- Dive Club
- Posts
- 🤿 new way to design with AI
🤿 new way to design with AI
+ tips for designing a rocket ship

Lovable has quickly become the go-to way I build my ideas with AI and this week we get to hear from their first designer Nad Chishtie.
We go deep into what it takes to succeed as a founding designer and all of the ways AI is shaping modern product teams.
Some highlights:
Nad’s tips for collaborating creatively with AI tools
How designers can be enablers instead of bottlenecks
How Nad balances Figma with new AI tools like Lovable
Why Lovable built and deleted a Figma-like layers panel
What it’s like at the fastest growing startup in European history
a lot more
🤝 WITH GRANOLA
As a designer I’m always talking to people (team meetings, design CRIT, user interviews, etc.).
So it’s super important to capture the ideas and feedback I’m receiving.

That’s why I never have a conversation about design without running Granola in the background. It’s like Apple notes but it transcribes my meeting for me 🤯
So when the meeting ends, Granola enhances the notes I’ve written and I can even ask questions or get tailored summaries from the call
It’s very quickly become a staple tool in my design practice
Every designer should be using this and if you click below you and your team can get 3 months free 👇
🎓 KEY TAKEAWAYS
3 highlights from my interview with Nad
1 — Be an enabler not a bottleneck
Too many designers operate in a waterfall mentality where things are either “designed” or “not designed”.
But when you’re growing at the speed of Lovable you can’t afford to position yourself as the keeper of all design decisions. So Nad is more than comfortable letting engineers carry things end-to-end when possible.
“My job is to enable higher quality decisions across the board rather than making all those decisions myself and then waterfalling them onto the team”
This means Nad thinks of quality as debt rather than a bar to hit. When you’re the first designer you have to be ok shipping some features with “design debt” to be paid off later.
2 — Getting feedback uncomfortably fast
Nad stresses the importance of not falling in love with your ideas (a theme Sam from Granola echoed last week too).
Because they’re going to be wrong.
The times Lovable has “failed” have been when they tried to be too visionary. Now the focus is on reducing iteration cycles and getting feedback “uncomfortably fast”.
“How do we maximize our learning in the shortest scale possible? What that means is lots of rapid, scrappy experimentation and lots of being willing to be wrong”
To accomplish this, Lovable puts a lot of weight on velocity of decision-making. Nad calls it having a high “clock speed” ⚡
“What stops you from making a 10-second version of that decision on the spot instead of waiting for a meeting next week?”
3 — How to be more creative with AI
When I work with AI I’m often using adjectives that relate to interfaces (minimal, energetic, etc.).
But Nad’s advice is to break out of the UI design vocabulary.
“Say something like, make it more art deco, make it more Bauhaus, etc. Like, don't stick to the UI styles that you see on Twitter like glass morphic or whatever”
He even talks about building color palettes by referencing Wes Anderson films 😅
How much did you enjoy this issue?Never hesitate to reply with feedback too :) |
Meet the Dive partners
I made a list of my favorite products and asked them to come on as sponsors of the newsletter/podcast. They said yes 🥹
The #1 way to support Dive Club is to check them out👇
Framer → How I build my websites
Genway → How I do research
Granola → How I take notes during CRIT
Jitter → How I animate my designs
Lovable → How I build my ideas in code
Mobbin → How I find design inspiration
Paper → How I design like a creative
Raycast → How I stay in flow while I work
Thanks for reading! I'm working hard to bring you the best design resources on the planet 🫶
If you want to go even deeper you can always:
![]() |
|
P.S. if you were forwarded this email you can subscribe here