Connect with the Product Hunt community

most of the conversation around AI agents is about what they can do. faster, smarter, more autonomous. but i've been thinking about the other side of that question.

when you're building with agents, at some point you have to draw a line. this agent can read but not write. it can suggest but not send. it can book but not pay. somewhere, someone made that call.

The tools keep getting better at the first week. Describe an app, get an app. Impressive and the demos aren't lying.

What I keep hearing about (and lived myself) is month two. You ask for one change and five files move. Styling drifts. The AI forgets decisions from last week because the only place your app's structure exists is the chat history and the chat history runs out. Every builder community has the same complaints in almost the same words.

So, honest questions for people actually shipping with these tools:

Since we launched Krisp MCP, some of our most advanced users have been scripting, automating, and finding workflows we didn t originally build for.

We watched

Road to 1,000,000 Votap users Day 77 | Current: 1465

Most AI chat products give you text back, maybe a code block. We wanted Kopai's agents to answer the way a good analyst would with the actual chart, table, or calculator, not a paragraph describing one.

So when an agent decides a visual beats prose, it writes real render-able code and it renders live in the chat inline, not a separate canvas. It runs in a sandboxed iframe with a null origin, so the generated code can't touch your cookies or session, even though it's fully interactive. It also picks up your theme automatically, light or dark, so it never looks bolted on.

It's not one generic "chart mode" either the agent recognizes what you're actually asking for and reaches for the right shape: an interactive widget, a chart, a diagram, a UI mockup, or generative art, and builds accordingly.

Ask your agent to "compare these three plans" or "show me how OAuth works" and watch what it reaches for instead of text.

A week after launch day, this is the biggest release DockDuck has shipped. A good part of it came straight from your comments and from what early users asked for, so thank you for that.

Here is what's new.

Workspaces

When launching a product, offering a free plan feels like the obvious choice. More users, more feedback, lower friction. But at the same time, charging from day one gives you a completely different signal. People who pay often use the product differently, give different feedback, and help you understand what they truly value.

The challenge is that both approaches seem to make sense.

A free plan can help you grow faster. Charging early can help you validate faster. There probably isn't a universal answer and it depends on the product, the market, and what you're trying to learn first.

You can either restart the app manually, or the auto-updater will do the job for you in a few hours :)
(FYI: The auto-updater polls every 6 hours, and it has been made opt-in)

This update carries the hottest requested features such as OpenCode support, tracking subagents and fixing the shocked state of the cat which I hope will make more sense now.
The Changelog is as follows:

Looking back, these past two weeks have been denser and more meaningful than all the time I spent building space ocr alone.

I asked six developers to build a demo with the space ocr API. What they brought back came straight out of the problems they deal with in their own work use cases I hadn't imagined. Getting to see that, and getting to talk with them about it, was probably the most valuable stretch of time in the whole life of this project.

Quick update for anyone who followed the Open Wearables launch.

We just published the second edition of our Wearables Integration Playbook. It's the written version of what we learned building the platform and seeing it run in production.

Last week PaymentKit finished #1 Product of the Day, #2 Product of the Week, and top 15 for the month. 457 upvotes and 106 comments.
The comments were the best part. A few were sharper than questions we get on sales calls, and two of them are now sitting in our internal notes.
Thank you to everyone who took the time!
Quick recap for anyone finding this now
PaymentKit.com didn t start as a random startup idea. Our parent company runs a portfolio of subscription brands, and for years we kept hitting the same three problems: billing lived in one tool, payments in another, revenue data in a third. Every processor change meant a migration. And all of it sat on top of a single processor whose risk team could change our business overnight.
We couldn t find anything that solved all three together, so we built Payment Kit and ran our own volume through it before selling it to anyone.
What it actually does:

• Payment orchestration. Connect the processors you already use. Every transaction is routed to the one most likely to approve it, and soft declines cascade to the next one instead of turning into lost revenue.

• Independent vaulting. Cards, Apple Pay and Google Pay are vaulted as network tokens under your control, not your processor s. Adding or dropping a processor is a routing change, not a migration, and your customers never enter a card again.

• Billing and revenue data in the same place as payments. One system of record instead of three tools that disagree with each other.

The trial is free, so you can poke around without having to talk to a sales person.
If you d rather have someone look at your specific setup, we can set up a quick call. Not a sales thing. We spent a few years on the wrong side of these problems and most of what we learned is more useful in a conversation than on a landing page. Drop a comment here or find me on the product page.
Thanks again!

Road to 1,000,000 Votap users Day 76 | Current: 1463

When we started building @ProdShort , our first instinct was to make the product "ready" before showing it to anyone. Then we started seeing founders launching much earlier. Sometimes with nothing more than a landing page, just to see if people were interested enough to sign up... or even pay.

It completely changed the way we thought about validation. On one side, launching early gives you real feedback much faster. On the other, launching too early can make people leave before they see the real value of your product.

We're still not sure there's a perfect answer.

We launched Traccia on Product Hunt yesterday and finished #6 Product of the Day.

But honestly, the ranking isn't what stayed with me.

It was the support from the community.

247 upvotes, 34 comments, finished second on a Sunday. The July launch got 362 and finished third. Better rank, smaller day. Both true.

The comments were worth more than the votes. A few things I didn't have good answers for, which is more useful than an upvote.

Huge, huge thank you to everyone who supported us with their kind notes, reviews and votes during our launch yesterday!!!

We have blown all the tools competing against us out of the water with the whopping 495+ points. We competed against some INCREDIBLE companies - including Cursor and Open AI!!

Excited to share that we have improved our Search flow in Recall! Search has moved out of the small popup and into your library, so results now fill the full page. That means a lot more room to see what you've found, and everything you'd normally do with your cards still works on the results. FYI: The improvement lands on desktop first, with a mobile overhaul to follow shortly.

Check out our quick video walkthrough of how it works.

Every fast-growing company seems to have the same quiet migration story. They picked an auth tool early because it was fast to set up, free enough that nobody really had to think about it, and honestly, it was probably the right call at the time. Nobody is evaluating whether a login system can survive an enterprise deal when they are 10 people and just trying to ship the product.

Then the growth actually happens. The company gets to 50 employees, maybe starts selling to bigger customers, and the first serious enterprise prospect sends back a procurement checklist with SSO sitting somewhere near the top, non-negotiable. That is usually when you realise SSO lives on a tier that costs more than the entire tool used to cost you, or in some cases is not even available anywhere near the plan you are already three years deep into. So now you have a migration project nobody planned for, timed exactly when the company can least afford the distraction. And auth migrations are not exactly like swapping out an analytics tool. They touch active sessions, integrations built against the old system, login flows, permissions, and every customer already using the product, all while the deal that triggered the panic is still sitting in procurement waiting for an answer.

I don't really think this is a story about any one vendor being careless. It feels more structural than that. Tools built to be generous and fast at the small end tend to hit a hard ceiling right when a company starts needing enterprise features. And tools built enterprise-ready from day one usually come with an onboarding process and cost that a five-person team has absolutely no reason to take on early. There is a weird gap in the middle where very few products seem designed around the assumption that the same company might actually grow from one end to the other while staying on the same stack.

Has your team already hit that wall, or are you still early enough to see it coming before it costs you a deal?

I ve been thinking about how much the day of a Product Hunt launch actually matters.

Product Hunt resets the leaderboard at midnight PST, so every day is essentially its own race with a different set of launches.

AI is becoming better and better. For writing, coding, and research, doing everything manually already feels like wasted time.

But some work still needs a real person to take responsibility. Lawyers, accountants, and anyone who must review and sign documents for institutions. AI can prepare the work. Someone still has to stand behind it.

Meridian is currently the #2 Product of the Day on Product Hunt, and your support could help us reach the top.

We built Meridian as an open-source, local-first AI work journal that runs entirely on your device. It turns your daily activity into a clear timeline, matches work with Jira and GitHub tickets, and drafts worklogs and updates for your approval.

Meridian is MIT-licensed, private by design, requires no account, and is free for individual developers.

As one of Meridian s makers, I d love to hear from other makers: what would make you trust an AI-generated worklog? Please support our launch and share your honest feedback.

Been on this platform a month now, and genuinely think the people here are sharper than what i've found anywhere else.
Curious if that's actually held true for others when it comes to hiring.
Have you hired someone you found on ph, or been hired yourself through here.
Also curious what your actual go-to platform is for finding people, ph, linkedin, twitter or somewhere else entirely.

Select is a curated day of talks by @Supabase and the industry's best builders. It will take place on October 2nd, in San Francisco, CA.

If you've been building on Supabase (or thinking about it), this is where you see what's next first and where you meet their team.