Use AI to Learn, Not Just Delegate

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 (https://x.com/geoffreylitt) (Design Engineer at Notion) to share his vision for the future of malleable software and AI system design.

Here’s 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

-[Ink & Switch is the research lab (https://www.inkandswitch.com/)

- Changing Minds by Seymour Papert (https://worrydream.com/refs/Papert_1980_-_Mindstorms,_1st_ed.pdf)

- Geoffrey’s nightmare bicycle article (https://www.geoffreylitt.com/2025/03/03/the-nightmare-bicycle)

- Don Norman’s Living with Complexity (https://www.amazon.com/Living-Complexity-Press-Donald-Norman/dp/0262014866)

- Spell Burst by Tyler Angert (https://spellburstllm.github.io/)

- A Pattern Language by Christopher Alexander (https://www.amazon.com/Pattern-Language-Buildings-Construction-Environmental/dp/0195019199)

- Patchwork - Geoffrey’s collaboration environment at Ink & Switch (https://www.inkandswitch.com/patchwork/notebook/)

⭐️ You can use the code DIVECLUB to get 20% off your first month of Lovable Pro 1!