Hey community! I thought to share this because it really changed my week, and I think more people should build their own tools, even if they are not perfect, regardless of their technical background.
For context: I built a tool that pulls my weekly calls from Granola, and turns them into a podcast-style audio every friday using @GranolaMCP, @Claude by Anthropic, and @Cursor.
Recently asked Cursor for a small change on a settings page, and along with the fix it decided to merge a few utility files without telling me. Everything looked fine on the surface, but it actually ended up breaking our export feature in production.
It made me realize that trusting AI to do "cleanups" while fixing basic stuff is super risky.
How closely do you inspect git diffs after AI edits and do you have team guardrails to prevent agents from making unrequested structural changes?
I'm a senior developer in Seoul. My commute is long and the subway is always packed. Here's how I tried to make mobile development work and where it fell apart.
Seoul subway is not quiet. You're standing, one hand gripping a bag, the other holding your phone. Coding the traditional way IDE, terminal, file trees is physically impossible. The screen is too small, your fingers too fat, and the text too tiny to read without squinting.
I let the model write every empty state and failure string in my app because it was fast and the copy read fine.
Then a generation path started failing and the message it showed was calm, vague and reassuring. Nobody reported it. I found it in the logs, not in support, and by then it had been broken for over a week. The writing was good enough to hide a real bug.
Hey everyone, first time posting here. I've been wrestling with production all day.. ended up hitting over 40 builds just trying to get the app to successfully submit.
Nobody really warns you about the absolute nightmare that is app store guidelines and provisioning profiles when you're first starting out.
When I vibe code with Claude Code or Cursor, the agent tends to invent a new button, card and table on every screen. The app works, but each page looks slightly different, and sometimes the agent builds a placeholder UI and calls it done.
A few things I've tried:
Putting design rules in the prompt or an AGENTS.md file. It helps, but the agent drifts after a few screens
Giving it a component library to use. More consistent, but only if the agent can actually find and read the components
Lately, I ve been exploring the concept of vibe coding that flow state where the environment, mood, and tech stack align so well that writing code feels like creating art. To me, vibe coding isn t about fancy editors or lo-fi beats (though that helps ).
It s about building in a way that feels natural, expressive, and efficient.
Sometimes it's HTML/CSS/JS with no build tools. Other times it s AI-assisted prototyping in real-time. It s fast. It s minimal. And honestly, it helps me ship more and stress less. What I d love to know from you: What s your idea of vibe coding? Do you believe tools and aesthetics impact how you think and build? Or is it all just a distraction from real dev work ?
I use a coding agent (omp) for most of my coding now, and I ship more than I used to. What I can't tell is whether I'm getting more done or just starting more things. It's so easy to kick off a new feature that I end up with a lot of half-finished work. I'm prone to that anyway, since I procrastinate and drop things too easily, and the agent makes it cheaper to jump to the next idea. Has your output actually gone up, or do you just feel busier? How do you tell the difference?
