The network for creativity
Join 1.25M professional creatives like you
Connect with clients, get discovered, and run your business 100% commission-free
Creatives on Contra have earned over $150M and we are just getting started
Back to feedPost
AI made me a faster developer.
Then I noticed something I didn't like.
I was sometimes building faster than I was learning.
I could ask AI to generate a route, build a component, structure an API, or fix an error—and suddenly the feature worked.
But “it works” isn't the same as “I understand it.”
That difference becomes obvious when the happy path breaks.
A request starts failing only under certain conditions.
Two operations touch the same data at almost the same time.
A third-party API returns something unexpected.
A bug appears somewhere between the frontend, backend, database, and the assumptions connecting them.
At that point, another prompt isn't always the answer.
You need to understand the system.
So I've changed how I use AI.
I still use it a lot.
But I make the important decisions myself:
→ Architecture
→ Data models
→ API behaviour
→ System boundaries
→ Trade-offs
Then I use AI to explain, challenge, debug, test ideas, and speed up implementation.
The goal isn't to become the developer who writes code the fastest.
It's to become the developer who understands what they're building well enough to fix it when everything stops going according to plan.
AI can accelerate the implementation.
You still have to own the system.
How do you use AI in your development workflow without letting it replace your own understanding?
The network for creativity
Join 1.25M professional creatives like you
Connect with clients, get discovered, and run your business 100% commission-free
Creatives on Contra have earned over $150M and we are just getting started
Related posts
My AI assistant runs all day. The expensive model only does the thinking.
Most requests need no AI at all. "Call me in 30 minutes" is handled by plain code. Reminders, schedules and limits are code too.
Short tasks like sorting and scoring go to fast models on a free tier.
The big model only gets planning and long conversations, where it actually has to think.
If it hits a limit, a backup model answers instead of the app going silent.
If your AI app's bill keeps growing, check what really needs the big model.
What does your app send to the most expensive model?
Same pattern holds in outbound tooling. Filtering, dedupe and enrichment lookups are plain code. The model only writes the first line once the row is already verified. Cuts cost and the weird outputs.
AI can design websites. So why do startups still need designers?
AI knows what your product does.
But does it understand why your customers struggle with the problem it solves?
Does it understand their problems, doubts, and what makes them trust your product?
That's where human understanding matters.
As a designer, I keep noticing gaps in startup websites.
Unclear messages, weak value, and websites that don't connect with customers.
These aren't always visual design problems.
They're problems of understanding the customer.
AI can help us design faster. It can generate layouts, write copy, and explore ideas.
Someone still needs to understand the customer and decide what the website should communicate.
The goal isn't to choose between AI and designers.
It's to use AI as a tool while keeping human understanding at the center of the process.
Because a website shouldn't just look good.
It should make the right customer feel:
"This is exactly what I need."
If you're building a startup and feel your website could communicate your product better, I'd be happy to connect.
Understanding customer doubts is where UX really matters.
𝗧𝗿𝗮𝗱𝗶𝘁𝗶𝗼𝗻𝗮𝗹 𝗙𝗶𝗴𝗺𝗮 𝗱𝗲𝘀𝗶𝗴𝗻 𝗶𝘀 𝗱𝗲𝗮𝗱 ! ! !
As a designer, I love how AI is changing the way we work.
We’re moving from simply sending clients static designs on Figma to building clickable prototypes that bring their vision to life.
Now, a founder can actually experience how their website will look and feel before development is complete.
They can click through pages, explore interactions, and see animations in action.
And for developers? The handover becomes much smoother because they can see how everything is supposed to work, not just how it should look.
Less guesswork. Better collaboration. A clearer vision.
Honestly, it’s a win-win for everyone.
I think every designer and developer should embrace AI in 2026. Not to replace our skills, but to expand what we can create with them. 🚀
So are you still team traditional Figma design ? Or you now use Ai to advance your design work ?
Awesome work!