<img src="//bat.bing.com/action/0?ti=5739181&amp;Ver=2" height="0" width="0" style="display:none; visibility: hidden;">

IT Operations

Can Artificial Intelligence Solve Alert Fatigue?

It’s a well known fact that IT operations are subjected to more alerts than they can handle.

Companies use a wide variety of tools to monitor their operations. Each of these tools generates its own incidents, alerts and notifications.

It’s gotten to the point where tools have cropped up just to help IT ops manage their alerts.

Let’s reflect on this for a moment.

Ops tools are meant to help operations with their day-to-day work. But they are generating so much overhead that additional tools are necessary just make any functional sense of them.

This is a lose-lose. Ops teams either miss out on relevant information or are forced into managing yet another tool in an already overcrowded stack.

A more intelligent solution would:

  • Monitor entire environments for noteworthy events
  • Perform full root cause analysis of identified events
  • Use alerts generated by other tools to assist in contextualization 
  • Aggregate all the above to report only an actionable number of the most pressing issues happening each day

We Take Alert Fatigue Very Seriously

That’s why we’ve developed the Loom Systems AutoTuner.


Don't worry, Loom Systems won't break into song (though we have an open feature request for that)


AutoTuner is a dynamic mechanism built into Loom Systems. Its purpose is to assign detections a severity score so users never miss a crucial alert.

The basic, least flexible way to manage alerts prioritization is through a set of strict, deterministic rules. Each rule is applied to an incident chronologically and outputs a yes or no result. This does not take into account other rules and detections that went on in the system in the past or present.

AutoTuner Is Much Smarter 


AutoTuner utilizes an advanced, two-tiered feedback module. This module allows Loom Systems to implement a hybrid strategy to detection scoring: implicit and explicit.

The implicit strategy scores detections based on a set of rules it applies to each detection. Each rule analyzes a specific aspect of the detection and gives it a numerical score indicating how influential it is.

The explicit strategy gives every detection a score based on how similar detections were treated by users in the past. Detections that users chose to “Raise” (give more importance to) or “Mute” (give no importance to), affect the scores of similar future detections.

This two-tiered feedback module ensures each detection is given a dynamically generated score.

This allows Loom Systems to ensure users are never in the dark about the most pressing issues in their environment.

An Alerting Solution You Can Love 

Loom Systems is built to be a layered, dynamic and thoughtful monitoring solution.

Above all else, we’re building Loom Systems to be a solution users can love. One that simplifies their lives and reduces their day-to-day drag.

With AutoTuner, Loom Systems found a way to take maximal care of both users and their data. Get Started for Free Today.




Loom Systems delivers an AIOps-powered log analytics solution, Sophie, to predict and prevent problems in the digital business. Loom collects logs and metrics from the entire IT stack, continually monitors them, and gives a heads-up when something is likely to deviate from the norm. When it does, Loom sends out an alert and recommended resolution so DevOps and IT managers can proactively attend to the issue before anything goes down.
Get Started with AIOps Today!

Looking for more posts like this?