this client was insane said in 2 months needs:... - total rebrand - packaging - fully loaded website (custom cart + checkout + PDP) - cart/checkout upsells - smart bundles related to product - 152 product renders - 3D animations all designed in Figma and Cinema4d, dev'd w Claudeshow more

FashionNova dominates fast fashion. But their funnel? It’s a... masterclass in impulse-driven conversion. We just broke it down: ✅ Paid Ads ✅ Product Page ✅ Cart + Checkout UX ✅ CRO strategies This is the engine behind one of the fastest-growing fashion brands in the world. All mapped into 1 simple system. Want the full funnel teardown? Like + comment "CRO" and I'll DM it to you. Retweet for priority access. (MUST BE FOLLOWING ME so I can DM it to you!)show more

Fable 5 + Goose Ads is insane – literally... a full ad-creative team right in Claude Code. 1. Install the skill: npx gooseworks install --all npx gooseworks login 2. Ask Claude Fable to make ads for your brand. /goose-ads create ads for my brand . Fable 5 pulls the ads already winning in your space and rebuilds them on-brand – your product, your palette, your copy – a whole batch, ready to test. It can ship a month of creative testing in a single prompt. This is also possible with Opus and Sonnet, but Fable's brand research is next level. Link below.show more

Bro another winning digital product someone is printing money... in the mental health niche found a page called "Healing with Nora" 54 active ads right now, been running since september. 7 months straight. 1600 ads total. 100% confirmed winner. the product? 200+ therapy bundle. worksheets, trauma tools, self-esteem guides, ADHD support. the offer? they sell it for completely free. $0.00 then checkout hits you with 6 upsells at $1.97 each, a $4.97 "processing fee" they call "support our mission" and somehow you end up with a $23 subtotal on a FREE digital product hahhaha same trick i keep telling you guys about free offer up front, stack everything on the backend. the ads? completely faceless. ai clips and some podcasts mixed with product walkthroughs and voiceovers. the store? they just run a basic shopify store. no sales page, no funnel. and that is exactly where the opportunity is. if i was jumping into this niche i would build a proper sales page funnel, print the digital ebook and film it , and run way better creatives than what they are doing right now. guys i keep sharing winning products here in x. jump on them and just do it better. and i will share more here on x about digital product adsshow more

I built a clone of the Yeezy store with... Next.js. This was a fun challenge — the site has some smooth animations and feels very fast. But it was bothering me that I couldn't use the browser back button. Can we do better? So I rebuilt the site with v0 and Motion. Here's how it works: 1. When you click on a product, Motion is able to animate the original position of the product in the grid, to the zoomed in product detail page. 2. During this transition, we also shallow update the URL with the `/p/slug` route for the page. 3. If you press the back button in the navbar, or use the browser back button, or press escape — all options will take you back to the main product listing page. 4. If you reload the page while looking at a product, or someone sends you a link to a specific product, it still works! This is the best parts of a SPA and MPA mixed together. In the future, I can make this even better with View Transitions (I wasn't able to get the product animation just right, but if you can I'd love to see it!). I also took some creative liberties from the original design. The whole 1/2/3 size thing, where you needed to click the "?" to see SM/MD/LG was strange, so I just went directly to those sizes. Similarly, I prefered the more traditional style sheet/modal with the background color change, versus the full screen takeover. If you wanted to actually hook this up to Shopify now, you can swap the cart implementation with Next.js Commerce, which has all the APIs you need + optimistic writes 🔥 Should I make a video walking through the code?show more

Gemini Omni + GPT Images 2 + Claude Code... is f*cking cracked i just built an AI animation ad generator that turns any product into a fully scripted AI 3D explainer video drop in your product photos and a one-line pitch. the system analyzes your brand, pitches you 4 proven ad concepts with hooks and shot lists, then renders the whole thing end-to-end. scripted, voiced, stitched, ready to post. if you're still paying editors $200+ per video or waiting days for revisions this replaces that entire workflow. here's how it works: > set up your brand kit with product photos and a one-line pitch > hit analyze and the AI pitches you 4 different proven ad concepts > pick one and hit generate the system then scripts every shot, renders each clip in parallel, adds voiceover, QC checks and stitches it into a finished vertical ad 3 minute setup and 4-12 min per ad. each 30 second ad costs under $3 in API credits which is cheaper than any editor and 10x faster. RT + reply "ANIMATION" and i'll send you the full app + setup guide (must follow so i can dm)show more

HE BUILT A $10,000-TIER ANIMATED SITE WITH CLAUDE CODE... - FOR THE COST OF A SUBSCRIPTION What's on screen isn't a landing page with a parallax background It's a fully interactive, scroll-driven site with real-time 3D rendered in the browser What's actually on the page: > 3D product models rotating and reacting to scroll in real time via WebGL > Smooth hover interactions and transitions - no hand-coded keyframes > Cinematic minimal aesthetic that got featured on Awwwards > Typography layering, editorial layouts, everything assembled in one session What it normally takes: > A 3D artist, a motion designer, and a frontend developer > Weeks of handoffs - modelling, exporting, wiring animations, layout, copy > Six separate systems integrated by hand That pipeline was the moat. It's what justified the invoice The price gap: > Studio build at this level: $5,000-10,000+ > Your cost: a Claude subscription Timeline: weeks of production -> a single session Full walkthrough in the article belowshow more

Claude + GPT Image 2 + Seedance + Meta... Ads MCP Just fired my $10k/month performance marketing agency. Here's the exact stack (and how it runs): Step 1: Research Hand Claude your product page, your competitors' pages, and your best ad angles. It spits out a full brand brief + competitor breakdown in minutes. No strategist. No $200/hour consultant. Step 2: Static ads in seconds Claude crafts image prompts from your brief. Drop those into GPT Image 2. You get scroll-stopping creative. Batched. On-brand. No Figma needed. Step 3: Video ads that convert Claude writes video prompts. Feed them into Seedance 2.0. UGC-style clips. AI actor formats. Product showcases. All generated. Zero filming. (Both GPT Image 2 + Seedance are live on HeyOz right now.) Step 4: Publish + optimize on autopilot Hook Claude into Meta Ads MCP. It pushes your creatives live, tracks performance, and keeps iterating. Your agency was billing you hourly for this exact thing. I documented the full workflow in a guide: prompts, setup, and the exact MCP config. Why this matters: Most brands are still bleeding money on slow, overpriced creative production. The ones who crack this in the next 90 days will own an unfair advantage. Don't be the brand that figures it out too late. Comment "REPLACE" and I'll DM it to you.show more

HIGGSFIELD + FABLE 5 BUILT A FULL CLIENT WEBSITE.... MY PART WAS 35 MINUTES. the old studio needed a designer, a dev, and someone for media. every hire ate the margin. now you personally touch exactly two stages - the models handle the heavy middle: → INTAKE (you · ~15 min) turn the client request into a tight spec: pages, brand, edge cases. judgment work - the part actually worth paying for. → DESIGN (Fable 5) brief in → design system out: layouts, components, responsive states. the week-in-Figma part, gone. → BUILD + MEDIA (in parallel) Claude Code writes the site - components, CSS, animations, CMS, deploy. Higgsfield MCP generates every visual - hero video, product shots, motion - from prompts, in the same chat. → QA + HANDOFF (you · ~20 min) review against the spec, deploy, notify. templated after your first few clients. two human stages, both fast. the slow, labor-heavy middle is the one you removed yourself from. you went from laborer to orchestrator. CONNECT HIGGSFIELD (MCP): add it as a custom connector in Claude Code: - mcp_servers: - higgsfield: - url: " one OAuth flow. Claude generates and pulls clips directly - no exporting by hand. THE MATH: → what you sell: a productized site + a monthly retainer → what it costs you to deliver: ~$750/month across every client → the margin isn't clever pricing - the cost of delivery fell through the floor while the value stayed the same. you pocket the spread. one operator, three tools, the whole studio. Follow me, reply "MCP" and I'll send you the full step-by-step playbook. full breakdown in the article 👇show more

PaladinAI is about to celebrate its first anniversary! This... incredible journey began with a bold vision: to be the first AI-powered bot specialized in Web3 security. Over the past 11 months, we’ve continually evolved, launching multiple versions and integrations. Together, we’ve achieved something extraordinary, our bot has scanned over 278,900 smart contracts for 31,560 unique users. But it was time to take things to the next level, to disrupt the norm. Months ago, we announced that we were working on a complete transformation of PaladinAI, expanding its reach and purpose. Today, we’re proud to reveal the first product of this evolution: the PaladinAI Assistant. This new tool will officially launch on December 2, 2024, and will be exclusively available to users holding a minimum of 50,000 $PALAI in their wallets. The PaladinAI Assistant is designed to dive deep into emerging narratives, track smart money movements, provide project recommendations, and deliver detailed insights into smart contracts. We’re committed to constant innovation with daily updates to keep the assistant fresh. To align with this transformation, we’ve completely reimagined PaladinAI’s brand identity, a new website, a fresh logo, updated colors, and a new artistic direction that reflect our elevated mission. Our full suite of tools will be unveiled gradually with the highest standards of excellence. We’re here to cover every need of Web3 users and redefine the experience from every angle. Thank you for being part of this journey. $PALAI #PaladinAIshow more

How a 22-year-old developer built a full 3D Jet... Ski racing game in just 40 minutes with zero manual coding He used Claude Opus 5 to generate physics, WebGL 3D graphics, HUD, and audio in a single prompt and turned single-prompt gamedev into a high-margin income stream. Costs: $423 He launched a single-prompt generation workflow that built the entire HTML5 project from scratch: Top layer: A Three.js and WebGL rendering pipeline dynamically creates 3D water physics, real-time wave dynamics, dynamic lighting, and jet ski fluid mechanics, all written autonomously inside one output file without external frameworks. Bottom layer: The Claude Opus 5 engine processed a massive 690-million-token context window to generate the complete gameplay logic, collision handling, dynamic sound generation, controls, and UI layout directly from a detailed initial system prompt. The trend of single-prompt 3D game creation is rapidly exploding across media and indie development. The author monetizes this tech stack through three main channels: 1. Viral Content & Media Systems: Short-form breakdown videos driving massive reach, monetized via promo placements, prompt-pack access, and private developer communities. 2. Rapid Hypercasual Prototyping: Testing 10+ WebGL mechanics per day, flipping fully functional browser games on itch io or CodeCanyon, and licensing prototypes directly to casual game portals. 3. Interactive WebGL Client Solutions: Delivering custom 3D promotional browser games and interactive brand experiences for clients in 48 hours instead of weeks. First month results: > WebGL games generated: 24 > Viral impressions generated: 3.8M+ > Total revenue across licensing & content: $21,400 The AI completely automated the core development lifecycle: Claude Opus 5 built the physics engine, rendered 3D graphics in WebGL, hooked up audio controllers, and generated interactive browser logic with zero manual line-by-line coding. Bookmark it and check article 👇show more

Veo 3.1 + n8n is insane 🤯 Google's new... model lets you generate studio-quality UGC videos that look like they cost $1k to produce. Copy my entire automated workflow below 👇 Most e-commerce brands & creative agencies are stuck choosing between: → Expensive creator networks ($500-$2k per video) → In-house production (weeks of coordination) → Stock footage that looks generic This n8n automation cuts through all of that. Here's the complete process: Step 1: Upload one product image to an n8n form Step 2: AI generates multiple UGC prompt variations automatically Step 3: Veo 3.1 renders each prompt into ultra-realistic video Step 4: System creates testimonials, unboxings, demos & lifestyle shots Step 5: All videos delivered to your workspace production-ready Total cost per video: $2-3 Total time: 15 minutes for 20+ videos Full commercial rights: yours forever This is the same workflow I've been using to generate 100+ UGC videos for e-comm brands. 100% automated. Want the complete n8n workflow? > Comment "VEO" > Like this post And I'll send it over (must be following so I can DM)show more

Everyone thought he was crazy for quitting his finance... job to sell ice cream. ​ Today, his novelty brand is available in 5,000+ stores, including Whole Foods, Erewhon, Bristol Farms, and The Fresh Market. ​ Here's how to do the same: ​ Step 1: Find the big idea ​ David's advice: Ask yourself what's missing? ​ - Look around at the way you live - Write down the products you love - Ask yourself: what would improve my quality of life? How can I make something that is 5-10x better than what exists? ​ For David, the missing thing was a way to satisfy his sweet tooth with portion controlled & snackable products like Nestle’s Dibs. As someone who was lactose-intolerant and had issues with dairy, there weren't many options. ​ And so, his dream snack, Dream Pops, was born! ​ Step 2. Make your prototype ​ David's advice: It doesn't have to be perfect. ​ In the early days, David was making samples in his mom's kitchen by hand. ​ One thing entrepreneurs get wrong? Trying to launch something perfect. If you're prototyping a food product, follow his advice: ​ - Create a delicious and unique product - Differentiate with your packaging & branding - Iterate in small format grocery stores and get feedback from your customers before launching into national accounts ​ Step 3. Put your product out there ​ David's advice: Get your product in as many hands as possible—any way you can. ​ Some ideas: - Host pop-ups with like-minded brands. Some brick and mortar brands were willing to pay $5K-$10K for a tailored “ice cream social”’ event with custom packaging. Revenue + awareness = free marketing. - Personally do samplings at local grocery stores to get real-time feedback from your customers. What do they love about the product? What do they hate? Those are your golden nuggets. ​ Step 4. Scale thoughtfully ​ David's advice: Don't get tempted by a big retailer with thousands of stores out the gate. ​ Getting into a huge retailer can kill your business if you aren’t ready. Don't chase revenue and door count. ​ Consider profitability, product quality, and overall risk. ​ Some retailers require you to pay "slotting" where you spend $50K to $150K+ to be on the shelf for eight months. ​ If you don't perform? You're out. ​ The risk is massive and can put you out of business before you have the opportunity to flourish. ​ Instead, find independent grocery stores and regional grocers with 3-10 locations and scale slowly – laser-focused on profitability and velocity. ​ Today, Dream Pops is a multi-million dollar brand sold at Whole Foods, Safeway Albertsons, Acme, Shaws, Erewhon, ShopRite, The Fresh Market, Fresh Thyme, GoPuff, CVS, Thrive Market, and many more. ​ This is your reminder to tune out all the noise, trust your intuition & keep building. ​ Want to get 1:1 advice from a CPG industry expert? You can now book David Greenfeld on Intro. ​ -- Did you enjoy this business breakdown? Follow @useintro to learn how the world's most successful entrepreneurs built $100M+ businesses.show more

🚨BREAKING: just dropped their Shopify integration yesterday. Now you... can build a complete Shopify store by talking to AI. This changes a lot of things for ecom. WHAT THIS MEANS: Lovable AI can now: • Build complete online stores from text prompts • Set up checkout and shopping cart automatically • Add products with AI-generated descriptions • Deploy live stores in minutes, not weeks They proved it by building their own merch store: lovable[.]dev/merch THE OLD ECOM SETUP: • Hire Shopify developer ($3K-$10K) • Wait 2-4 weeks for completion • Go through endless revision cycles • Pay for theme customizations • Debug technical issues • Launch after months of delays THE NEW REALITY: "Build me an online store for selling fitness equipment" → AI creates complete store in 10 minutes → Add products with descriptions → Click publish → Start selling immediately WHAT THIS MEANS FOR ECOM OWNERS: The Technical Barrier Just Disappeared: • No coding knowledge required • No designer needed for basic stores • No developer for functionality setup • No technical troubleshooting Speed Becomes the New Standard: • Test product ideas in hours, not months • Launch seasonal stores instantly • Pivot business models without rebuilding • A/B test different store concepts rapidly The Cost Structure Changes: • $29/month Shopify + AI tool vs. $10K+ development • Instant iterations vs. expensive revisions • Self-service setup vs. agency dependencies • Focus budget on marketing, not development THE REALITY: While you're waiting 6 weeks for your developer to finish your store… Your competitor just described their business idea to AI and launched 3 different store variations to test the market. THE OPPORTUNITY FOR BRANDS: • Test 10 product ideas instead of 1 • Launch seasonal campaigns instantly • Create niche stores for different audiences • Focus on products and marketing, not tech THE WINDOW IS CLOSING: Right now, most ecom owners don't know this exists. In 6 months, everyone will expect instant store creation. In 12 months, waiting weeks for a basic store will look amateur. As for me, I’ll say basic Shopify development just became commoditized. P.S. Thanks to Lovable, everyone will have a store soon. Your real edge isn't in JUST building it. It's in the operations, automations, and strategy that make it profitable.show more

2020 COLLECTION: 5 YEARS LATER - DAY3 OOF. at... this point it was pretty clear Duncan and Griffin at NiftyGateway that one person was winning every single auction. There were still 10 more to go on this Sunday... At the very last second of the final auction, a extremely last second bid cam in taking the total from about $350k to $777k, destroying the record for the most expensive NFT ever bought. you can see the disbelief in the video as we were sure the auction was over. but our boi tim.eth ⁙ illestrater came through at the last second clinching single W against the insane performance that Metakovan had built over the last two days winning every other auction. i was fully a pile of mush at this point, trying to wrap my head around how I had just sold $3.5M worth of this 'thing' that almost nobody I knew understood and I had only learned of less than 2 months earlier. but the real people who made this event possible are Metakovan and tim.eth ⁙ illestrater and i really don't think they get enough credit for the insane belief and conviction this took. their actions over this weekend literally changed the course of art history. little did i know that as fucking INSANE as this was... it was actually just the beginning. 😅show more

this effect is all over tiktok right now and... nobody's explaining how to actually do it properly... the 3d balloon character thing. where someone turns into a shiny inflatable version of themselves that still moves and talks. looks pretty smooth in feeds. the workflow is stupid simple once you see it. step 1: take any photo. drop it into an image gen tool (nano banana pro). prompt it with something like "make the person in the photo a plastic blow up balloon character with a shiny surface. keep the face details as 3d balloon details including the person in the background. don't change background" that's it for the image. don't overcomplicate the prompt. shorter = more consistent results. (learned this after wasting like 2 hours trying to get "perfect" prompts that kept giving me garbage) step 2: take that balloon image + your original video and drop both into kling motion control. prompt: "turn the motion and detailed mouth movement of the video to the setting of the image" that's literally it. kling maps the motion from the real video onto the balloon character. mouth moves. head turns. expressions transfer. the whole thing renders in a few minutes. the result looks like a $500 custom animation and costs you maybe $0.30 in kling credits. people are getting 500k+ views with these because the scroll-stop factor is insane. nobody expects to see a shiny inflatable version of someone giving a real speech or doing a product review. the play here is obvious btw. run this for client content (mix with the hook and real body, check the results yourself) or use it on your own faceless channels as a hook pattern before the algo catches up...show more

Sora 2 + n8n is absolutely insane 🤯 This... n8n automation generates entire UGC campaigns with the same AI creator across unlimited videos. All from one Airtable form. Perfect for DTC brands & agencies who need brand consistency in their AI ads without hiring real creators. Why this matters: Every AI video tool gives you a random person each time. You can't build multi-video campaigns because your "creator" changes in every clip. Sora 2 consistent characters solves this: Same AI creator → Different scenes → Unlimited videos The n8n workflow: → Fill out Airtable form once (select your character, describe scenes, choose quantity) → Claude AI generates professional Sora 2 prompts automatically → Sora 2 renders videos with your consistent character → Videos auto-upload to ImageKit CDN → Everything tracked in Airtable with shareable URLs No manual prompting. No file management. No different people in every video. What you can create: → 3-part testimonial series with the same person → Before/during/after transformation campaigns → Product tutorial sequences that feel cohesive → Entire ad creative libraries with your "brand ambassador" Track everything in Airtable: → Video status (queued → generating → complete) → Shareable URLs for each clip → Scene descriptions and prompts → Production-ready in 5-10 minutes Built 100% in n8n + Airtable. Want the complete template? > Comment "SORA" > Like this post And I'll send it over (must be following so I can DM)show more

Late Night NotebookLM release notes from a busy week!... 1. Slide Decks 🎉 - the freedom it gives you to turn anything into a story is incredible. Probably the first Nano Banana Pro fully dependent product. People are exploring fonts, styles, tips & tricks, but most of all stoke. so cool to see! 2. Infographics 🎉- capture the true essence of your sources in a creative but informative single image. You can use the Custom prompt to also make amazing Worksheets to accompany a lesson! Tobi talked about it. Maybe we should make question and answer sheets a clear option 3. Custom Style prompting for Visual Overviews - direct access to the model... 4. Thinking UX! this one was a while coming but we're gonna roll out a mvp and get moving (hoho). More informative soon. 5. Longer custom personas. You can now go up to 5k chars instead of the previous measly 500.... If you need more, LMK. 6. a bit "bold", but the "create notebook +" button at the top of every notebook. We'll probably collapse this into a smaller affordance, but wanted to get a quick workflow enhancer in there for people that don't know how to get to the homescreen. We'll do more on workflows. 7. Shout out to the TPUs which are definitely melting, and thank you all for the enthusiasm this week! More soon!show more

I Combined ChatGPT 5.5 Image-2 + Claude Fable 5…... And Built This FULL Game in JUST 8 Hours 😱 The World Has Officially Changed Forever Guys… I still can’t believe what I just pulled off. I took ChatGPT 5.5’s new Image-2 to generate every single visual characters, environments, UI, particles, everything and paired it with Claude Fable 5 for the entire codebase. The result? A complete, polished, fully playable game… finished in only 8 hours. No massive team. No months of crunch. No expensive asset packs. Image-2 created mind-blowing art assets on demand. Fable 5 turned those images into real, working code mechanics, physics, AI, animations, menus everything. This hybrid combo is straight-up sorcery. The world has truly changed. We are no longer waiting years for games to be made. One person + these two god-tier AIs just built something that used to require entire studios and huge budgets… in less than a single workday. This is the next level of human civilization. This is what creation looks like from now on. But here’s the crazy part: This free access ends June 22, 2026. After that, you’ll have to pay/subscribe to keep using it. If you’ve been waiting to see what the future of game dev actually looks like… THIS IS IT. Go try it right now before the paywall hits. Don’t sleep on this. Seriously. Drop in the comments: What game should I build next with this insane Image-2 + Fable 5 hybrid? Like if your mind is blown too 🔥 And tag a friend who NEEDS to see this before it’s gone. The future isn’t coming… It’s already here. And it’s free for one more day only. #Fable5 #ChatGPT55 #Image2 #AIHybrid #GameDevRevolutionshow more

Claude Design is f*cking cracked for landing pages 🤯... Find any competitor's e-com lander → feed it to Claude Design w/ your brand's design system → get back a fully rebuilt version in your brand, your copy, your design. All inside Claude Design. Perfect for DTC brands and agencies who are still paying freelancers to build advertorial pages from scratch. If you're finding landers that have been running on Meta for 6+ months and want to test the same structure for your brand —> Briefing a designer, waiting a week, getting back a flat mockup, giving notes, waiting again... Claude Design eliminates the entire loop: → Use Go Full Pag to screenshot the full competitor lander → Feed it to Claude Design with your design system → Prompt it to extract the exact section structure and rebuild it for your brand → It rewrites all copy, applies your fonts, colors, and layout → Iterate section by section — send a screenshot of what you want to fix, it fixes it → Drop in your product images and founder photos as you go No designer. No back-and-forth briefs. No starting from scratch. What you get: -> Full production-ready lander built around a proven structure that's already converting on Meta -> Live elements (countdown timers, animated sections) auto-generated -> Mobile and desktop versions you can refine with plain-English prompts -> A repeatable system — new competitor, new screenshots, same pipeline I put together a full playbook breaking down the exact process — the prompts, the section-by-section editing approach, and how to set this up for any competitor lander. Want it completely for free? > Like this post > Comment "CLONE" And I'll send it over (must be following so I can DM)show more

I learned this the hard way: do NOT use... SwiftUI if you want your app to look and feel amazing. At least when coding with AI. (sorry, Apple colleagues reading this 😅) I'm sharing my process vibe coding this calorie tracker. I get a lot of questions about the fluid transition in the video. Here's the whole story. Initially, Claude built the grid with SwiftUI. It was quick and easy, and looked good! But the transition to the day view was a boring navigation push/pop. No fun. I wanted something custom. I asked Claude to make it a fluid transition that remaps the food tiles from their source to destination positions. All hell broke loose. Claude tried a bunch of horrible things. Initially it used matched geometry effects, which worked OK but didn't lend themselves well to gesture-driven animations. So it resorted to SwiftUI preference keys + geometry readers to figure out the source and destination positions and calculate the interpolated position based on gesture progress, coordinating across grid and day views. But this meant it had to write a custom layout because it couldn't reposition tiles inside the native SwiftUI grid. And it had to do an awkward handoff between views, which always created ugly pops or jumps. And don't get me started on trying to put it on a bouncy spring, that only made the math 10x buggier. Fortunately, Claude Fable was smart enough to see that this was becoming a disaster (and discover most of the issues itself, in the simulator), so it pivoted away from SwiftUI. Opus might not be so wise, so you'll have to pay attention and intervene. Ultimately, it rewrote it in plain UIKit and everything turned out great. After that, we moved from 2D images to 3D assets, which introduced a new set of performance challenges and yet another rewrite to a single Metal layer, which is what you see below. I can write more about the 2D-to-3D saga if anyone's interested. If I were to do it again, I'd just say "Don't use SwiftUI" from the very first prompt, and save a few hours of headaches. SwiftUI can be amazing for a human iterating directly in code. But agents don't benefit from any of its advantages. Plus, agents have seen decades of UIKit training data, so they're great at writing it, and it's far more flexible. Here's hoping we see more agent-friendly iterations of SwiftUI in the future. Till then, I'm probably going to avoid it.show more