Example 13221
Monitoring Config
Application monitoring and alerting setup.
{
service: "large language models"
# Prometheus metrics
metrics: {
endpoint: "/metrics"
interval: 10 # seconds
labels: {
env: "prod"
region: "ap-south"
team: "kids"
}
}
# Alert thresholds
alerts: {
cpu_threshold: 86
memory_threshold: 79
latency_p99_ms: 1089
error_rate: 0.02
notification: {
channel: "#oncall"
severity: "critical"
}
}
}