I recorded a 47-minute tutorial on how I use Opus 5.5 to create designs with gorgeous three.js scenes. I've been using Mobbin MCP to give my agents strong references, then letting Opus bring them together into a full landing page with multiple sections and a consistent design. Opus also created a super detailed brand guide, logo explorations, and some amazing ad creatives. Went way beyond my expectations. Live site: sunset.mengto.here.now Site made during the tutorial, with prompts: sunset-tutorial.mengto.here.…

Opus 5.5 sculpted every part of this ship in code, including the dragon, sails, and architecture. I can't say it has bad taste anymore. But it still needs steering, so I tried a new way of prompting. Live site: ship.mengto.here.now I asked Opus to score every part of the scene: the ship, water, landscapes, buildings, and their individual parts. Then I asked it to keep improving each part until it scored at least 8 out of 10, depending on my token and time budget. The key is to let it work as long as possible. The longer it works, the better it gets, until it reaches a point where I need to course correct. For me, Opus 5.5 reaches a level of detail and realism that no other model does.

Opus 5.5 is next level. I’m genuinely impressed by the three.js details. I generated a playable boat scene through Japanese landscapes with dynamic weather, day and night lighting, realistic textures and 3D characters. Live site: valley.mengto.here.now The water reflections, physics, scenery and architecture are insane. I could look at this all day.

I recorded a 41-minute tutorial on how I use Astra to create insane three.js websites in Codex. I've been using DiffUI to brainstorm UIs before moving into code. It's fast and cheap, generates multiple variants and lets me branch ideas, sections, logos, and other components. Then I use "Copy for agent" and bring everything into Codex where I add transparent PNG layers, animations, and three.js skills. Live sites: cardgame.mengto.here.now renaissance.mengto.here.now 3D skills: github.com/MengTo/Skills Get $20 in credits on DiffUI: diffui.ai/?invite=inv_6ca449…

I made a learning site for grades 1–7 with books for math, English, and science. My kids loved it. I used GPT-6 Astra with the Hyper3D Rodin MCP to create the 3D shelf souvenirs, candles, lamps, and pins. What stood out was the speed and quality. Rodin gave me richly detailed, high-quality, production-ready assets for the site. You can see the detail in the metalwork on the candelabra and lantern.

GPT-6 Astra is amazing for motion design, especially when you're presenting a UI or an app. I asked it to create a Codex promo using PerspectiveUI from my ThreeUI library. Then I kept refining it: a midnight-blue nebula, stars forming a 6, progressive blur, 3D camera moves, close-ups of typing, and text particles. I finished by cutting it to 30 seconds, six distinct scenes, and three prompts from our conversation. Live site: motion.mengto.here.now

This is a japanese house-tour landing page made in three.js with Fable 5.1 using the dream-loop skill. Live site: seijaku.mengto.here.now It's crazy how realistic it looks even though it's all code and under 1 MB (except images). You can tour every room, switch between seasons, see light rays through the house, and watch koi swim through realistic water. The secret sauce to ultra-realistic 3d in code is a loop like this: dream-loop gets the agent to generate a target image, compare the live 3d against it with a separate critic, and keep refining the result. Skill: github.com/achimala/dream-lo… Let me know if I should open-source the page.

I built a multiplayer Catan-inspired game entirely with Astra. It's free to play: settlecoast.com It's mobile-friendly and has narration, guides, customizations, multiple expansions and a game lobby where anyone can join, chat, and use voice chat. It took 4 days to build and hundreds of dollars in tokens. Becoming a game dev in 2026 wasn't on my bingo card, but here we are. AI has advanced so much that you can finally make the game you've always dreamed of, even without a team.

So I'm adding learning books for math, science, and languages using the same concept. It's still early, but my kids loved the stories! For some reason, they don't like doing homework on paper. Hopefully, creating a world around it and making it interactive and rewarding will work better. I'm trying different themes like Harry Potter and origami. A lot of people want to create their own, so I'll make a specific course about this and include the source code. For now, you can take my Fable 5.1 game development course and join my webinars: designcode.io/courses/build-…

I built StoryComet with Fable 5.1 in three days. 15 animated children's books in five languages, with translated voiceovers, covers and UI. storycomet.app Parents can track progress. Kids can take quizzes, collect pins and 3D souvenirs, and switch languages on the fly. Six books teach English, Spanish, French, Japanese or Chinese. My three-day workflow: - Day 1: prototype (and post on X) - Day 2: 9 more books, languages, progress, quizzes, pins and souvenirs - Day 3: polish, domain name, supabase, accounts, Stripe and optimization The first three books are 100% free so you can try the whole experience. Members unlocks the other 12 at early-bird pricing. The 3D models and tokens cost me hundreds of dollars, so your support means a lot.

I asked Astra to create a Catan game in three.js and it came out incredibly well. I played it, and the animations make it so much fun. The instructions and info cards make the game easy to learn. It even has AI players and trading. Astra used another game I had started building as a reference. The more games I build, the more skills and assets I have for the next one. It can remix the UI, 3D models, pages, and sounds instead of rebuilding everything. Now I want to see how many other board games I can make from this foundation.

It’s incredible how far you can push the UI with Fable 5.1. This is an interactive children's book that reads the story aloud, uses layered 3D illustrations, and animates every word. Fable created the concept and story from scratch based on a prompt. You can reuse the result as a template for more children's books, then have Fable voice, animate, and illustrate each one.

I tried to push Astra to create a Bloodborne-inspired game with console-quality graphics. For this one, I asked it to start with Unreal Engine-level graphics. In the end, it created a third-person three.js browser game with breathtaking detail. The key was to keep prompting for better textures, lighting, gameplay, and environmental details like the night sky, moonlight, rain, wet characters (which helped with reflections), and ultra-realistic water. Another thing that helped a ton was using 3D models from Meshy and Tripo3D for the character, weapons, and boss. I made a course showing how I prompt for game development: designcode.io/courses/build-…

Astra can create beautiful three.js UIs entirely in code. You don't need an assets library or MCP to create detailed 3D models. These are all code and are easy to customize for your agent. Give Astra a video, URL, or code reference, then ask it to keep comparing the result against the reference and fixing mistakes. Liquid Glass, shaders, motion design, procedural three.js models, and full environments. All from a few prompts. Some prompts I used: "Recreate this in a single HTML file with three.js. Keep comparing it against the reference and fix any differences." "Add Liquid Glass buttons. On hover, animate the lighting around the borders and make the background gradients move slightly with the pointer. Add subtle particles." "Improve the lighting, edges, and modeling. Give the keys more depth and verify the result against the real MacBook." Too many projects I could open-source. Let me know which one should I release.

Astra built this three.js game with gorgeous graphics, then recreated every scene in Blender and made the trailer too. It feels like a massive upgrade from Sol for 3D graphics and front-end design. The UI feels way more polished and less like AI slop. The rocks, trees, monuments, and characters are all procedural code, keeping the game under 2 MB before the image and music assets. The level of autonomy is unbelievable. It needed very little steering, though I still had to keep pushing it to work harder on the details. The UI icons, buttons, and ornaments were made as transparent PNGs with GPT Image 2.

Fable 5.1 one-shot this Dark Souls meets Diablo game. All code, 222 KB total, zero asset files. Every texture, model and sound effect is generated procedurally. The whole sfx system is 7 KB of Web Audio synthesis. It nailed mechanics I only named in text: stamina, dodge rolls, barbarian skills, and a punishing Souls-style boss. The soul pickups and death animations came out way smoother than I expected. What gets me is how much it infers from a few genre references, with no screenshots or video to go on. Reaching this level used to take dozens of prompts in Sol or Opus 5. Anyone with taste can now make really fun games in the browser.

I open-sourced the three.js site I built with Fable 5.1. I pushed the Kyoto theme further with tatami spaces, sliding doors, a 3D plastic menu, and a retro footer animation. It's surprising how much you can reshape when the whole experience is procedural code. Live site: mengto.github.io/sublevel-st… GitHub: github.com/MengTo/sublevel-s…

Okay, Fable 5.1 is crazy good at creating three.js sites. It’s faster, understands complex design instructions better, and recreates references with surgical precision. The English is also much easier to read. With this much power, it’s hard to settle for static sites, especially when so many AI-made sites look generic. A few things I noticed though: - It still creates generic AI illustrations if you don’t specify the images. - Difficult 3D subjects like people and dogs still become 3D slop unless I use Higgsfield 3D models. - You still have to push it to improve the textures, lighting, modeling, and small details. - Taste still matters. I had to fix overlapping elements, negative space, and scroll behavior. - I used canvasui.dev and threeui.com for the particle, VHS, and CRT effects. - Because it works faster, I go through tokens like there’s no tomorrow. Inspired by basement.studio. I can open-source this if anyone is interested.

Insane what you can create with three.js nowadays. I made a game-quality 3D experience in the browser with water ripples, smoke effects, a 3D paper menu, underwater UI, and a peeling footer. The whole thing is pure code and only 183 KB. Seriously, no loading screen needed. I combined canvasui.dev and threeui.com components with a few direct prompts: - Open the hamburger menu as a 3D paper overlay {threeui 3D paper} - Add a peel effect to the footer {canvasui peel} - When the cursor passes through the heading, turn the letters into smoke {canvasui liquid object} Inspired by the amazing unseen.co site. Let me know if I should open-source it.

I recorded a 21-min video to talk about how I'm changing my strategy for the AI era