Clip / AI Tools

Verification is the thing people get wrong

From Boris Cherny: We Cut 80% of Claude Code’s Prompt · ≈20:13

Locates the real bottleneck in agent engineering — giving the model a way to check its own work — rather than in prompt wording.

What’s in it

Locates the real bottleneck in agent engineering — giving the model a way to check its own work — rather than in prompt wording.

Watch this moment

Clip transcript

think I think these will kind of like come and go. I think the skill nowadays is less about prompt engineering and more about figuring out how do you give Claude a hard task that seems a little bit too hard. And then how do you make it possible for Claude to verify its work along the way? And the verification I think is probably the single most important thing that people do not get right or actually. Um