Started building finance apps in 2014 (smartfinanceapps.com). Creative itch, as simple as that.
10+ apps since. Killed half. Rewrote the rest more times than I'd like to admit.
Now building an AI factory to grow these and build what's next.
Posting how it goes.
1
2
351
Replying to @BO5AMIS
Real phone is the right call.
Simulators catch a lot for us, but spacing, scroll and the keyboard covering input fields only show up on a device.
Did it catch layout bugs too, or mostly broken flows?
1
1
21
Replying to @ShipToMRR
10+ years freemium, no trial, on my finance apps.
Hard paywall probably wins on day 60. But freemium got me reviews and rankings early, and my first app from 2015 still sells off them.
Replying to @NabhaniMehdi
Comparison page is a good call. I'm rebuilding every app's page now, then I'll rerun the same 59 questions and see if we show up anywhere.
1
3
Replying to @PaulSolt
Product pages matter more for me this year.
Since mid-October ChatGPT sent Money Goals 331 iPhone downloads. Google: 8. Those people skip search results and land straight on the page.
So the page does all the selling.
15
Since mid-October, ChatGPT has sent Money Goals 331 iPhone downloads. Google: 8. Those ChatGPT users buy Pro about twice as often.
So I asked ChatGPT 59 "which app should I use…" questions about my 6 apps.
We showed up in 0.
It reads developer websites first, not the App Store. Now rebuilding every app's page.
1
16
Replying to @UsefulSupplyCo @MaxHirsch13
Yep. Take the debt payoff niche. It's packed with apps, and mine still sells years later because it does one narrow job better than anyone else.
Clone the screens and you're just noise.
19
Replying to @SebastianRoehl
I had an agent doing this for new app ideas. Paused it.
It found plenty of ideas. The bottleneck was me deciding which one to build. What does yours filter on?
19
Replying to @luisnhenrich @conortrains
Haven't switched one yet. Cost per agent and per task comes first, so I know which one is worth testing.
I suspect the setup (founder mode queue via Claude sessions) is not optimal and has room for optimisation as the first step…
6
Replying to @alex_prompter
Had exactly this. Two scheduled agents died on a usage limit, and the morning looked quiet.
Quiet was the bug.
3
Replying to @conortrains
Same boat. Usage exploded once agents ran on schedules, I hit every limit.
What helped so far: most runs are quick passes, one full pass a day, heavy jobs early morning before limits run out. Next step: cost per agent, so I see who burns it.
1
57
We stopped caring which file each tool reads.
Our skills and rules live in one repo, and a sync step installs them into each tool: Claude, Cursor, our own bot. One source, no complexity tax.
29
Replying to @thorstenball
My cure for tab hoarding: founder mode. Every agent's ask lands in one queue, and I clear it in batches, one by one.
When it gets too much, bad luck for whoever's at the bottom.
9
Replying to @MaxHirsch13
Never offline, but I pick when I'm on.
Three kids and a wife won't accept "the agents need me". So the factory queues every ask for me, and I clear it in batches.
8
Replying to @jdluk87
Android is less scary than it looks from iOS.
When Dues sat in Apple review for 3+ weeks, Google approved it in 3 days. Our finance apps run on both now.
Hope the appeal goes through, though.
15
Replying to @MaxHirsch13
Crowded isn't the problem. Copycat is.
All my apps sit in crowded finance niches: debt payoff, savings goals, subscriptions. 10 years in, they still pass review and still sell.
None of them is "another X". Each does one narrow job better than the big ones.
1
41
Replying to @rdominguezibar
About 25 core ones, hand-picked and hand-crafted. Plus a fluid number of tbd skills that come and go.
Think product, support and factory skills etc., plus a set of review/improve routines.
4
Replying to @maxzrco
Ha. Running exactly the same test right now. Mind sharing which layouts you tested?
1
1
32
Replying to @ios_dev_alb
But it's still the best platform on the planet.
Between the $50K MRR posts there are 50 good ones on the topic you care about, especially if it's AI, building or automating.
24

