Skip to main content

Quick Start

Get your first AI-powered investigation running in about 10 minutes.

Prerequisites​

  • A Kubernetes cluster (EKS, GKE, AKS, or self-hosted, version 1.24+)
  • Helm 3.x installed on your machine
  • kubectl access to your cluster with admin permissions
  • A monitoring system with webhook support (Prometheus AlertManager, Grafana Alerting, or Datadog)
  • A Slack workspace (recommended, for receiving investigation results)

Steps Overview​

1. Create Your Account​

  1. Go to app.opsworker.ai and click Sign Up
  2. Sign up with Google SSO or email/password
  3. Verify your email address

2. Create a Workspace​

  1. After signup, you'll be prompted to create your first workspace
  2. Name it something meaningful (e.g., your company or team name)
  3. Workspaces group your clusters, users, and configurations — you can create more later

3. Add Your First Cluster​

  1. Navigate to Configurations → Add Cluster
  2. Name your cluster (e.g., production-us-east)
  3. Select which integrations to enable (you can add more later)
  4. Copy the Helm install command — it includes your unique cluster token

4. Install the Kubernetes Agent​

Run the Helm command from Step 3 in your terminal:

helm repo add opsworker https://charts.opsworker.ai
helm repo update
helm install opsworker-agent opsworker/opsworker-agent \
  --namespace opsworker \
  --create-namespace \
  --set clusterToken=YOUR_CLUSTER_TOKEN

Verify the agent is running:

kubectl get pods -n opsworker

You should see the agent pod in Running state. Back in the portal, your cluster status should show Connected.

5. Connect Your Alerting System​

Configure your monitoring system to send alerts to OpsWorker via webhook. Your webhook URL is available in the portal under Integrations.

6. Connect Slack​

  1. In the portal, go to Integrations → Slack → Install
  2. Authorize OpsWorker in your Slack workspace
  3. Select the channel where investigation results should be posted

7. Run Your First Investigation​

You have three options:

  • Test Integration — Click the Test Integration button in your cluster settings to send a synthetic alert through the full pipeline
  • Wait for a real alert — The next alert from your monitoring system that matches your alert rules will trigger an investigation automatically
  • Use AI Chat — Open the Chat interface in the portal and ask a question about your cluster

Expected Outcome​

When an investigation completes, you'll receive a Slack message containing:

  • Alert summary — What triggered the investigation
  • Root cause analysis — The underlying issue identified by AI
  • Affected resources — Kubernetes resources involved (pods, services, deployments)
  • Recommended actions — Specific steps to resolve the issue, including kubectl commands
  • Feedback buttons — Rate the investigation quality (Accurate, Partially Accurate, Needs Improvement)

The full investigation is also available in the portal under Investigations, where you can see the topology map, collected data, and chat with the investigation for follow-up questions.

Next Steps​