Skip to main content

Introduction

WhyLabs AI Observability

WhyLabs is the leading observability platform trusted by high-performing teams to control the behavior of ML & data applications. ML teams across healthcare, financial services, logistics, e-commerce, and others use WhyLabs to:

  • Monitor and observe model performance for predictive ML models, supporting delayed ground truth and custom performance metrics

  • Monitor and observe data quality in ML model inputs, Feature Stores, batch and streaming pipelines

  • Detect and root cause common ML issues such as drift, data quality, model performance degradation, and model bias

  • Explain the cause of model performance degradation using tracing and feature importance

  • Detect and root cause common LLM issues such as toxicity, PII leakage, malicious activity, and indications of hallucinations

WhyLabs Overview Video

If you enjoy learning about software in video format, checkout our youtube channel for workshops and tutorials. Here is one of our most popular workshop videos:

WhyLabs in the ML Lifecycle

WhyLabs is a purpose-built ML Observability platform. The main goal of the WhyLabs platform is to create feedback loops which help ML teams continuously improve and control production ML models.

WhyLabs in the ML Lifecycle

WhyLabs architecture at a glance

WhyLabs observability solution is a hybrid SaaS, consisting of two major components:

  1. Telemetry agents: open source libraries that deploy directly into the user environment. These libraries collect privacy-preserving telemetry data that describes the health of models and datasets.
  2. Platform: the hosted platform that operates on the telemetry data generated by the agents. The platform offers a rich user interface for visualizing model and data health, configuring and detecting issues, and sending alerts.

WhyLabs Architecture

WhyLabs can also be deployed into the VPC. Contact our team if you are interested in a custom VPC deployment.

What does WhyLabs monitor?

WhyLabs Platform enables monitoring for a wide range of use cases:

  • Predictive ML models: all of the common ML model types
  • Generative AI models: LLMs
  • Data health: streaming and batch data pipelines
  • ML features & feature stores: tabular data, text, images, and audio

WhyLabs Usecases

Resources

To learn more about WhyLabs:

Prefooter Illustration Mobile
Run AI With Certainty
Get started for free
Prefooter Illustration