logoalt Hacker News

Seattle3503 • today at 1:32 AM • 0 replies • view on HN

I still use plan mode, but during plan mode I will spin out sub agents to implement the current draft in a tmp dir and bring back lessons. I feel this keeps me grounded in my original starting point, rather than ending up with a implemention that meanders through the agents own discovery process. It also lets me ask concrete questions about (possible) implementation