Building https://t.co/5Pr4g958ZE for personal trainers.
Automate your entire coaching stack with ai so you can focus on training clients.
Scale your expertise with a coaching platform that understands and remembers how you like to program for clients.
Trying to make it easier for coaches to diff the actual prescribed sets / reps vs. actually completed sets / reps. Surprisingly dense how much information you need to capture when logging workouts. Eventually, the idea is to feed all this data to an AI
Easy way to do some e2e tests in the background: use the playwriter mcp tool to go through test cases that you've written out / described in a markdown file, and let claude / cursor go to town
From now on, hype-centric splashy launches will likely be strongly uncorrelated with success.
If by the time you launch you donโt have escape velocity, you will likely get Sybil attackedยน. Agents will spin up 10 competing products with your same interface.
Start with an audience of 1 and get confirmation that it works. Then expand to a circle of friends or design partners. By the time you go public, your moat needs to be deeper than itโs ever been.
ยน https://t.co/aAhxdYwkv7
For anyone who has domain knowledge, agents / ai are a massive accelerator, but I just dont see how you can really vibe your way to expertise if all you're doing is spitting out junk
It's wild the bubble that we live in. People here on twitter / in SF are talking about ralph loops / agent orchestration, meanwhile back in Hong Kong, folks are still copy pasting into chat gpt.