Nondeterministic output needs its own evaluation layer, so ServiceNow built an LLM judge that scores against a golden data set before anything reaches a customer.

Users did not want the agentified version of the human process. They wanted the outcome and the next best action, not the steps.

The fix was a feedback loop that narrates what the AI is doing in the background, which buys the patience a long task needs.

The agentic skills worked. Users still abandoned them, because a five to fifteen minute wait broke their expectation of what AI should feel like.

ServiceNow is its own Customer Zero, running the platform on itself and testing every feature internally before customers see it.