I'm building a small website called "Loading..." - (work in progress - making with Cursor)
Shout out: This was inspired by @joshpuckett's - Interface Craft interfacecraft.dev/ . His (amazing) work feels very soulful and personal.
The interaction always belongs to the world itself, so a VHS card rewinds, a cassette clicks, a terminal waits for exit and so on. At its heart, Loading... is about the space between cold systems and warm human feeling.
I have a lot of cards (and worlds) to go, but here are 2 cards I completed.
PS: The sounds here of course, were added during editing. But the sounds in the website closely mimic it. Part of the website's experience are the sounds!
I’ve been sharing how I’m working on Tenet UI Studio over the last few weeks.
ChatGPT as a persistent thinking space and Google AI studio for quick prototypes to ground decisions in behaviour.
fourzerothree.in/p/designing…
I finally built (vibe coded) my portfolio website!
-----------------------------------------------------
For the longest time, my newsletter doubled as my “portfolio.” But I thought why not
- vibe code a portfolio website
- In a full 90s PC game aesthetic
Honestly I was a little skeptical I could pull it off, but with some amount of iteration (and patience), I finally shipped it.
Its not perfect, but I am genuinely happy with the output.
If you’d like to take a peek: sanketh-s-retro-portfolio-v1…
Designers today are experimenting with AI workflows. You see people talk about “prompt → riff → refine” loops. But the truth is: no one has a perfect workflow yet. 👇
- User flows IA in ChatGPT → bring them to life in FigJam
- UI layout (text based) in ChatGPT
- Use v0 to bring these layouts to life
- Keep “riffing” and forking in v0
- Debug with ChatGPT
- Back to v0
- Export to Figma using the “HTML to Design” (Figma) plugin 👇
1. At work, I was part of a team tasked with an open-ended but challenging goal: “experiment with AI and figure out how it could actually make our design process faster and more efficient.” 👇
fourzerothree.in/p/context-e…
3. Long conversations meant hitting context window limits. The challenge, I then realized was carrying over context across conversations. If I wanted GPT to act as a “copilot”, I couldn’t just prompt it once and hope for the best. 👇
So, while prompts get all the attention, it’s actually context engineering that makes or breaks an AI-augmented workflow. Context, by far, is the only way you’d get consistent, high-quality outputs across the full design process.
fourzerothree.in/p/context-e…#aidesign#uxdesign