Cooper: AI coding agents prefer complex CLIs with hundreds of flags
Jake Cooper · The Agent-Native Cloud: 3M Users, 100K Signups/Wk, Data Centers, & Death PRs — Jake Cooper, Railway · May 20, 2026 · at 30:18
Railway CEO Jake Cooper discusses how developer tooling and CLI design must adapt when software interfaces are consumed by AI agents rather than human engineers.
“Things that were prohibitively annoying to humans are not actually prohibitively annoying to agents. They're really, really nice, right? And so, if I wanted to hand you a CLI and I said, hey, guess what? The CLI has 40 arguments and. Right. 600 flags. You'd be like, wow, that's crazy. Like, I'm never gonna use all those things in general, right? But if you hand it to an agent and you say, hey, there's 40 arguments and 600 flags, it's going to be like, oh yeah, this is excellent. You know, like I have so many handles that I can go in and kind of like work on with this, right?”
quote is from the automated transcript, cleaned for reading: filler sounds and stutters are removed, nothing is rephrased. names can be misheard (the analysis reads context, assessments check outside sources). how →