We just released websockets today.

Test coverage is high. I'd recommend checking it out to form your own opinions.

Cool, but it's a bit hard to rotate. Could be more intuitive.

Cool. Will try this with my agent.

Quick comment: the code on the website isn't using any sort of intellisense or highlighting

I can't seem to create tools on https://anytoolhq.com/dashboard. Report back when it works, and I'll give it a try.

Hey thanks for taking a look! Diving in now. support@anytoolhq.com routes to me, happy to chat!

edit: problem found, fixed, and tested.. let me know if you have a chance to try again

I tried creating a tool, it's been stuck "generating" for a few minutes now.

Thanks for testing - i apologize for wasting your time... But I did take a deep look at things and figured out how to make generation of tools more reliable.

If you're still interested, please take another try... I've got more visibility into logs and errors, and it should be much more reliable!

Yes, thank you, I know it's not ideal now. It would make a much better impression.

I plan on adding it soon, after smoothing out the internals.

Some background: I previously built and sold a Chrome extension that reached 30k users, and created an open source tool with around 150 stars and 11k downloads that's been adopted by companies like Goldman Sachs.

I'm now building qoery.com. The product is functional but not fully polished. I have 60 sign-ups but no paying customers yet. The feedback I'm getting from existing users is "improve the product and we'll pay."

I've spent the last two weeks iterating heavily on the product based on this feedback. It's significantly better now, but growth has completely stagnated during this time.

So I'm facing a dilemma: should I keep iterating based on user feedback until I convert those first users to paid customers? Or should I shift focus to customer acquisition and try to find users who might pay for what exists today?

Looking for advice from founders who've been through this.

I would find the customers who are willing to get dirty with you (screen shares, phone calls, etc)., and work only with those people until they are happy paid customers. Having a free tier almost seems like a bad idea for this product from my perspective. I'd want to interview my customers and pick carefully at first.

Hi Bob,

I see what you're saying. Stay laser-focused on potential enterprise customers, and iterate with them until they pay.

The users that you have but are not paying: what they're complaining about or find a lack of? Are there any emergent patterns? Or everybody wants basically something completely different?

This is brilliant advice. I'll email my users to find out.

I can't tell how this differs to Cursor from your website. How is it different?

A bunch of specific things below, but the main point is that it integrates a bunch of features that data scientists use that don't come with Cursor.

Specifics (mostly reproduced from above):

1. R/Python/Julia consoles accessible by the user and AI

2. Optimized jupytext system for editing notebooks efficiently

3. Plots pane for viewing and tracking plots

4. Databases pane for managing SQL/FTP connections

5. Environment pane for managing Python/R/Julia packages and environments

6. Help pane for documentation

7. An AI that interacts with all of that.

8. Open source AGPLv3

For me, the biggest difference in the AI usage is that the AI doesn't need to write one-off python scripts for everything and run them from the terminal because it can just use the console directly.

Type 'EV adoption rates in Norway' and get a formatted time-series CSV in 10 seconds. That's the entire product. Statista charges €490/month for literally the same thing.

Still early and has rough edges: some queries fail, source citations need work, and the UI is... functional. But it works well enough that I've stopped paying for Statista. Which is wild because most of this data is already public anyway.

Free tier is live at qoery.com. What data would you search for first, and did it actually work?