We launched Operum on Product Hunt.
#28 of ~700. 5x traffic for a day. 6 sign-ups.
Nobody new got their AI team running.
Here's what I learned the day after 🧵👇
The numbers
→ #28 of nearly 700 products that day, 68 upvotes
→ Website traffic up 5x for one day
→ 6 people signed up
→ 0 got as far as a working AI team
For perspective: Linear finished #30 on its first Product Hunt launch, with 64 upvotes. Product Hunt doesn't create demand. It amplifies the audience you already have.
What surprised me
Most messages weren't from users. They were from people selling upvotes, PR, launch services and "collaborations". Dozens of them.
But a few conversations were gold:
"How do you make AI-built apps secure?"
A solo dev quoted my line back to me: "I was the bottleneck, not the AI"
A founder walked through our site like a first-time visitor and found 3 places where we promised one thing and showed another
By the next day, our own AI team had rewritten those pages, with every claim checked against the real product.
The biggest lesson
Operum's AI team works best through @cursor_ai. If you already use Cursor, you get a whole product team on top of a tool you already pay for.
Claude Code and Codex also work, but only with a pay-per-use API key. Fine for one agent, expensive for a whole team working all day. That's not our restriction. It's how Anthropic and OpenAI currently let other products use their models.
So for anyone without Cursor, "subscribe to us AND to another AI tool" is a wall. More visibility won't fix that.
We're not giving up. We're adding new AI engines so more people can try Operum without a second subscription.
What's next
Focusing on builders who already use Cursor, and watching real people set it up for the first time.
I'd rather hear a hundred honest "no"s than one polite "looks great".
So, honestly: what would stop you from trying an AI product team today? The AI engine cost, the setup, trust, or "I don't need it"?
I can change anything I want any time, and i'm constantly changing/adding to my CRM. Because I created it for myself, and exactly how my business and I need it. If I was creating it for the users, I would add a customization functionality with basic changes, so each user could organize their contacts the way they want.
We're live on Product Hunt today 🚀
I'm not a developer.
But over the past months I built my studio website, my own CRM, and a page for the parents of the seniors I photographed this year. Without writing a single line of code.
How? With Operum, the desktop app Alex and I have been building.
Operum gives you a full AI product team:
• PM
• Architect
• Engineer
• Tester
• Marketing
• Community
You describe what you want in plain words. The team plans it, builds it in your own GitHub repo, and tests every change. Nothing ships without your approval.
It works with the AI engine you already use: Cursor, Claude Code or Codex.
And it's not a weekend project. We build Operum with Operum: 5,300+ merged pull requests and 100+ releases since January.
If you've ever had an idea and thought "I'm not technical enough to build that", this is for you.
We'd love your feedback 👇
https://t.co/dt6TV6oTzn
Good idea, thank you. A small demo task on a throwaway repo, showing the diff and the approval step, would answer the trust question before anyone connects a real project. We're also building test setups to measure how much Operum adds to code quality and performance compared with using Cursor alone.
Good question. 4 of the 6 never opened the desktop app, so for most it was the install step. The 2 who opened it got stuck at choosing the AI engine: Operum runs on Cursor, Claude Code or Codex, and you need a paid Cursor plan or an API key. Our guess is that's the wall. We emailed all of them to ask why and offered a call, but no replies yet. Meanwhile we're rewriting the site so the engine part is clear up front.
Thanks! It fits my studio exactly: bookings, clients, my own AI assistant that knows everything about my business and each client, follow-ups. Nothing I don't use. Building it myself was the fun part. 😄 I couldn't believe I could do it, until I switched to it 6 month ago and stopped paying for someone's CRM I didn't like.
Thank you! 📸 Honestly, it all finally came together. Psychology and HR taught me how real teams work. I built software with engineering teams at companies I worked for. Then growing a luxury photography studio taught me the business side. Operum is all of it in one place: an AI team that works like a real one. The best part is getting to use everything you've learned in life.
@matt__makes Haha yes, finally! 🚀 Worth the wait though: we used the extra days to ship Codex support, so now it runs on Claude Code, Cursor or Codex. Would love your honest UX take, Matt: https://t.co/WH9PyjlmV5
Three weeks ago, I shared why we postponed our Product Hunt launch.
Tomorrow, November 10, we’re launching Operum. 🚀
Two days before our planned October launch, we received an email: our proposed use of Claude subscriptions wasn’t approved.
Supporting more AI engines was already on our roadmap. That email moved it to the top.
Since then, we’ve added Cursor and Codex alongside Claude Code, improved onboarding, and strengthened agent isolation. OpenCode is coming next, with local models to follow.
We were also preparing an accelerator application. It pushed Alex and me to think harder about our business model, who we’re building for, and the problems Operum helps them solve.
For me, that’s personal. I used Operum to build my photography studio’s website and the CRM that runs it—without a coding background.
Operum brings six AI specialists into one desktop app. They plan, build, test, and help launch your product, while you stay in control of the decisions.
And tomorrow, we get to share it with the Product Hunt community.
Excited? Yes. Nervous? Also yes.
To everyone who tested, challenged us, encouraged us, or followed along: thank you. 💜
We’ll share the link tomorrow. Come take a look and tell us what you think—honest feedback is exactly what we need.
Our AI team shipped 290 changes in 11 days. Here's why we moved our launch.
On Oct 15 we decided Operum shouldn't be locked to one AI engine.
Since then:
→ 346 commits
→ 290 changes merged
→ 226 tasks closed
→ 2 releases
Most of it was shipped by Operum's own AI agents. We build Operum with Operum.
Result: Operum now runs on Cursor and Claude. More engines are coming before launch.
What Operum is: six AI agents (PM, architect, engineer, tester, marketing, community) that work like a real team. Describe what you want in plain English. They plan, build, test, ship and help you launch it.
Websites, web apps, stores, internal tools, SaaS. No code, no terminal.
Stressful? Kind of. Exciting? Absolutely.
Free tier available. If you already have Claude or Cursor, you're ready.
Honest feedback wanted, good and bad 👇
@lucian_lutas Thank you! Yes, Stripe, this monster is so good, I'm not ready yet to create my own Stripe 😃, but booking is already mine, everything else is build inside the CRM.
For years, the question was: can you code?
I can't. I'm a non-technical business owner.
My whole photography studio runs on software I built anyway.
My website: rebuilt on Wix three times until I loved it. Now I change it myself whenever I want.
Noran Shine CRM: built section by section over four months. Bookings, payments, automations, and an AI assistant that knows every client. My studio runs on it every day.
I build with Operum, a team of AI agents. But the AI isn't the lesson.
The hard part was never the code.
What I learned:
→ Deciding what's worth building is the real work.
→ Describe the problem, not the solution.
→ Before you call it done, use it like your client would.
Developers are learning the same thing from the other side. When code gets easy, the rare skill is knowing what's worth building.
So the question changed.
Not "can you code?"
But "do you know what's worth building?"
What would you build if code weren't in the way?
@irapss_ae We are launching on November 10th on Products hunt with 3 engines. Can't believe that so much changes were made within 2 weeks only. Thank you for asking!
I build AI agents for a living. I still write my own comments.
Last week I left a comment on someone's Product Hunt launch. Nothing clever, just what I actually thought, in my own words.
A few days later, another founder messaged me. He'd read that comment, liked my take, and wanted to connect. Now he's offered to support our launch on Nov 10.
No AI wrote that comment, and I think that's why it landed.
My company, Operum, is a team of AI agents that builds and ships software products. I use AI for almost everything:
research
first drafts
summarizing long threads
finding holes in my thinking
adapting one idea for different platforms
It saves me 2+ hours a day.
But six months ago I set one rule, and I still follow it:
I write my detailed ideas. AI drafts. I publish.
Every post and comment has an idea that's mine, and I read and send it myself. The draft can come from AI; what I say is my decision.
The Blog about it in comments
I built a client landing page in 15 minutes. Without writing a single line of code.
This fall I photographed the senior class at a local school. As a premium studio, I care about more than the portraits. Families deserve a great experience viewing and ordering them too.
I already had my studio website, built from scratch with Operum. This time I needed just one new page for the parents:
→ I described it in plain English
→ My PM talked the structure through with me and suggested something I'd forgotten: an ordering deadline
→ The engineer built it, and the tester checked it
→ 15 minutes later, the preview was ready
The detail I love: the PM made sure the page is hidden from Google, so only families with the direct link can see it. I didn't even have to ask.
The video below was made in Operum too. I recorded my screen, explained what had to stay private, and every child's face is blurred.
I run two businesses, my photography studio and Operum, and I couldn't do it without my Operum team.
Try it, it's free👇