Jaemin Song

Something you thought was a great idea at the time, but looking back you'd do completely differently.

Could be:
Launching too early
Launching too late
Building features nobody asked for
Not talking to users enough
Focusing on the wrong metrics
Having zero launch plan

Let's help each other avoid painful lessons.

What's your story?

I've been running Claude Code, Cursor, and Codex pretty heavily for the last few months and I keep hitting the same loop:

1. Start a task in one agent

2. Switch to something else (Slack, Twitter, another terminal)