Skip to navigation
Custom Dashboards

Safety

Monitor flagged conversations and evaluate how your agent handles harmful content. Without regular safety reviews, harmful content can reach users or trigger compliance violations you only discover after the fact.

Safety dashboard

Metrics

MetricWhat it shows
Caller utterance risk levelHow risky incoming messages are and how well the agent manages them
Total callsTotal call count during the selected period
Calls managed for riskHow often safety filters were triggered (count and percentage)
Distribution of flagged callsTrends in flagged calls over time
Caller utterance categoryBreakdown by hate, self-harm, sexual content, and violence

Configuring filters

Safety filters are configured project-wide in Behavior and overridden per channel in Voice and Messaging. See Safety filters for the full reference – categories, severity levels, language support, and how filters fit with Guardrails.

Safety filters

Configure per-channel filter categories and severity levels.

Standard dashboard

Day-to-day performance monitoring: containment, call volume, and duration.

Conversation review

Inspect individual flagged conversations in full transcript view.