The landing page is clean. "$29 one-time vs subscription" against Warp is a strong differentiator, and explaining the App Store limitation upfront builds trust.
Since you asked about workflow: I run multiple Claude Code sessions and the biggest friction isn't organizing terminals, it's remembering what each one was doing when I come back hours later. Subwindow naming helps, but a "last command" preview in the quick switcher would save me from opening each one just to remember where I left off.
One thing worth thinking about: since this is a direct .dmg download (no App Store safety net), your landing page has to do all the convincing. I'd be curious how a first-time visitor reacts before clicking Download. I run testbyhuman.com where a real person screen-records their visit with voice narration. Happy to do a free test on getbeam.dev if you want to see that first impression.
Interesting approach. The core problem you're solving - "not enough real users yet but need behavioral feedback" - is very real for early-stage products.
One gap I'd watch for: AI personas will tend to be too rational. Real first-time users do things no persona model would predict. They misread buttons, get distracted halfway through a flow, form completely wrong mental models of what your product does. The "impatient user" persona is a good start, but actual impatient humans are more creatively confused than any simulation.
We're working on the other side of this at Test by Human (testbyhuman.com) - actual people screen-recording their first time through your product with voice narration. The combination could be strong: use Acceptify for fast iteration loops during development, then validate with a real human before shipping.
Curious how the agent decides when to "give up" on a confused flow vs. keep trying. That threshold seems like it would matter a lot for the quality of the feedback.
Since you asked about workflow: I run multiple Claude Code sessions and the biggest friction isn't organizing terminals, it's remembering what each one was doing when I come back hours later. Subwindow naming helps, but a "last command" preview in the quick switcher would save me from opening each one just to remember where I left off.
One thing worth thinking about: since this is a direct .dmg download (no App Store safety net), your landing page has to do all the convincing. I'd be curious how a first-time visitor reacts before clicking Download. I run testbyhuman.com where a real person screen-records their visit with voice narration. Happy to do a free test on getbeam.dev if you want to see that first impression.