we launched code interpreters for deep agents last month. Basic idea is to let agents plan, delegate, and organize context using code instea…

we launched code interpreters for deep agents last month. Basic idea is to let agents plan, delegate, and organize context using code instead of chained tool calls Code interpreters don't need a sandbox, but we still need a way to securely run that code! (and running untrusted code is a famously hard problem) Here's the writeup on how we're looking to do just that:

Source: Harrison Chase (X) | 2026-06-30