@CircuitStream Honoured to have my Augmented Reality project final "Dewi the Desktop Companion" featured and to be acknowledged by @CircuitStream as an XR Designer Alumni.
To hang out with Dewi❤️, tap the link on your phone or tablet.
https://t.co/RBt98bU0je
Launching today: Claude can now create branded designs at scale.
Add the Moda MCP to generate full campaigns with ads, social posts, flyers, decks, and more.
All in a fully editable canvas with layers you can control.
Claude plans it. Moda designs it 👇
AI helped me prepare for Google I/O
Google I/O happened this week, and I used LobeHub to help prepare for it: https://t.co/Ren3YtfWKw
What I found is that LobeHub feels less like another chatbot and more like an AI workspace.
I started with a simple prompt:
“Get me ready for Google I/O. What should I expect this week? AI glasses? New robotics models? New agentic features?”
https://t.co/L6JhPU40Zi
(I will do the same for Apple's WWDC coming up in June).
It came back fast with a useful breakdown of what to watch, then helped me narrow in on the announcements and sessions I wanted to pay attention to.
Then I used Tasks to organize the work: research themes, session ideas, follow-ups, and notes I wanted to come back to after the event.
That part is important.
Most AI tools are good at answering one prompt. The harder part is managing what comes after: research, drafts, comparisons, follow-ups, and things you need to return to later.
LobeHub’s Tasks feature gives that work a place to live.
Instead of losing useful ideas inside a long chat history, I can keep the next steps organized and return to them with context.
For Google I/O, that meant I could keep track of what I wanted to research, which announcements looked important, and what follow-ups I wanted after the event.
That’s why LobeHub is interesting to me.
It is fast, flexible, and makes AI work feel more organized without needing to run something nerdier myself.
For many people, Hermes or OpenClaw can do similar things, but LobeHub is much easier to get started with.
Worthy of trying:https://t.co/zObEtlHG57 !
#LobeHub #ChiefAgentOperator #CAO
We believe our Labs experiments are at their best when they’re helping you create whatever you can imagine. We had some fun and put them to the test ourselves. Take a look at our Labs-inspired creations:
🧵1/5 A brand book that we created with @PomellibyGoogle.
3d gaussian splats + photogrammetry can work together beautifully – you don’t have to choose.
I’m using a drone capture for the hero asset. Google maps aerial photogrammetry for the world around it.
Had the pleasure of testing this out over the past week.
Very, very good model. Quality aesthetics, fast generations along with Moodboards and Style transfer.
Excited to explore more with Krea 2 ↓
It might not be sexy, but everyone uses authorization technology.
Here I sit with the founder/CEO, Jake Moshenko, of https://t.co/k4nTjG67Kw
This video teaches viewers why authorization—the system that determines who or what is allowed to do specific actions—is becoming one of the most critical infrastructure layers in the AI era.
While authorization has traditionally been a back-end enterprise concern, the rise of AI agents, agent swarms, autonomous tools, robotics, and eventually brain-computer interfaces makes it a frontline issue for both businesses and consumers.
The interview explains how authorization is evolving from a “boring IT function” into foundational infrastructure for the agentic future.
I need to be real with you all. I've gone back and forth about posting this but I can't stay quiet anymore.
My 4 year old son has a severe neurological condition. He's non-verbal and autistic and requires constant specialized care. That alone turned our family's life upside down. We found treatments that are extremely promising but they're just out of reach right now.
Then a few weeks ago, my 11 year old was diagnosed with Type 1 Diabetes.
What was already the hardest chapter of our lives just got significantly harder. We have a 4 year old with intensive daily needs, an 11 year old whose health now requires around the clock management, and a 1 year old. There aren't enough hours in the day and there aren't enough of us.
The art and design markets have been going through some serious changes and it's left us in the tightest financial spot we've ever been in. I'm not here for sympathy. I'm here because love and will do anything for them and have to exhaust every option I can.
If you or anyone you know needs creative work, I have 15+ years of experience across brand identity, creative direction, advertising, content, and AI art. I've worked with adidas, Nike, Google, Valentino, and many others. I'm ready to start immediately.
If you love the art, I have a small curation of unminted new works and my PIECES drop is live on SR. I'm also very open to commissions.
I've always tried to show up here with energy and positivity. Right now the most honest thing I feel I can do is show up with the truth instead.
I'm going to get my sons the care they need and get my family to a place where we can all thrive. If you can help from any angle, please reach out. If you can RT, that matters too.
DMs are open. 🙏
We are building up to something big for I/O, but we had to sneak this update out early. ✨
The native image generation inside Stitch just got a glow-up. We've upgraded the underlying agent to give you:
🖼️ Higher overall quality and fidelity
🎨 Better alignment with your specific brand vibe
📝 Deeper understanding of your page's context
Check out the before and after! 👇
Fun interactive science app ideas | Part 3
Played around with generating 3D biological structures and made an app to explore them interactively
UI Design
GPT Images 2
Code
Gemini 3.1 Pro
More demos ↓
how to use Google's NEW open source Design.md + AI Skills to make your startup look like a $100 million company in 1 hour:
1. Design.md is an open source file from Google that captures the soul of a design. Typography, colors, spacing, all in one markdown file. You attach it to your prompt and your agent builds beautiful things every time.
2. Think of it this way. The HTML is the finished dish. The design.md is the recipe. The skills are the ingredients. Put them together and everything you build looks consistent and professional.
3. Don't create a design system from scratch. Find a brand you love. Linear, Stripe, Vercel, whatever resonates. Study it. Use ChatGPT or Claude to help you extract the design language into your own design.md file.
4. Build skills on top of your design.md. A landing page skill. A mobile app skill. A motion design skill. A slide deck skill. Each one references the same design.md so everything looks like it came from the same designer.
5. The biggest mistake people make: they nail one screen and then everything else looks generic. Design.md solves this. One file keeps every page, every format, every medium consistent.
6. Use it across everything. Your landing page. Your app. Your pitch deck. Your promo videos. Same DNA. Same taste. Same system. That's what separates a startup that looks real from one that looks vibe-coded.
7. Build a second brain for design inspiration. When you see something beautiful in the real world or online, capture it. Save it. When you're building something new, reference it. Taste is developed, not downloaded.
8. It's obvious but the difference between a product people trust and a product people bounce from is how it looks and feels. Design.md gives you that edge.
you can watch below
https://t.co/Am1BdxLtzM
shoutout to @mengto for coming on @startupideaspod and walking through his full workflow.
if you want to use AI to actually build gorgeous designs, you'll want to use see this.
watch