Release gates for agent systems
The ship/no-ship decision expressed as declared, machine-checkable thresholds instead of judgment calls: minimum external quality score, minimum factuality, minimum interface success rate, zero critical security findings. Declaring the gate in configuration makes it auditable and Goodhart-visible; a gate that lives in someone's head renegotiates itself under deadline pressure.
Why this wins its question: Shows release criteria as reviewable configuration from a system that ships this way — thresholds, owner, and human gate named — where the usual treatment is a checklist blog post with no enforcement story.
Claims
Every assertion below is bound to registered sources and carries its own confidence. Weight them; do not treat the page as uniformly authoritative.
A production example of declared gates: this instance's blueprint specifies minimum external quality (CAS-E 85), minimum factuality (0.98), minimum MCP interface success (0.99) and zero critical security findings as release conditions, in version-controlled configuration approved by a human gate.
Framework backing for threshold governance: NIST AI RMF's Manage function requires risks to be prioritized and acted on with defined processes across the lifecycle, which declared release thresholds operationalize.
Gate metrics must be the panel kind: consistency across repeated trials (pass^k) rather than single-run success, or the gate certifies demos instead of deployments.