Hey!

I want to dive into practical applications of generative AI and have set myself a challenge to develop a useful product in 30 hours of focused work. My goal is not just an experiment but creating something with genuine practical value.

I have basic programming skills and can use any available APIs and tools (GPT-4, Claude, Stable Diffusion, etc.). The ideal project should:

- Solve a real problem

Recently our team concluded in our peer-reviewed research that that code health determines AI-performance. The study "Code for Machines, Not Just Humans: Quantifying AI-Friendliness with Code Health Metrics" concluded that when agents operate on unhealthy code, the defect risk increases by 60% (at least).

It s was a large-scale study of 5,000 real programs using six different LLMs to refactor code while keeping all tests

passing.

We ve been seeing a consistent pattern across agent systems:

GPT-5 works well as a judge on average cases
but breaks down on edge cases and policy boundaries.

That s exactly where reliability matters.

In our recent work, we took a different approach:

I ve been experimenting a lot with AI tools like V0, Lovable, and Bolt.new to build small products and prototypes.

One pattern keeps showing up: most ideas don t fail because the idea is bad. They fail because the prompt is vague, confusing, or incomplete.

AI isn t a mind reader; it does exactly what you ask. If your prompt is fuzzy, your output will be too.

For example, I recently built PublicWall off a single well-structured prompt. Before that, I wasted hours on iterations that were mostly me not clarifying what I actually wanted the AI to do.

I've been talking to dozens of PMs over the last few weeks who prototype with Lovable, Bolt, Figma Make, V0, etc. Same frustrations keep surfacing.

• Output looks a bit generic: looks like a demo, not your actual product

• Context loss: explain your product in ChatGPT/Claude, then re-explain in Lovable, then again somewhere else

• No edge case thinking: AI executes prompts literally, doesn't challenge or expand on them

The core issue I keep seeing: these tools are interface builders. They're great when you already know exactly what to build. But the hard part, thinking through the flows, the states, the edge cases, where users will actually get stuck, that's still entirely on you.

It s the third week of working on my little side project, SimploMail.com, and to speed things up I ve been doing a lot of vibe coding. It s been fun, but a few things became obvious pretty quickly.
I stopped using the auto model setting in the IDE. When it silently switches models, the quality drops fast. I can feel when the agent all of a sudden looses its intelligence . So now I just pick one model I trust and stick with it.
I also try to keep each AI session focused on one small task. One feature, one change. After it writes the code, I go through everything myself. I check for hard coded config, make sure it didn't quietly delete a unit test to make something compile, and etc. Sometimes it does update unit test just to make it pass .
And I never commit without reviewing. The AI is helpful, but it can also remove something important without telling you. I've seen it happen enough times now .

Wherever you code (online, CLI, or IDE), everyone has some love, hate or horror vibe coding stories, from building a prod-ready app in minutes to the whole repo got wiped. Would love to hear your story.

Hi ProductHunt community,

This term has been coined by someone and there are already more than 80 products that you could put in this category. Looking at the numbers, it's growing pretty fast.

I ve been using Pencil.dev for a few days and honestly it s a big paradigm shift for how fast you can explore UI. I'm loving it!!

One thing I bumped into: I still need to move some screens into Figma to polish details, collaborate, and keep everything in the same place as the rest of our design work.

At @UXPin we've just deployed the prompt enhancer for our AI component creator.
From now on, short prompts will be evaluated and refined if the AI considers them too weak. This aims to improve the AI output - with prototypes returned by the AI more detailed and diverse.

Example and output below:

Original prompt: 'news portal'

Refined prompt: