Monitoring Setup Guide

# Prometheus / Grafana alerting rules (adapt for your platform)
groups:
  - name: [service-name]-alerts
    rules:

      - alert: [Service]HighErrorRate
        expr: |
          (
            sum(rate([service]_http_requests_total{status=~"5.."}[5m]))
            /
            sum(rate([service]_http_requests_total[5m]))
          ) > 0.01
        for: 2m
        labels:
          severity: critical
          team: [team-name]
        annotations:
          summary: "High error rate on [Service Name]"
          description: "Error rate is {{ $value | humanizePercentage }} (threshold: 1%)"
          runbook_url: "[runbook link]"

      - alert: [Service]HighP99Latency
        expr: |
          histogram_quantile(0.99,
            sum(rate([service]_http_request_duration_seconds_bucket[5m])) by (le, endpoint)
          ) > [0.5]
        for: 3m
        labels:
          severity: warning
          team: [team-name]
        annotations:
          summary: "p99 latency elevated on [Service Name]"
          description: "p99 latency on {{ $labels.endpoint }} is {{ $value | humanizeDuration }}"
          runbook_url: "[runbook link]"

# Datadog monitor configuration (Python SDK or Terraform)
import datadog

datadog.initialize(api_key="[key]", app_key="[key]")

datadog.api.Monitor.create(
    type="metric alert",
    query=f"sum(last_5m):sum:{{service}}.http.errors{{service:[service-name]}} / sum:{{service}}.http.requests{{service:[service-name]}} > 0.01",
    name="[Service] High Error Rate",
    message="Error rate exceeded 1%. @pagerduty-[service-oncall]\n\nRunbook: [link]",
    tags=["service:[service-name]", "team:[team-name]"],
    options={
        "thresholds": {"critical": 0.01, "warning": 0.005},
        "notify_no_data": False,
        "evaluation_delay": 60,
    }
)

┌─────────────────────────────────────────────────────────────────────┐
│  [SERVICE NAME] — Service Health Dashboard           [Time range ▼] │
├───────────────┬───────────────┬───────────────┬─────────────────────┤
│  Error rate   │  p99 Latency  │  RPS (current)│  SLO budget remaining│
│  [BIG NUMBER] │  [BIG NUMBER] │  [BIG NUMBER] │  [BIG NUMBER / days] │
│  vs SLO: 0.1% │  vs SLO: 500ms│  vs avg: [N]  │  [Error budget gauge]│
├───────────────┴───────────────┴───────────────┴─────────────────────┤
│                   Error rate over time (24h)                        │
│  [Time series: 5xx rate line, SLO threshold line]                   │
├─────────────────────────────────┬───────────────────────────────────┤
│  Latency percentiles over time  │  Request throughput over time     │
│  [Lines: p50, p95, p99, p999]   │  [Bars: RPS by endpoint]          │
│  [SLO threshold horizontal line]│                                   │
├─────────────────────────────────┴───────────────────────────────────┤
│  Latency heatmap (all requests — shows distribution shape)          │
├─────────────────────────────────┬───────────────────────────────────┤
│  CPU utilisation over time      │  Memory utilisation over time     │
│  [All instances/pods — lines]   │  [All instances/pods — lines]     │
│  [Alert threshold: 80%]         │  [Alert threshold: 85%]           │
├─────────────────────────────────┴───────────────────────────────────┤
│  DB: connection pool utilisation│  DB: query latency (p99 per query)│
├─────────────────────────────────┴───────────────────────────────────┤
│  [Business metric 1 over time]  │  [Business metric 2 over time]    │
│  e.g. Payment success rate      │  e.g. Orders created/min          │
└─────────────────────────────────┴───────────────────────────────────┘

┌─────────────────────────────────────────────────────────────────────┐
│  [SERVICE NAME] — Dependency Health                                 │
├─────────────────────────────────────────────────────────────────────┤
│  For each dependency: error rate | latency | current status         │
│  [Database]    [N]% errors | [N]ms p99 | ● Healthy / ⚠ Degraded    │
│  [Redis]       [N]% errors | [N]ms p99 | ● Healthy                 │
│  [External API][N]% errors | [N]ms p99 | ● Healthy                 │
├─────────────────────────────────────────────────────────────────────┤
│  Outbound call latency over time (one line per dependency)          │
├─────────────────────────────────────────────────────────────────────┤
│  Circuit breaker / fallback state (if implemented)                  │
└─────────────────────────────────────────────────────────────────────┘