Settings control how your tenant classifies AI response confidence, what automated actions to take based on those classifications, which AI model providers are available for routing, and how external applications and agents authenticate to AskRAI. The Settings page organizes these controls into a sidebar-driven navigation.
Confidence Thresholds
Tune the score boundaries that classify AI responses into high, medium, and low confidence bands.
Escalation Rules
Define automated actions — tickets, reviews, or suppression — that fire based on confidence scores.
Model Providers
Connect your own AI model providers (BYOM) for use in routing configuration.
Programmable Access
Issue API, CLI, and MCP credentials for external applications and AI agents, with tenant-wide rate limits and per-credential overrides.
Alert Preferences
The Alerts tab is coming soon. Once available, it will allow you to configure notification preferences for escalation events and system alerts.