Connect with the Product Hunt community

I sometimes get questions on LinkedIn from people who come from Product Hunt:

"What should I post about so that my thread is approve / featured?"

"I want to be more visible, so I need to contribute. About what?"

MCP just locked its biggest revision ever, and it quietly changes the unit of distribution from "a user opens your app" to "an agent calls your tool." That's a strategy decision, not an integration ticket.

A couple of weeks ago the Model Context Protocol shipped its final 2026-07-28 spec the largest revision since it launched. Most of the coverage was about the plumbing: it's stateless now, it runs on ordinary HTTP, the session handshake is gone. Real changes, and if you operate a server they matter. But that's not the part I'd flag for makers. The part I'd flag is what MCP has quietly become while everyone argued about transports: the way software gets used by agents instead of by people. There are close to ten thousand servers in the official registry now, MCP lives under the Linux Foundation with AWS, Google, Microsoft and Salesforce behind it, and this same release added MCP Apps servers can now render their own interactive UI right inside the agent. The protocol stopped being a developer curiosity. It became a distribution surface.

We launched Second Brain on Saturday, listened closely to the feedback, and got straight back to work.

Today, v2.1 is live.

I audited an AI-written billing service this week. 22 findings, 10 critical.

None of them crashed. All returned 200. Four that stuck with me: an auth check that silently lets anyone in when one env var is missing, SQL injection in the one query that wasn't parameterized, a broken permission boundary so anyone can attach a charge to a workspace that isn't theirs, and a Stripe retry that double-grants seats because there's no idempotency check anywhere.

Over the past few days, I ve been following a heated discussion about how Marc Lou is selling parts of his body in some kind of simulation to promote products (ad placements in the form of virtual tattoos) and making a lot of money from it.

I swear, the whole thing has gone mainstream.

Building the product? Honestly, that part can feel easier than expected.

You can ship features, fix bugs, deploy, iterate and feel like you re making progress every single day.

Then comes the part where you actually have to talk about it.

We ve been looking at a question that feels increasingly relevant as more products put LLM output directly in front of users: if two frontier models are asked to judge the same factual claim, how often do they actually reach the same conclusion?

We tested five frontier models on 1,000 real-world claims under the same forced-choice setup.

• On 63% of the complete claims, at least one model disagreed with the others or no majority formed.

• On 23%, the disagreement was substantive verdicts at least two categories apart.

We did it! Prelint hit #1 on Product Hunt this week - thank you for every upvote, comment and DM Now let me return the favour:
I honestly didn't imagine a launch where we'd have a customer registering every couple minutes - or that I'd spend part of it exchanging comments with one of the world's most popular YouTubers. Wild week.
I replied to every comment on our launch - solo builders, CTOs, investors all interested in the same problem from different angles. Here is how it started in February:
Prelint exists because of one code change. An agent ignored our event-driven architecture and implemented a feature completely bypassing it. The code was technically correct, passed all tests. And nobody made that decision - it was just quietly baked into our product.
That's product drift. It's almost never one big bad call - it's micro-decisions nobody notices for 6 weeks. A change in permissions, a "simplified" billing edge case, a dependency nobody approved. Usually it's good code, wrong product.
So here's my launch offer - not a discount - it's my time.
If you're rolling out coding agents and agentic workflows at your company right now, comment or e-mail me at wojtek(at)prelint.com. I'll share the exact agentic workflows and tooling we use internally to manage 50 production changes a day as a small team and I'll honestly tell you which parts you can solve in-house before you need a tool like ours. These conversations were the best part of the launch and I want more of them :)
Also - if you want to see what your agents have been deciding on your behalf, connect a repo at prelint.com Code PH100 gets you 100$ in free review credits this month - it's full speed AI, but with lane assist.

Meridian is an open-source, MIT-licensed, local-first AI work journal. It runs on your device, captures work that often gets forgotten, and drafts clear worklogs and project updates for you to review and approve.

If you believe productivity tools should help people make their work visible without becoming surveillance software, please support Meridian on Product Hunt. We would also value your honest feedback on what works, what feels unclear, and what we should build next.

Product Hunt: https://www.producthunt.com/prod...

GitHub: https://github.com/Meridiona/mer...
Thanks!

We're building Expertise, a platform where GTM experts publish their playbooks as skills that businesses run on their AI agents, and there's a debate that comes up with every expert we onboard: should a skill be open or locked?

Before building, we looked at why prompt marketplaces and open skill catalogs kept dying. A playbook written as text is just a string, and a string gets copied the moment it's worth copying. And there's a newer twist: ten years ago you open-sourced for other humans, who fork you, cite you, hire you. Now the biggest consumer of an open playbook is the AI itself. Every framework posted publicly becomes something an agent runs tomorrow with your name stripped off. You're not sharing with a community anymore, you're training your replacement one prompt at a time.

When you're pre-launch with zero audience, the generic "hey, check out my product" DM just doesn't work, people can tell it's copy-pasted to 200 others.

What's worked better for me:

• Give value before asking anything (a real comment, a resource, actual context on what they built)

• Skip broad cold DMs, join niche communities instead (Discord/Slack) and let the product come up naturally

• One follow-up max, then let it go

We launched on Product Hunt yesterday and the response has been amazing. Thank you to everyone who supported us!

Now I want to hear the real stuff: what did you like, what confused you, what would you change? If you haven't tried it yet, Snipplet lets you turn your favorite places into beautiful, shareable visual guides. Use code PRODUCTHUNT to get a free month of Pro.

Coming soon to Votap...
Question of the Day: one major political story from your country, turned into a quick daily vote.
The idea: open Votap with your coffee, see what actually matters today, vote, then check back later to see where everyone landed.
A tiny daily political ritual.

1. Me and @nischal_naik refreshed our leaderboard page more times than we got upvotes, I hope we were not the only ones

2. Nobody asks the question you come prepared for, instead they will ask the most obscure things you might have not even though they could ask, and thats a GOOD thing!! It means more people are have a different POV about your product and will also make you think from the different POV to answer those.

3. The upvote spammers found me before my own users did, within hours of launching, all our dms got spammed by scammers trying to selling me upvotes and "we will get you to top 3 rank" little do they know our organic support is far better than their botnet

4. Its incredible how just a week of planning can give you the best results. Although we have been building Construct for 6+ months, we only recently decided to launch it here, just to put ourselves out there, we simply wanted to launch irrespective of whatever rank we get, but here we are competing for product of the day, incredible! :)

Before the day closes, we genuinely appreciation everyone who supported us.

@ruffledzest is the reason this launch looked like anything at all. Every visual, every asset, the whole aesthetic of the page and the product itself, that's him. People decide whether to click in about two seconds and he's the one who won those two seconds for us, over and over. Genuine MVP of the day and it isn't even close.

If so, what apps do yall use, and what is the number one feature you wish was there, or what s the most annoying pain point when using these dictation apps? Appreciate any feedback, and I m considering giving people lifetime access to my app if they contribute their ideas, guys let s work together to make the best local dictation app out there.

Solo dev here. We hand-made 137 animation groups per species, six species, 5,242 frames, for a habit app where the progress bar is a pixel pet.

Then our founder said: we made all those special animations and I never see a single one.

I assumed he was wrong. He wasn't. signature_move_played had fired once in the app's entire history. The cause was arithmetic, not art: a pool weight of 8 out of 108 with a selector ticking every 7 seconds meant a ~90 second expected wait. Our median session is 59.5 seconds. We had built twelve animations that a typical session could not reach.

Fixing it surfaced four more defects. But the one that still bothers me is meta: our own detectors produced ten false alarms during the work.

Hello guys,

first thank you for all the support in the launches, btw we are live today so let's support !

I watched Sam Altman talk about what separates successful startups from the rest.

Here are the 7 things that stood out to me:

1. Build something people love
Not something people kind of like. Something they d genuinely miss if it disappeared.

Hey everyone!

I wanted to share something a little different from NoteUX that I ve been building on the side.

I was wondering where I can see the last new posts on Producthunt. Especially the new projects that are being launched. I'm very much interested in the newest project, because the ones on top of the leaderbord already are known by many.
Thanks for your help, greetings Verdictfootball

AI Context Flow reached 4200+ users in 10 months with new paid users coming in every week - proving that context management is a growing pain for AI users. 

If you are also frequently repeating context to different AIs, try AI Context Flow and make your life a little easier.

Curious to know which ESPs (email service providers) PH community members are using for correspondence, transactional and marketing emails.

Why did you choose those ESPs? Price, features, integrations?