Let Zebrium not only catch application incidents, but also show root cause using your Elastic Stack. No manual training, no manual alert rules and no changes to your end points.

This is not like the noisy anomaly detection you might have seen before. It  uses machine learning to detect real incidents and produces incident summaries showing root cause.

See auto-detected application incidents in an elegant Kibana dashboard. With just a click you can view the set of correlated log events that describe the root cause. Thumbs up and down buttons let you provide feedback on incident quality and customize your incident feed. 

Elastic native machine learning can find anomalies in your logs and metrics. But they are typically noisy and require human interpretation and correlation to uncover useful information. Zebrium takes a different approach - it simply finds incidents and shows root cause. More details here.

No More Fragile Alert Rules

You no longer need to build and maintain manual alert rules for the ever-increasing number of possible failure modes. Zebrium configuration is automatic, and accurate detection occurs within an hour of first use.

Reduce false positives

Zebrium machine learning works by finding hotspots of  abnormally correlated anomalous patterns across logs and metrics. This significantly reduces the number of false positives compared with other anomaly detection techniques.

It only takes a few minutes to setup Zebrium to work with your existing Elastic Stack. Just add a Logstash output to send logs to Zebrium and an input for Zebrium  to send incident details back to Logstash.  You can setup your own dashboard to see Zebrium incidents or use our prebuilt Kibana canvas.