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
The hardest part of AI-assisted development isn't generating code.
It’s knowing when the code is wrong.
I’m currently working on a poker-vision project where the system has to interpret what’s happening on the table — including card recognition, board ranks, hero cards, and positional coordinates.
And this is exactly where AI-assisted development gets interesting.
The agent can make a change.
It can tell you the change looks correct.
It can even run the code.
But then you look at the actual result and realize:
“Something is still wrong.”
In this case, I was working through an OCR/ranking issue where the system was reading card information and producing an incorrect interpretation.
So the workflow became:
Inspect → Understand → Change → Run → Compare → Debug → Verify.
Not:
Prompt → Generate → Ship.
That difference matters.
AI coding agents are increasingly capable of working across repositories, editing multiple files, running tools and debugging issues. But current engineering discussions increasingly focus on the verification layer making sure generated changes actually produce the intended behavior. CodeRabbit
For me, this is changing how I think about development.
The value isn't just how quickly I can generate code.
It’s how well I can understand the system, identify the real problem, direct the agent, and verify the final result.
That's where engineering judgment still matters.
And honestly, some of the best lessons come from the bugs that refuse to disappear after the first fix. 🔥
Developers using AI: what's one bug that looked “fixed” until you tested the actual behavior?
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
Challenges
View all
Related posts
I've joined the Lovable Partner Program as a Certified Partner. 🎉
Through Mathias Media, I use Lovable to build custom websites, applications, and the systems that connect them.
If you're exploring solving the problems closest to you with Lovable, I'd love to talk. If you’re planning a custom website or application, or want your existing business systems to work better together, send me a message. I’d be glad to hear what you’re working on.
Congratulations 🎊🎈🍾 to you
I desired to learn Framer deeply, with infusion of AI and this is my first live Project.
MacBook inspired Retro Portfolio Piece.
Congrats on your first live Framer project! Fun concept to explore.
As an AI Engineer, I spend most of my day working in the terminal—so I thought, why not make my portfolio look like one? 🖥️🟩
I wanted a personal site that reflects how I actually work. No flashy animations or endless scrolling, just a clean, interactive command-line interface built with React and TypeScript.
In the video below, you can see how to navigate it. You can type ls projects to see the RAG systems and ML architectures I've built, or cat experience to see my background.
Take it for a test drive and let me know if you discover any of the commands!
The terminal metaphor is carried through with real discipline—the monospace hierarchy and command-based navigation make the portfolio feel like a tool, not just a skin. Exposing projects, experience, and contact as discoverable commands is a smart interaction detail.