🤿 malleable software

insights from a design engineer at Notion

AI is fundamentally shifting the way we think about digital products and the core deliverables that we're bringing to the table as designers.

So I asked Geoffrey Litt (Design Engineer at Notion) to share his vision for the future of malleable software and AI system design.

He’s dedicated much of his career to this topic so his insights are fascinating. Some highlights:

  • The keys to effective system design

  • Geoffrey’s workflow for “working like a surgeon”

  • Why too many products become “nightmare bicycles”

  • The principles of malleable software vs. disposable software

  • Why version control is the most important AI interaction problem

  • Inside Geoffrey’s malleable software experiments at Ink & Switch

  • + a lot more

Listen on Youtube, Spotify, Apple, or wherever you get your podcasts 👇

🤝 WITH LOVABLE

Lovable has had some pretty big releases but their latest might be the biggest yet.

They just launched Lovable Cloud and Lovable AI 

It means you can ship fullstack, AI-native apps just by prompting. No more setting up databases, authentication, file storage, or API keys for all of your AI integrations.

You can get an entire backend set up and running in a single prompt.

No external dashboards or configuration screens. Everything. Just. Works.

And you can add AI features to your app just by asking for them (like document search, or image generation, or anything anything else you can think of)

So if you’re a designer and you have ideas you want to build use the code DIVECLUB at checkout for 20% off your first month of Lovable Pro 1 👇

🔑 KEY TAKEAWAYS

Are we approaching a platform shift?

This line from Geoffrey stuck with me 👇

“A lot of the things that I care about around malleable software aren't things that any one application can easily solve. There are more platform level things that really require a fundamentally new way to think about software.

And those shifts don't happen very often. They last a decade or more…

I think we're in a time of such volatility right now with AI kind of forcing everyone to reimagine how things work, that there's actually going to be a serious platform shift over the next few years.”

Geoffrey Litt

That line “fundamentally new way to think about software” isn’t hyperbole.

In our interview Geoffrey teases out ideas that challenge nearly every constant we associate with digital products and the practice of design.

Some questions I still have on my mind:

  1. what if anyone can mold software over time as they use it?

  2. what does it look like for designers to be responsible for pattern systems rather than fixed UI?

  3. how much of “malleable” software is also “disposable"?

  4. what patterns need to be created to enable effective version control in a much wider array of AI experiences?

  5. what does it look like to effectively expose the system when designing AI products?

This episode will get you thinking so I hope you enjoy it as much as I did :)

How much did you enjoy this issue?

Never hesitate to reply with feedback too :)

Login or Subscribe to participate in polls.

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:


See you next week ✌️ 
- Ridd

P.S. if you were forwarded this email you can ​subscribe here