Common use cases

The patterns below each represent a complete workbench setup for a common operational need. For each one, the agent's behavior is shaped by skills — pre-built instruction documents from Plural's skills library, or custom runbooks from your own Git repository. You do not need to write a system prompt from scratch; attach the relevant skills for the use case and add a brief system prompt to orient the agent to your platform if needed.

Alert root cause analysis

Automatically investigate every firing alert and produce a structured root cause analysis with remediation suggestions.

How it works

When an alert fires in Datadog, Grafana, or another supported provider, a webhook trigger creates a workbench job. The agent immediately begins querying the relevant service, its Kubernetes resources, logs, and metrics. When it finishes, the job result contains a diagnosis, the signals that led to it, and concrete next steps.

Setup

Capabilities:

• Infrastructure: Services, Kubernetes, Pod logs
• Observability: Metrics, Log aggregation

Tools: Attach a Prometheus or Datadog tool with credentials for your metrics backend.