Microsoft Developer
@msdev
Introducing run-assert-eval.
With a single prompt in @code, the skill identifies risks specific to your agent, measures how often they occur, generates runtime policy based on those findings, and reruns the same eval to see whether the policy worked.
commandline.microsoft.com/run-assert-eva…
With a single prompt in @code, the skill identifies risks specific to your agent, measures how often they occur, generates runtime policy based on those findings, and reruns the same eval to see whether the policy worked.
commandline.microsoft.com/run-assert-eva…
commandline.microsoft.comIntroducing run-assert-eval: Find the risk, fix it, prove it
14 181