- Dive Club
- Posts
- š¤æ the newest design tool
š¤æ the newest design tool
A guide for designers who want to build their ideas
One of the most impressive things Iāve seen a designer make all year is Meng Toās DreamCut š
Itās the perfect example of what it looks like to transition from traditional designer to builder šŖ
So if youāre interested in becoming a designer who ships then this is the episode for you because Meng gives a highly practical breakdown of what it looks like to go from 0 to 50,000+ lines of code as a designer.
Also Meng is the perfect person to onboard you into tools like Claude and Cursor because heās spent 10+ years teaching designers how to code through Design+Code.
So in this episode we go deep into:
Mengās tech stack and go-to AI tools
How to fine-tune visual details in code
The secret to an effective first 10 prompts
How to find the perfect first project to build
How much code you need to know to build with AI
What parts were easier/harder than Meng expected
Why Meng considers Claude the newest design tool
a lot moreā¦
š¤ WITH GENWAY
Iāve been loving this new product called Genwayāit uses AI-powered interviewers to help you gather rich, qualitative data at basically an infinite scale.
So Iāve been using it to interview Dive Club listeners all over the world!
I tell the AI what Iām hoping to learn and then it has a dynamic conversation with each person. Genway then automatically organizes all of the key insights for me.
I learned more in a 2 week study than I had in a year and half prior. Needless to say I am totally hooked š
So if you want to take your research to the next level, visit this secret landing page specifically for Dive Club listeners to get your first 2 months free š
š KEY TAKEAWAYS
How to build your ideas with AI tools
If youāve never built your ideas with AI before, then hereās a breakdown of how Meng recommends you get started š
1 ā Pick an idea that you care deeply about
AI rewards designers who show perseverance. Because itās rarely going to work on the first try. If you donāt genuinely care about what you are building then itās too easy to give up.
"It has to shake your core to a point where you're not gonna give upā
Remember how Mariana said she failed the first two times she tried learning how to code? She only succeeded when she made building the primary objective instead of focusing on the next learning rung.
Maybe you solve your own problem in Figma with a plugin (ex: Meng spent 3 weeks building a simple .svg pattern plugin as a way to practice). Or perhaps you capitalize on the limitations of Figma to create a prototype that is truly function (ex: a form that users can actually submit and store data).
2 ā Start with Claude Artifacts
Claude Artifacts was the tipping point where Meng realized that he was now capable of building his own ideas.
If youāre not familiar, itās a simple side-by-side view where you can prompt the AI on the left and immediately generate a product on the right.
"Design is about function and problem solving. And if you think about design that way, Claude is really, really good at that."
3 ā Be intentional about your first ~10 prompts
āIt's not code that scares peopleā¦ itās that they don't know how to deconstruct the app in a way that makes sense to the AIā
That word ādeconstructā is key š
Meng couldnāt start by asking Claude to ābuild a video editorā. You have to think about your product from first principles and break it down into its fundamental components.
Then you can tackle each element one step at a time using simple prompts (Meng recommends staying under 3 sentences per prompt).
For DreamCut, Meng focused just on the timelineā¦ and then just on the video player. And every step of the way you have to get ultra specific. For example you canāt just say you want a video playerā¦ you have to specify where the video is coming from. Are you uploading it? Are you rendering YouTube links?
This is what it means to think like an engineer.
4 ā Invest in aesthetics
Meng says he doesnāt worry about tweaking the styling until heās āready to post on Twitterā š
Most AI products revolve around TailwindCSS. If you havenāt explored their docs before itās actually quite straightforward and Iām willing to bet you could pick it up in <30 min even if youāve never written code before.
āLearning Tailwind can give you a huge leg up in understanding aestheticsā
Meng also is a big fan of using UI Kits like ShadCN as a baseline.
5 ā Move over to Cursor
When you get to ~400 lines of code itās probably time to move things into Cursor. This can be a scary jump but āyou learn it once and then youāre good.ā
Cursor Composer gives you a chat UI where you can write code using natural language and have the AI explain what is happening in a way that even designers can understand.
The hardest part is setting up your local environment, installing packages like Node, etc. This is where youāre probably going to want to follow a YouTube tutorial step by step. Itās annoying but youāll get through it I promise.
6 ā Manage your code base with Cursor
For a while, all of your code will live in a single file. This is totally fine to get momentum! But at some point youāre going to want to split your code into separate pages and start turning things into reusable components.
The good news is that Cursor Composer is great at this šŖ
AI will write the code and create the files for you. Itās so good that Mengās 8 year old son was able to create a pretty sick Three.js site without knowing how to code.
Also remember that Cursor is building up context for your project as you add to it. So each feature requires less and less explanation. For instance Meng thought adding a camera recording feature would be especially difficult so he saved it until the end. But it ended up being a single prompt and it worked right away!
7 ā Build in public
Meng made a big deal about the importance of building in public.
Itās the best way to hold yourself accountable and ensure that you ultimately ship something youāre proud of.
ā100% of my projects would fail if I wasnāt building in publicā
There will be many failures along the wayā¦ heck you might not even end up in the place that you thought you would. Thatās ok! Because itās the process that matters. And I guarantee sharing your journey (failures included) will inspire others and push you to keep going.
The only difference between a designer and an engineer is the tool
btw if you want to save this link I broke it all down in article form š
š¤ WITH RAYCAST
Iāve been anticipating today for quite some timeā¦ Raycast Notes is finally here!
Their old floating notes product was my go to for quick captures but theyāve taken it to the next level. Thereās markdown formatting, keyboard shortcuts, multiple notes, etc.
You can even create a Quicklink to a specific note and assign a hotkey to it! That way you can open it from anywhere with a single keystroke.
Itās just another way that Raycast helps me stay in flow while I work šŖ
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 š„¹
The #1 way to support Dive Club is to check them outš
Dessn ā How I ship like a design engineer
Framerā ā How I build my websites
Genway ā How I do research
Jitterā ā How I animate my designs
Play ā How I design mobile apps
Raycast ā ā How I do most things on my computer
Visual Electric ā How I generate imagery
How much did you enjoy this issue?Never hesitate to reply with feedback too :) |
Thanks for reading! I'm working hard to bring you the best design resources on the planet š«¶
If you want to go even deeper you can always:
ā Read all āideasā
ā Watch all āepisodes ā
|
P.S. if you were forwarded this email you can āsubscribe here