Episode Player

Boris Cherny, the creator of Claude Code, recently shared his personal workflow — and the idea at the center of it is one that serious AI builders keep arriving at independently: the model that wrote the code should not be the model that reviews it. Boris achieves this with subagents running in fresh, isolated contexts. The Chief Engineer workflow achieves it with a separate model entirely. The structure is the same. The only philosophical difference is whether 'independent reviewer' means a fresh instance of the same model, or a different model altogether. This episode explores what that principle is, why it matters, and why two very different practitioners landed on the same answer.

 Produced by VoxCrea.AI

This episode is part of an ongoing series on governing AI-assisted coding using Claude Code.

👉 Each episode has a companion article — breaking down the key ideas in a clearer, more structured way.
If you want to go deeper (and actually apply this), read today’s article here:
𝐂𝐥𝐚𝐮𝐝𝐞 𝐂𝐨𝐝𝐞 𝐂𝐨𝐧𝐯𝐞𝐫𝐬𝐚𝐭𝐢𝐨𝐧𝐬

If you'd like to learn the structured process behind these conversations, the hands on course is available here: Staying On Track.

𝐆𝐨𝐥𝐝𝐞𝐧 𝐀𝐫𝐜𝐡𝐢𝐭𝐞𝐜𝐭 𝐀𝐜𝐚𝐝𝐞𝐦𝐲 is a new community exploring that idea together. Here we discuss the process discussed in 𝐂𝐥𝐚𝐮𝐝𝐞 𝐂𝐨𝐝𝐞 𝐂𝐨𝐧𝐯𝐞𝐫𝐬𝐚𝐭𝐢𝐨𝐧𝐬 𝐰𝐢𝐭𝐡 𝐂𝐥𝐚𝐮𝐝𝐢𝐧𝐞.

 At aijoe.ai, we build AI-powered systems like the ones discussed in this series.
If you’re ready to turn an idea into a working application, we’d be glad to help.