John Michael

We launched PromptQL on X/Twitter 2 weeks back and went viral as the first AI version of slack; and we just went live on Product Hunt! Yesterday Jack Dorsey announced his version, Buzz. And as someone following the space - I see a lot of people having strong opinions about this.
So what's yours? Is slack working for you as you do more and more of your work with AI? Where does it break? Do we even need a new era of collaboration tools?

For me, I feel like the hardest part isn't choosing between tools like React, Firebase, Railway, etc, it's really deciding which parts of the stack I should commit most of my time and tokens early and which ones may become painful to replace later.

Do you stick with a familiar stack and avoid overthinking it, design around expected scale from day one, let your coding agent influence the architecture, or start with the cheapest setup and migrate later? Also, curious which early technical choice has saved you the most time, and which one you wish you probably shouldn't have overthinked on.

Hey Product Hunt community!

I'm the co-founder of Orchestria. While Batu is managing the main launch discussion, I wanted to open a highly technical thread with the engineers, builders, and music producers here regarding our architectural approach.

When we looked at the current generative music space (Suno, Udio, etc.), we realized they all hit the exact same brick wall: they treat music like pixels, rendering a single, uneditable stereo file.
We knew that for real studio production, this is a dead-end. Creators don't want a final master; they want modular components.

To fix this, we avoided standard prompt-to-audio wrappers entirely. Instead, we built an agentic audio pipeline that spins up real, professional-grade, headless VST instruments (like Vital and Surge XT) directly inside our production servers.