Recently stumbled across this Cursor pro-tip from Ian Nuttall on X:
"1. ask it to recommend a folder structure

2. ask it to actually create the folder/files based on that this makes it 10x easier for me to get started and Cursor is more accurate using codebase cos it knows where to update files."

That got me thinking, what other pro tips are people using to generate better code, ship faster, organise your space better, etc. Drop em below:

AI dev tools are moving stupid fast. Every few weeks, there s a new must-use. Some stick. Most don t.

Some vibe coders are developing full products with @ChatGPT by OpenAI+ @Replit. Others swear by @Cursor + @Claude by Anthropic . A few are mixing @Lovable , @v0 by Vercel , and @bolt.new . New and shipping way faster than expected.

I ve been refining my own vibe stack lately.
Building with @Google Antigravity at the core. It keeps the flow clean when things get messy.

Share your current Vibe Stack:

Now, since some do these things, while others charge every bit as much without these features, I already expect that they have:

• Built-in Github commit

• Credit rollovers (e.g. if I do not use all credits in a paid plan, they are added to the next month - indefinitely)

• Nothing that tries to keep my project within their ecosystem and then expects that as my business scales, I pay them more.

As Lovable, Bolt, v0, Base44, Bubble, Make, etc. jostle to out-do each other and be the one that we pay for, I think we will soon see:

• Back-end solutions that guide non-technical creators through the steps to ship a SaaS product that is actually ready to scale to take on real traffic

• Pre-emptive best-price/best-solution external solution-shopping, such as for white-listed bulk emailing and available domain search.

if i use claude or codex, i constantly am screen capping to show bad padding / alignment / whatever. is there a defacto way to let claude or codex tool call to see the browser or render a page for themselves?

Hey everyone! I had a massive reality check this month and wanted to see if other founders have experienced this.

We use Stripe for billing and HubSpot as our CRM. Our dashboard looked incredibly healthy, MRR was growing, and deals were marked as "Active." But out of curiosity, we cross-referenced our active paying users with our actual product analytics (Mixpanel/PostHog).

Turns out, almost 12% of our paying customers hadn't logged into the app in over 20 days. They were "ghosts." Because their Stripe subscription hadn't failed yet, our CRM was completely blind to the drop-off, and our CS team was doing nothing to save them.

We ended up having to build a native bridge to pipe usage data directly into HubSpot to fix this.

Hey makers!
I've been deep in prompt engineering lately while building an AI tool, and I'm genuinely curious about how others approach this.
A few questions:
1. Do you save your best prompts somewhere? Notion, text files, dedicated app, or just copy-paste from chat history?
2. How do you iterate? Do you have a systematic approach or just tweak until it works?
3. Different prompts for different models? Or do you use the same prompt for ChatGPT, Claude, Gemini?
4. Text vs image prompts do you treat them completely differently?
I've noticed I was doing the same optimizations over and over (adding role, being more specific, structuring output format), which made me wonder if everyone has their own "prompt formula."
Would love to hear your workflows!

I'm a big fan of voice dictation apps. In fact, I'm using one right now to write this very post (you'll have to wait till the end to see which one I'm using )

The two main products I've used in this space are @Aqua Voice and @Wispr Flow. From talking to others, these are the two that I typically hear people mention using. In general, I hear a lot more people talk about using Wispr Flow.

Were you able to build and monetize the product?

Please avoid answering the question if -

• You've built just another Product Hunt Spinoff or any other directory.

• You're monetizing by selling prototypes just like agencies.

• Any other kind of business where you are charged to display ads.

It'll be good to see if people could monetize a real SaaS product that they vibe coded.

I keep seeing advice like use this model for the easy stuff and that one for complex problems. But it makes me wonder what really counts as a complex problem for an LLM?

For us, complex usually means lots of steps, deep reasoning, or tricky knowledge. But for AI, the definition might be different. Some things that feel easy for us can be surprisingly hard for models, while things that seem tough for us (like scanning huge datasets quickly) might be trivial for them.

After rebuilding the same project three times because AI forgot my architecture, I got fed up and built @CodeRide (Beta) with my team.

The problem: AI code assistants lose track of your project between sessions. Every time I start coding with Cursor, Claude, or any AI assistant, I waste time re-explaining my codebase structure, architectural decisions, and coding patterns.

What we built: The project management tool for coding agents using MCP. Upload your project documentation or PRD, and CodeRide breaks it into optimized, fully contextual tasks ready for your AI agent.