Command CenterRequests/min
--
Loading...
P95 Latency
--
Target: <1000ms
Error Rate
--
Target: <1%
Active Instances
--
Auto-scaling enabled
🔧 Backend API
Service: artemis-consolidated
Latency: --
Version: --
🌐 Frontend App
Service: artemis-superior-ui
Latency: --
Region: us-east4
🗄️ Database
Type: PostgreSQL 14
Segments: 4,260
Region: us-east4
🤖 AI Models
Routing: Multi-Model Active
Models: Haiku, Sonnet 3.5, Sonnet 4.5
Savings: ~60% cost reduction
📈 Request Rate (Last Hour)
⏱️ Response Time (P50, P95, P99)
💻 CPU Utilization
🧠 Memory Utilization
👥 Active Sessions
--
Real-time users
🎯 Targeting Queries
--
Last hour
✅ Completions
--
Conversations completed
💾 Cache Hit Rate
--
Target: >70%
🗄️ Database Connections
⚡ DB Query Time (ms)
🖥️ Database CPU
📊 Database Memory
📋 Recent Logs (Errors & Warnings)
Loading...
--