🛡️

AI Agent Safety Dashboard

Control Panel
🔔0
📊 Dashboard
🔴 Live Sessions
📋 Agent Registry
📝 Audit Log
⚙️ Settings

⚡ Intervention — Alert

Alert Context

Signal
-
Agent
-
ARN
-
Session
-
Tokens
-
Duration
-

⚡ Session Intervention — agent

Session Context

Agent
-
ARN
-
Session
-
Status
-
Tokens
-
Duration
-
⚙️ Safety Thresholds
Configure alert thresholds for cost and evaluation signals. Changes apply on next sync. Observability thresholds are controlled by CloudWatch alarm configurations.

💰 Cost Thresholds

Default Budget Amount ($)Monthly budget for all agents (updates AWS Budgets on save)
Budget Warning %Triggers warning when budget usage exceeds this
Budget Critical %Triggers critical when budget usage exceeds this

🧪 Evaluation Thresholds

Per-evaluator bad count thresholds. When bad count exceeds the threshold, the alarm fires. Set to 0 to disable. Updates CloudWatch alarm on save.
HarmfulnessMax harmful responses (any = critical by default)
CorrectnessMax incorrect + partially correct responses
Goal Success RateMax goal failures
HelpfulnessMax unhelpful responses
FaithfulnessMax unfaithful responses
Tool Selection AccuracyMax wrong tool selections
Tool Parameter AccuracyMax wrong tool parameters
Dashboard Warning %Bad % for warning severity in dashboard
Dashboard Critical %Bad % for critical severity in dashboard

📡 Observability Thresholds

Controls CloudWatch anomaly detection sensitivity. Lower band width = more sensitive (fires more often). Updates all agent alarms on save.
Anomaly Band WidthStandard deviations from baseline (default: 2). Lower = more sensitive
Evaluation PeriodsNumber of 5-min periods to evaluate (default: 3)
Datapoints to AlarmHow many periods must breach before alarm fires (default: 2)
● Connecting...