Agent Pipeline Latency
—
Avg response time across 3 Gemini agents
Total API Spend
—
Real token costs from Vertex AI
Self-Healing Actions
—
FP rate escalations triggered
Dynatrace Uptime
—
Based on open problem count
Real Pipeline Latency (per transaction)
P95
Actual
Cumulative Vertex AI Spend (USD)
Dynatrace Live Problems
Queried from Dynatrace /api/v2/problems every 30s
Loading...