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 architecture at a glance
WhyLabs observability solution is a hybrid SaaS, consisting of two major components:
- 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.
- 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 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
To learn more about WhyLabs: