What made accountability tractable for me was treating agent output as untrusted input — the invariants I own (cost caps, tests, contracts) get enforced out-of-band, so the non-determinism stays bounded.
Only in the bleeding edge/kool-aid drinking bubble. I’m in a company that’s taking a gradual approach and supporting us with budget when we want to explore ways it might make us more efficient, but not setting any mandates. And we still have the expectation of understanding the output as if we’d written it.
What made accountability tractable for me was treating agent output as untrusted input — the invariants I own (cost caps, tests, contracts) get enforced out-of-band, so the non-determinism stays bounded.
We're building MCP server reliability monitoring — has anyone been burned by silent failures? Would love to talk.vouqis.tech
> Is anyone else going through this
I thought this became the norm already, isn't the whole industry working in the same way at the moment?
Only in the bleeding edge/kool-aid drinking bubble. I’m in a company that’s taking a gradual approach and supporting us with budget when we want to explore ways it might make us more efficient, but not setting any mandates. And we still have the expectation of understanding the output as if we’d written it.