Unlock hidden insights with automated alerts for log anomalies. Learn how F33 leveraged Vertex AI’s NLP capabilities for Nobl9’s log monitoring.

Use Case Study: Tracking Anomalies in the Stream of Logs for Nobl9

Unlock hidden value in logs data to enrich SLOs functionality. How has F33 used Vertex AI’s powerful NLP capabilities to track anomalies in the stream of logs for the Nobl9 company?

Challenge

Nobl9 is an unchallenged leader in multi-cloud/environment SLOs solutions. We have been working with Nobl9 using their product for monitoring AI and ML models. You can read more about this here. This experience made us think deeper about combining SLOs and AI/ML. After a few brainstorming sessions, we developed an exciting business case.

Our customer Nobl9 wants to help their customers and employees by reading through logs and alerting them in case some unusual system behavior is about to occur. To do so, the company needs an automated solution for extracting knowledge from logs and detecting time ranges when systems do not act in a normal, expected way. The company has access to historical logs. They can acquire information about system’s health status from experts.

Our Solution

F33 has followed its AI/ML Framework to deliver AI/ML solutions for Nobl9 company. As a result, we helped them to formulate requirements, prepare datasets (we used logs from their product Nobl9), and upgrade their IT infrastructure to be able to communicate with the model.

It was interesting for us to adapt Google’s Universal Sentence Encoder to work with log datasets. Using Tensorflow TFX framework it was reasonably easy to build a model that could calculate the anomaly score for the next log in a stream. See the picture below as a demonstration of the working solution.

Models were implemented using F33’s MLOps GCP Platform and the diagram below presents all core components used for this implementation.

Benefits

Nobl9 has confirmed that the solution brought a lot of benefits to their current product functionalities. The most important was that it was possible to create an anomaly detection model based on logs that would improve and enrich existing SLOs functionality. This unlocks an ocean of possibilities but, most importantly, can lead to easier product implementation and also the ability to create SLIs that are not biased by humans. Implementing F33’s MLOps Platform gave Nobl9 a standardized and reproducible workflow to experiment and compare different ML models on their log data.

The Results

One outcome of this project was a baseline anomaly detection model that proved AI is useful for log analysis for Service Level Objectives. Another result was a scalable environment for developing and testing various ML approaches to obtaining knowledge from logs. F33 also delivered a standardized and reproducible workflow to experiment and compare different ML models.

About Nobl9 Inc.

The software reliability platform Nobl9 is in the noble pursuit of reliable software. We help software developers, DevOps practitioners, and reliability engineers deliver reliable features faster. Through software-defined Service Level Objectives, they help link monitoring and other logging and tracing data to user happiness and business indicators.

The solution brought a lot of benefits to Nobl9’s functionalities. The most important was that it was possible to create an anomaly detection model based on logs that would improve and enrich existing Service Level Objectives functionality. F33’s MLOps Platform gave Nobl9 a standardized and reproducible workflow to experiment and compare different ML models on their log data.
– Marcin Kurc, CEO, Nobl9 Inc