MORE

Service Mapping Icon

Operational Intelligence

ServiceNow® Operational Intelligence lets IT proactively analyze IT infrastructure to spot issues and prevent service outages. Using advanced machine learning to analyze information about IT infrastructure, the application automatically determines dynamic thresholds and identifies anomalies that may indicate potential service outages.


Operational Intelligence, an add‑on application to ServiceNow Event Management, is a key, preventive ingredient in a service‑centric, complete solution for eliminating service outages that includes proactively identifying service issues, pinpointing service outages, and automating remediation.
 

 

 

Benefits

Prevent service outages with proactive identification of potential infrastructure problems

Pinpoint disruptions by using data about your infrastructure items to analyze the root cause of outages

Application Highlights

Out-of-bound infrastructure metrics indicate potential issues

Out-of-bound infrastructure metrics indicate potential issues

Out-of-bound infrastructure metrics indicate potential issues

Infrastructure anomalies become alerts for preventive action

Infrastructure anomalies become alerts for preventive action

Infrastructure anomalies become alerts for preventive action

Create custom views of infrastructure metrics to investigate issues

Create custom views of infrastructure metrics to investigate issues

Create custom views of infrastructure metrics to investigate issues

Feature Details

All
  • Automated Thresholds for Infrastructure Metrics

    By adding ServiceNow Operational Intelligence to Event Management, IT can use operational metrics to detect out‑of‑band behavior of infrastructure items, which may not be captured by events.

    Rather than processing events from monitoring tools, Operational Intelligence processes raw operational metric data instead. It then applies machine‑learning algorithms to automatically create dynamic thresholds for normal behavior, eliminating the need to manually set and manage hundreds or thousands of monitored thresholds.

    Operational Intelligence learns the data pattern, sets what the upper and lower bounds should be, and adjusts the threshold for seasonality

  • Infrastructure Anomaly Detection

    With the automated threshold in place, Operational Intelligence can apply to each infrastructure item attribute an anomaly score, which is relative to a respective threshold. High anomaly scores indicate that an infrastructure item may be at risk to cause a service outage. 

    Anomalies can be promoted to become alerts on the alert console and service health dashboard for preventive action. Instead of waiting for monitoring tools to indicate something is wrong based on a set rule, IT can start seeing trends and anomalies in real‑time before services fail.

  • Metric Explorer

    Operational Intelligence’s Metric Explorer enables IT to use operational metrics data to triage alerts, correlate metrics to better understand probable causes of issues, and easily identify probable causes by using a service history view that includes changes.

    IT can browse, search, and compare metrics across multiple infrastructure items and can create and share metric views with other operators.

Resources

Operational Intelligence Is Part of...

IT Operations Management functional illustration

IT Operations Management

Proactively eliminate service outages and manage hybrid clouds.