Skip to main content

​
Getting Started

This guide will help you set up AccelOS and run your first AI-powered incident investigation.

​
Prerequisites

Before you begin, ensure you have:
  • An AccelOS account (contact support@accelos.com for access)
  • Admin or Owner role in your organization
  • Credentials for at least one observability tool (Datadog, Grafana, etc.)

​
Step 1: Log In to AccelOS

1

Access the Dashboard

Navigate to your AccelOS instance URL (e.g., https://accelos.com) and click Log In.
2

Authenticate

Sign in using your organization’s SSO provider or the credentials provided during onboarding.
3

Select Your Team

If you belong to multiple teams, select the team you want to work with.

​
Step 2: Connect Your First Integration

Integrations allow the AI agent to query your observability tools. Let’s connect your first one.
1

Navigate to Integrations

From the sidebar, click Integrations.
2

Choose an Integration

Select the integration you want to connect. We recommend starting with your primary monitoring tool (e.g., Datadog, Grafana).
3

Enter Credentials

Provide the required API credentials. See Integrations for detailed instructions for each integration.
4

Test Connection

Click Test Connection to verify the integration is working correctly.
Start with Datadog or Grafana as your first integration - they provide the richest context for incident investigation.

​
Step 3: Set Up Your Knowledge Base

The Knowledge Base stores runbooks, procedures, and learnings that the AI agent can reference during investigations.
1

Navigate to Knowledge Base

From the sidebar, click Knowledge.
2

Create Your First Runbook

Click New Document and select Runbook as the template.
3

Add Content

Document a common incident type your team handles. Include:
  • Symptoms and how to identify the issue
  • Step-by-step remediation procedures
  • Escalation paths if needed
4

Save and Publish

Save your runbook. It’s now available to the AI agent.

​
Step 4: Start an Investigation

Now you’re ready to use the AI OnCall Agent!
1

Open the Investigations Panel

From the sidebar, click Investigations.
2

Describe the Issue

Type a description of the incident you want to investigate. For example:
High latency alerts firing on the checkout service.
Started around 2:30 PM UTC.
3

Let the Agent Investigate

The AI agent will:
  • Query your connected integrations for relevant data
  • Search your knowledge base for related runbooks
  • Analyze patterns and correlations
  • Present findings and recommendations
4

Follow Up

Ask follow-up questions to dive deeper:
Can you check the database metrics during that time?

Are there any similar incidents in the past week?

​
Example Investigation

Here’s what a typical investigation looks like:
“We’re seeing 5xx errors spike on the payment service. Can you investigate?”
The agent will:
  1. Query Datadog/Grafana for error rates and latency metrics
  2. Pull recent logs from the payment service
  3. Check for recent deployments or changes
  4. Search the knowledge base for payment service runbooks
  5. Present a summary with potential root causes
You can then ask:
  • “What changed in the last deployment?”
  • “Show me the database connection pool metrics”
  • “Are other services affected?”

​
Next Steps

Connect More Integrations

Add more observability tools for richer investigations.

Build Your Knowledge Base

Document your runbooks and procedures.

Invite Team Members

Add your team and configure permissions.

Explore Integrations

See all available integrations.

​
Getting Help

Need assistance? Contact our support team at support@accelos.com or check the detailed guides in this documentation.