Sentinel
AI quality monitoring overview
Evaluate-not-assert monitoring for chatbots, copilots and agents.
The Sentinel page (AI control plane)
Monitor live AI agents: report runs, score them, and apply guidance.
Evaluators and scoring
The five evaluators, configuration, self-consistency and the safety backstop.
Eval suites and CI gates
Golden datasets, the red-team preset, and gating deploys on AI quality.
Model compare and KB grounding
A/B models with an independent judge; semantic knowledge-base grounding.