Generate Check Rules with Agent0

Agent0 is Dash0's AI assistant that generates check rules from natural language descriptions. This is the fastest way to create check rules, requiring no knowledge of PromQL or query building.

Step-by-Step: Generate a Check Rule with Agent0

Follow these steps to use Agent0 to generate a check rule configuration.

Step 1: Open Agent0

Go to Agent0 to begin generating your check rule.

Step 2: Describe What You Want to Monitor

Once you've clicked Dashboards & alerts, select Creating an alert.

Agent0 generates a prompt as a starting point:

As you continue and enter a natural language description of what you want to monitor, continue to click the responses that meet your needs.

Be specific about:

• The service or component you're monitoring
• The metric type (latency, error rate, resource usage, etc.)
• The threshold value
• Optional: notification preferences

Example prompts:

• "Alert me when frontend latency exceeds 500ms"
• "Monitor error rate for payment-service and notify me when it's above 5%"
• "Create a check for database connection pool exhaustion"
• "Alert when the checkout endpoint P99 latency is over 2 seconds"
• "Monitor log errors in the auth service and send to Slack"
• "Track when CPU usage on backend services exceeds 80%"
• "Alert if any service's request rate drops below 10 requests per minute"

Agent0 analyzes your description and automatically:

• Generates valid PromQL queries
• Sets reasonable thresholds based on the metric type
• Configures appropriate grace periods to prevent noise
• Suggests notification channels and severity levels
• Creates summary and description templates with variables

Step 3: Review the Generated Configuration

Examine the complete check rule configuration that Agent0 has created based on your description.

Agent0 generates a complete check rule configuration. Review:

• Query: The PromQL expression that monitors your telemetry
• Thresholds: Critical and degraded values
• Grace periods: Evaluation frequency and trigger delays
• Summary and description: Alert message templates
• Notification channels: Suggested channels (if mentioned in prompt)

What Agent0 generates:

1234
# Example generated query for "Alert me when frontend latency exceeds 500ms"
histogram_quantile(0.99, 
  sum by (le) (rate(d.span_durations{service_name="frontend"}[5m]))
) * 1000

Generated thresholds:

• Critical: 500 (based on your prompt)
• Degraded: 350 (70% of critical, automatically calculated)

Generated summary:

1
Frontend P99 latency is {{ $value }}ms (threshold: {{ $threshold }}ms)

Step 4: Refine the Configuration

Iterate with Agent0 to adjust any aspect of the generated configuration.

If the generated check rule needs adjustments, you can:

• Ask Agent0 to modify specific settings
• Request a different approach
• Iterate on the configuration with follow-up prompts

Refinement prompts:

• "Change the critical threshold to 1000ms"
• "Add degraded threshold at 700ms"
• "Also send notifications to PagerDuty for critical alerts"
• "Change the grace period to 2 minutes"
• "Monitor all services, not just frontend"

Step 5: Use the Configuration

Once satisfied with the generated configuration, copy it to use when creating the check rule.

What to copy:

• PromQL expression
• Threshold values (critical and degraded)
• Grace period settings
• Summary and description templates
• Notification channel suggestions

Further Reading

• About Alert Monitoring — Overview of Dash0's alerting capabilities and how check rules monitor your systems.
• Create Check Rules — Step-by-step guide to creating check rules in the Alerting section.
• Investigate Failed Checks — Troubleshoot failed checks by exploring the underlying telemetry.
• Optimize Alert Messages with Templates — Variables and template functions for creating dynamic alert messages.