Skip to main content

Example Prompts

Overview​

Use these prompts as starting points for AI Chat conversations. Customize resource names and namespaces to match your environment.

Kubernetes Investigation​

Why is pod my-app-7d8f9b6c4-x2k9p failing?
Show me events in namespace production from the last hour
What are the resource limits vs actual usage for deployment api-gateway?
Are there any pods in CrashLoopBackOff?
What's the exit code for the last crashed container in deployment worker?

Service Health​

Is service payment-api healthy? Check its endpoints.
Show me the endpoints for service user-service in production
Are there any services with no healthy backends?
What's the readiness probe configuration for deployment api-gateway?

Log Analysis​

Show me error logs from deployment api-gateway in the last 30 minutes
What exceptions are occurring in namespace staging?
Find any OOM-related messages in logs for namespace production
Show me the last 50 log lines from pod worker-abc123

Configuration Review​

Show me the environment variables for deployment worker
What's the ingress configuration for frontend?
Compare the resource limits of all deployments in namespace production
What configmaps are mounted by deployment api-gateway?

Topology & Dependencies​

What services depend on database-service?
Show me the full topology for the payment processing flow
What ingress routes traffic to api-gateway?
Which deployments are in namespace production?

Change Tracking (requires Git integration)​

What PRs were merged today?
Show me recent commits to the Kubernetes manifests repo
Who last changed the deployment config for api-gateway?

Grafana Metrics & Logs (requires Grafana MCP integration)​

Run a PromQL query: rate(http_requests_total{namespace="production",code=~"5.."}[5m])
Search Loki logs for "connection refused" errors in namespace production
What Grafana dashboards exist for the payment service?
Show me the CPU and memory utilization panels from the API gateway dashboard
Are there any Grafana alert rules currently firing?
Who's currently on call according to Grafana?
What annotations were added in the last 24 hours?

Datadog Metrics (requires Datadog integration)​

What's the error rate for service api in the last hour?
Show me the CPU usage trend for namespace production
Are there any Datadog monitors currently alerting?

Tips for Better Prompts​

  • Be specific — Include resource names, namespaces, and time ranges when you can
  • Ask follow-ups — The chat maintains context, so you can ask "Why?" or "Show me more" after any response
  • Name the resource type — "Show me the deployment config" is better than "Show me the config"
  • Combine concerns — "Are there any pods with high restart counts AND high memory usage?"