Monitoring and evaluating AI systems in AI Control Tower

Continuously monitor your ServiceNow and external AI systems to determine whether they meet quality and safety standards, and investigate root causes when they don't.

Get started

ExploreLearn how monitoring and scoring models work.	ConfigureActivate evaluation and configure metric templates.	Review scoresReview quality and safety scores across your AI portfolio.
Investigate sessionsDrill into sessions to find and fix root causes.	ReferenceEvaluation metrics, fields, and system values.

• Exploring AI system monitoring in AI Control Tower
  Learn how AI Control Tower automatically scores live AI interactions against quality and safety metrics using an OpenTelemetry-based data model of sessions, traces, and spans.
• Configuring monitoring and evaluations in AI Control Tower
  Set up monitoring in AI Control Tower by activating evaluations, adding metrics, and configuring metric templates.
• Reviewing quality and safety scores
  Determine whether your AI systems are meeting quality and safety targets by reviewing scores and evaluation trends.
• Investigating low-scoring sessions
  Narrow a quality or safety issue from a broad score to a specific cause by reviewing evaluated sessions and session details.
• AI Control Tower evaluations reference
  Reference topics provide additional information about the evaluation metrics in AI Control Tower.