Krystian N-Ł.

shipped a first launch once, still remember every comment. human-ai coexistence framing is the right instinct, way more defensible than "10x productivity" bets everyone else is making. curious what the retention curve looks like past week two.

this is a strong wedge. custom panels instead of preset bundles makes a lot of sense - especially for people tracking specific protocols (fasting, hormones, performance, longevity). the real win here isn’t just “AI doctor”, it’s reducing waste: – fewer irrelevant markers – fewer separate lab visits – clearer interpretation layer curious how you’re thinking about longitudinal tracking and...

this hits. most people don’t want to “build an agent” - they just want the skill and the outcome. turning SOPs into installable skills is a strong move. feels like the app store moment for agents. curious how you’ll handle quality as it scales 👀

this is a W. screen recording in, polished demo out - no timeline headaches. on-device processing is the cherry on top. nice one 👏

this is lowkey dangerous in the best way one script tag and suddenly your site isn’t a brochure anymore it’s a room turning traffic into presence is a power move minimal surface, heavy impact clean execution. respect.

auto-annotation cool til your model learn nonsense human in the loop ain’t weakness that’s control speed without discipline? just faster mistakes data clean > hype loud

finally someone admitting the obvious most language apps are gamified flashcard machines if you can’t speak after 300 days, the streak was the product - not the language making speaking the core loop just makes sense