[−]SubiculumCode · 2026-10-11 Sun 02:36 UTC ·
link
So you restricted it to implementing the same function (same inputs,outputs, dependencies as original?) and prevented the agents from making design decisions by keeping it's scope restricted?
[−]brandonpelfrey · 2026-10-11 Sun 03:04 UTC ·
link
Yes. It can gain more context, but this has been enough. Note, there is also a notion of adversarial review layered on top in which it tries to poke holes in the test plan "you didn't handle this case of XYZ". It isn't actually perfect as a parallel thread said it may miss things like wrapping behaviors. In practice, it's very effective.