Patronus AI
Engineering Software · New York, United States · 51-200 Employees
View Company Info for Free
Overview
Headquarters
New York City, New York, United StatesWebsite
www.patronus.aiRevenue
$13 MillionIndustry
About Patronus AI
Patronus AI is a San Francisco, California-based AI evaluation and security company founded in 2023 by machine learning experts from Meta AI. The company develops an automated platform that enables enterprise development teams to test, evaluate, and monitor large language models at scale. Its core offerings include LLM performance scoring, adversarial test case generation, hallucination detection, benchmarking, and real-time agent monitoring through its Percival platform. Patronus AI's evaluators assess model outputs across a broad range of dimensions including accuracy, copyright risk, PII leakage, brand alignment, and safety all accessible via a single API call. The platform serves Fortune 500 enterprises and leading AI companies seeking to deploy generative AI products safely and in compliance with regulatory and organizational requirements. Patronus AI is backed by Notable Capital, Lightspeed Venture Partners, and Datadog, among others.Explore more
SIC Code 73,737NAICS Code 51,518Show morePatronus AI Org Chart
Compare Similar Companies to Patronus AI
Compare insights from companies similar to Patronus AI, focusing on performance, financial data, growth rates, and unique benchmarks to identify key industry trends and opportunities.
Revenue
Number of Employees
Type
Funding
Founded In
Patronus AI Tech Stack
A closer look at the technologies used by Patronus AI
Top Engineering Software Companies
Top companies in Canada by revenue
Top companies in Australia by revenue
Top companies in New Zealand by revenue
Frequently Asked Questions Regarding Patronus AI
Sign Up For FreeTo access detailed company insights
Patronus AI is a San Francisco, California-based AI evaluation and security company founded in 2023 by machine learning experts from Meta AI. The company develops an automated platform that enables enterprise development teams to test, evaluate, and monitor large language models at scale. Its core offerings include LLM performance scoring, adversar... Read More