutoInsight continuously learns from New CFD and test data, feeds back into the model. Predictions stay aligned with the current vehicle platform. We can plug in: - Existing CFD workflows - Different solvers - Cross-team datasets Try a lightweight version of Autoinsight with a pre-loaded DrivAer model: https://hubs.ly/Q0499tdz0 If you want to know more about it, you can read here: https://lnkd.in/gupAsjpA #mechanical #automotive #aerodynamics #machinelearning #turbulence #cfd