AI Observability and Evaluation Platform

The one solution for AI engineers — from development through deployment. Build better AI with Arize.

Top AI companies choose Arize


Trace. Evaluate. Iterate.

Performance Tracing

Instantly surface up worst-performing slices of predictions with heatmaps that pinpoint problematic model features and values.


Gain insights into why a model arrived at its outcomes, so you can optimize performance over time and mitigate potential model bias issues.

Dashboards & Monitors

Automated model monitoring and dynamic dashboards help you quickly kickoff root cause analysis workflows.

Model & Feature Drift

Compare datasets across training, validation, and production environments to detect unexpected shifts in your model’s predictions or feature values.


Surface. Resolve. Improve.

Cluster Search &

AI-driven similarity search streamlines the ability to find and analyze clusters of data points that look like your reference point of interest.

Cluster Search and Curate

Embedding Monitoring

Monitor embedding drift for NLP, computer vision, and multi-variate tabular model data.



Native support to augment your model data with human feedback, labels, metadata, and notes.


Build Datasets

Save off data points of interest for experiment runs, A/B analysis, and relabeling and improvement workflows.

Build Datasets


Build better AI with AI-powered workflows

Unlock Model Insights Instantly

Empower your ML decision-making with Copilot for a seamless overview of model performance and trends. Gain deep insights into prediction accuracy and stability over time, so you can steer your model's outcomes with precision and confidence.

Enhance Data Quality with Precision

Effortlessly ensure your model's inputs are of the highest quality. Automate detection of any anomalies or shifts in your data, so you can quickly address issues and maintain the integrity and reliability of your analytics environment.

Optimize Performance Across Cohorts

Identify and resolve performance bottlenecks across different segments of your data. Copilot helps you dissect and understand factors influencing your model's effectiveness, enabling targeted improvements and strategic optimizations.


Bring compute to your data.

Open instrumentation

Our code tracing your AI-powered applications leverages OpenTelemetry, providing robust, standardized instrumentation. This consistency across your AI stack enhances the ability to diagnose issues, evaluate performance, and maintain high-quality service delivery.

Flexible instrumentation

Open data

Trace data is collected in a standard file format, enabling unparalleled interoperability, ease of integration with other tools and systems, and the ability to manage and analyze data as needed.

Own your data

Open source

Leverage our open-source LLM evaluations library and tracing code for seamless integration with your AI applications. You can even run the entire solution within your own infrastructure, for utmost control, flexibility, and security.

Arize Phoenix OSS

Battle-hardened for the real world.


Gain unparalleled performance, designed to scale effortlessly with your evolving needs.


Embedded at a structural level, see how we protect your company and data.


From SOC 2 Type II to HIPAA, we adhere to the highest standards of privacy.

Built by AI Engineers, for AI Engineers

“We adopted Phoenix due to its excellent documentation and support and well designed ability to integrate quickly into our existing prototyping workflows. Arize has also nurtured an active community of LLMOps learners, professionals, and advocates that I’ve personally found very helpful to (try to) stay on top of new developments.”

Peter Leimbigler
Data Science Team Leader, Klick Health

“LLM applications are complex. To optimize them for speed, cost, or accuracy, you need to understand their internal state. Each step of the response generation process needs to be monitored, evaluated, and tuned. Phoenix lets us evaluate whether a retrieved chunk contains an answer to a query.”

Atita Arora
Solutions Architect, Qdrant

“Arize observability is pretty awesome!”

Andrei Fajardo
Founding Engineer, LlamaIndex

“Arize offers an AI observability and LLM evaluation platform that helps AI developers and data scientists monitor, troubleshoot, and evaluate LLM models. This offering is critical to observe and evaluate applications for performance improvements in the build-learn-improve development loop..”

Mike Hulme
General Manager, Azure Digital Apps and Innovation, Microsoft

“We are constantly iterating on our production ranking model to improve activity relevance and personalization for our users’ unique preferences. As we launch A/B tests, Arize gives us the ability to break the performance further down into different data segments and highlight which features contribute to the model’s predictive performance the most. This gives us a broad overview of our ranking model’s overall performance at any time and allows us to identify areas of improvement, compare different datasets, and examine problematic slices.”

Mihail Douhaniaris
Senior Data Scientist, and Martin Jewell, Senior MLOps Engineer, GetYourGuide

“The US Navy relies on machine learning models to support underwater target threat detection by unmanned underwater vehicles. To ensure successful deployment of this technology, AI infrastructure is required to continuously monitor and improve model performance to ensure the systems remain effective. After a competitive evaluation process, Defense Innovation Unit (DIU) and the U.S. Navy awarded five prototype agreements in the fall of 2022 to Arize AI [and others] …as part of Project Automatic Target Recognition using Machine Learning Operations (MLOps) for Maritime Operations, nicknamed Project AMMO).”

Defense Innovation Unit

Start your AI observability journey