Coding agents work best for people who already think in small steps
Quote
process you already take is one where you take a large... thing and boil it down into a small series of steps. And so you just, you naturally sort of
Episode 263: Chat is Dead (episode page, opens in a new tab) 00:05:54 (play audio from this timestamp, opens in a new tab)
Voice-matched
Summary
Dave thinks the coders who succeed with AI agents already break big projects into small series of steps and naturally talk that way. It helps even more on a mature repository with established patterns, like the 100,000+ lines of Podcast Index code, where adding an endpoint just means following what's already there.
Not in the audio. The setup 'coders who are very successful with using AI agents...' is partly in an Unknown-labeled cue just before the quote.
Also said
Episode 263: Chat is Dead (episode page, opens in a new tab) 00:02:24 (play audio from this timestamp, opens in a new tab)
AI coding... has worked pretty well for my use cases because There was already a large existing code base.
Voice-matched