Agent Ops Monitor

Operational cockpit for monitoring autonomous agent infrastructure health, service metrics, and incident history.

Features

Signal Feed: Real-time alerts with escalation + acknowledgement controls
Service Metrics: Keep thresholds and trends visible next to active incidents
Incident Timeline: Show latest actions for quick war-room context
Environment Aware: Swap context (production vs staging) via props

Examples

Production Overview

Production infrastructure

Operations command center

Uptime 99.97%

3 signals

Live signals

Agent routed

Latency spike in us-east

Critical

P95 latency increased from 410ms → 930ms over the last 5 minutes

Owner · Agent Atlas2m ago

Drift detected in embedding model

Warning

Sentiment accuracy decreased by 4.8 pts vs. reference dataset

Owner · Agent Mira8m ago

Backup pipeline

Healthy

Nightly backups completed · 0 errors

Owner · Agent NovaCompleted

Service metrics

Targets

P95 latencyTarget < 550ms

930ms

Error rateTarget < 1%

0.8%

Agent availabilityTarget > 99.9%

99.7%

Latest incidents

Failover to eu-west orchestrator06:42

Action · Monitor

Customer impact flagged for tier-1 accounts06:55

Action · CS notified

Incident Response

Production infrastructure

Operations command center

Uptime 99.92%

3 signals

Live signals

Agent routed

Vector db replica lag

Critical

Replica lag is 28s (> 10s threshold). Agents throttled to 60 req/min

Owner · Agent Atlas1m ago

API 500s

Warning

Tool execution route returning 2.6% 500 errors for tier-1 customers

Owner · Agent Pulse3m ago

Backup pipeline

Healthy

Nightly snapshot completed. Verifying restore checksums

Owner · Agent NovaCompleted

Service metrics

Targets

P95 latencyTarget < 550ms

780ms

Error rateTarget < 1%

1.2%

Agent availabilityTarget > 99.9%

99.3%

Latest incidents

Triggered read-only mode06:30

Action · Monitor lag

Routed backups to secondary region06:42

Action · Confirm ETL status

Staging Sandbox

Staging infrastructure

Operations command center

Uptime 99.5%

2 signals

Live signals

Agent routed

Staging data refresh

Warning

Refresh pending security approval. Tokens expire in 4h

Owner · Agent RelayPending

Preview environment

Healthy

Preview deployment succeeded · build #812

Owner · Agent ForgeNow

Service metrics

Targets

Deploy successTarget > 95%

97.1%

Preview latencyTarget < 600ms

420ms

QA coverageTarget > 80%

84%

Latest incidents

No recent incidents.

Installation

npx shadcn add "https://agents-ui-kit.com/c/agent-ops-monitor.json"

API Reference

AgentOpsMonitor

Prop	Type	Default	Description
environment	`string`	`"Production"`	Environment name in header
uptime	`string`	`"99.97%"`	Uptime badge
signals	`OpsSignal[]`	Sample signals	Live alerts feed
metrics	`OpsServiceMetric[]`	Sample metrics	Service metrics cards
incidents	`IncidentEvent[]`	Sample incidents	Recent incident timeline
onAcknowledge	`(signal) => void`	-	Called when acknowledging a signal
onEscalate	`(signal) => void`	-	Called when escalating
onExportReport	`() => void`	-	Fired by export button
className	`string`	-	Tailwind overrides

Types

interface OpsSignal {
  id: string
  title: string
  status: "healthy" | "warning" | "critical"
  detail: string
  owner?: string
  lastUpdated?: string
}

interface OpsServiceMetric {
  label: string
  value: string
  threshold: string
  trend: "up" | "down" | "stable"
}

interface IncidentEvent {
  id: string
  timestamp: string
  summary: string
  actionNeeded?: string
}

Design Notes

Signal list wraps in ScrollArea for consistent height in docs
Buttons follow h-7 sizing for secondary actions
Status badges reuse blue/emerald/amber/red palette established across the kit