I ve been exploring MCP, an open standard from @Anthropic that aims to simplify AI integrations.

In theory, this should make it easier to connect AI with databases, task managers, or even development tools. But I m curious to know how well it actually works in practice.

I might be missing some but I've been pretty much in love with @Lovable, @Cursor, @bolt.new and have been trying to use @Replit more and I honestly haven't touched @BASE44 too much but have heard good things. @chrismessina has nudged me to use @Windsurf for whenever I build another Raycast Extension!
Currently I use:
- @bolt.new / @Lovable
- @Cursor
- @Warp
Curious what everyone thinks is the top one so far!

By engagement, I mean upvotes, comments, shares basically anything that helps your product get to the top of the voting.

Do you have an overview of which tactics were most effective in this regard?

So many indie makers launch like this:

• alone.

• no hype.

• no crew.

• no plan.

• just vibes.

They think it s noble. if it s good, people will notice.

But here s the problem:

When you're a 9-5 employee, it's relatively easy to determine when your work starts and ends.

But what about when you work for yourself?

Single people probably have no boundaries in this, but a completely different scenario occurs when you have a family.

Most AI startups today build tools to help existing companies work faster or smarter. But Y Combinator is doubling down on a much more ambitious vision: full-stack AI startups that don t just improve industries they replace them.

Instead of selling AI to law firms, why not build an AI-first law firm?

Instead of helping developers write code, why not launch a fully automated dev agency?

Why sell to customer service teams when you can eliminate the need for them entirely?

How often do you change the cost of your product?

Do you use any frameworks to decide when to change the price as you add more big features?

No shame.

We ve all nodded along while someone drops tool names like gospel.

But deep down, you re thinking:

I ve opened it 5 times. Still don t know what I m looking at.

Once I asked What do you consider when choosing the right co-founder.

But I have never asked where to find them...

That's why I would like to hear your "How we met story."

Let s play this out.

• You re not full-time.

• You re not VC-backed.

• Life s already happening.

• And your calendar hands you exactly 60 minutes a day to build something meaningful.

So now what?

No time for endless roadmap debates

Hey guys

I'm a solo founder currently building my first SaaS product, and I'm planning to launch a few more niche products in the future. I'm based in Australia and operating under my ABN (sole trader), but I m trying to figure out the best way to structure things for the long run.

We're working on a weather app that uses AI for voice-powered updates (like read out the weather forecast and wake you up: 'Rain in 30 mins grab your umbrella!').

But it got me thinking: what other cool stuff could AI do?

• Ultra-local predictions? ("Your backyard BBQ at 3PM will be sunny, but your neighbor s patio will be windy")

• Eco-friendly tips? ("Water plants today drought risk increases tomorrow")

• Personalized alerts based on routines? ("Heads-up, temps will drop during your usual jog time!")

With AI tools launching every other day, it s easy to forget the simple non-AI tools that still get the job done, sometimes even better.

For me, it's

Trello for clean, visual task management

Now, the trend seems to be growing. As companies focus on cutting labor costs and investing in AI tools, entry-level opportunities are shrinking. There s a concerning rise in unemployment among fresh graduates. It s not just about automation, AI investments may be crowding out budgets that were once reserved for hiring and training new talent.

But here s the question:

Lately, I ve been thinking about how much of today s marketing is shaped by algorithms, automation, and machine-generated insights and whether something essential is getting lost in the process.

It s hard not to notice:

AI can generate full campaigns before a human finishes the brief,

Strategy often starts with data models, not human moments,

Like most things, Loopify started out of frustration.

Cameron and I were just trying to find a simple way to post across multiple platforms, but what we found were either outdated tools that felt like flip-phone era relics, or shiny ones charging premium prices for the bare minimum. Or both. So we started building what we wished existed. Something modern, clean, and actually pleasant to use.

Right now, we re in learning mode, talking to creators, marketers, and small teams to understand what actually matters in a tool like this.

Curious to hear your thoughts:

Hey Product Hunt family!

Wanna hear your thoughts on tools for news feeds or news digest!

Last week, OpenAI had to roll back an update to GPT-4o after users reported that the chatbot was being excessively agreeable even endorsing harmful or irrational behavior. This sycophantic behavior was traced back to reinforcement learning that overemphasized positive feedback .

As a founder building AI-powered products, this incident hits close to home. It raises important questions:

Every day, the PH feed is packed with shiny new SaaS tools most of them browser-based, many of them AI-infused. It s exciting, no doubt. But compared to a time not so long ago, something seems missing: local desktop apps.

They re rare now, and it makes me wonder are native apps still worth building, or have they quietly slipped into the realm of nostalgia?

After all, web apps offer clear benefits for both users and makers or investors. Users don t have to install anything, updates are seamless, and their data is accessible from any device with a browser. For investors, the advantages are just as compelling: a single tech stack, easier user onboarding, lock-in effects, and plenty of levers for driving growth and virality.