I'm Kevin, founder of EnginifyAI. Over the last 12 months I've been working on a prompt engineering tool. I started off using Bolt but quickly I found myself unable to completely use it effectively. I then tried Cursor and was using it early on but maybe I had the wrong settings as I found myself using all my credits in 2 days. So, I switched to Windsurf, and to my surprise credits were a bit more manageable and it took about 2 weeks before my credits were consumed. Keep in mind that I am new to coding so I spent a lot of time asking questions in Windsurf instead of using my paid subscription to Anthropic.
I'm coding using React/Typescript and Supabase. I have learned that coding is a lot of work, a lot of fine-tuning, and a lot of testing and fixing. The one thing I haven't quite figured out completely is how to fix migrations. Early on I was running SQL scripts directly in Supabase without migration scripts because I found it to be faster. But now Windsurf uses very old migration script references and I find myself fixing the same issues because of an old migration script reference. Any idea how to fix this?
I assume that vibecoding is an experience everyone can enjoy but comes with frustrations about asking the right questions, or being very specific about my requests. I am using Claude Sonnet 4, 4.5 and 4.5 thinking. Are these the best coding ai models for Typescript?

I've been vibe coding( @Lovable , @v0 by Vercel ) for a couple of months now & it's such an incredible feeling. What once required specialized skills now happens through simple descriptions.

Breaking free from dependency on designers & engineers for mocks/prototypes has been especially empowering. Great to see this creative autonomy that has fundamentally changed how people build.

What an incredible future we are creating for kids who can create software from sentences.

For more than a year now I have been consistently working in a vibecoding format. During this time I have created several unusual solutions and finally decided to start showing them publicly.

These are small research pieces that can inspire and at the same time remain utilitarian.

I'm Vasyl, and three days ago I couldn't code. Well, today nothing changed lol. It would be great to hear some advice, how you guys as low Cursor credits as possible.
Today I'm 82% done with a web app full-stack mentorship platform.
WHAT IS IT: a mentor-mentee matching web app where professionals can find the right guidance and mentees can connect with experienced mentors in their field.
THE TWIST: I'm building this entire thing with zero coding background, using Cursor IDE + Claude AI, and documenting every single day publicly.
WHERE WE'RE AT (Day 3): - Backend: 100% complete (auth, payments, messaging, reviews) - Frontend: 70-100% depending on feature - Dashboards: Fully functional - One blocker: Database setup (2 hours away) - Launch: ~20 hours of focused work
WHY THIS MATTERS: Not trying to sell you on the app yet (it's not even live). But the meta-story is wild - AI just changed what's possible for non-technical founders. The barrier between "I have an idea" and "I shipped a product" collapsed.

FOLLOWING ALONG: Building in public on X (@VasylK23416) and LinkedIn. Every day. The wins, the bugs, the "why doesn't this work" moments. Launch coming next week. Would love your thoughts, feedback, or just follow the chaos. What was your experience learning to build your first product? #buildinpublic #AI #nocode #mentorship

Hey folks

Quick share: I got tired of bouncing between 10 different sites every time I needed a simple arrow or calendar icon. Felt like such a dumb waste of time.

As devs, we all know the struggle with code security scanners:

• Switching between IDE and clunky dashboards to check vulnerabilities

• Wasting hours sifting through false positives

• Getting vulnerability alerts with zero guidance on how to actually fix them

I stumbled on an IDE extension (ZAST Express for VS Code/Cursor) last week that s amazing for my workflow. The Proof of Concept (PoC) feature is what sold me instead of just flagging issues, it gives runnable snippets to validate the problem, plus clear fixes right in my editor. No context switching, no guesswork, and it s free to start.

@jim_hartung and I built this ultralight task manager for Chrome (also works well on Comet) in the form of a Chrome extension and within the first day or so, without any marketing at all got 20+ users!

So what is it? It's called "Easy Tasks" and it literally has all the important stuff you need from a basic task management:

• Organize your tasks in task lists

• Search and sorting

• Assign due date and priority to the tasks

• Have a simple "Today" list on top of everything else

• See tasks left behind

• Quick capture, as simple as highlighting some text anywhere online, hit a shortcut, and create a task

I would highly appreciate some information how you keep costs low. What we are now going to do:

• Run everything on VMs

• Rent A100s through Google Cloud for Startups Program (if they let us do this)

• Switch to Haiku

What else can you recommend?

I just shipped my first production-level app with a team of Claude agents in the cloud and it took me exactly 2 months from idea to launch! Most of that time was spent trial-and-error figuring out the right roles for each agent and dialing in handoffs so things actually worked in a real production setting.

Curious to hear from others:

- How long did it take you to get your first production-ready (not demo!) vibecoding or Claude Code agent project finished?

- What were the biggest slowdowns, unexpected obstacles, or surprising time-savers along the way?

Hey Community!

Is anyone else here documenting their vibecoding journeys from ideation to launch? I'm especially interested in process & workflow description, pivots & fails, and lessons learned.

Thank you!