Patronus AI, Inc.
To boost enterprise confidence in generative AI through automated evaluation, optimization, and security platforms for LLMs and AI agents.
At a Glance
- Technology
- Financial Services
- Healthcare
- Education
AI Tools by Patronus AI, Inc.
(1)Patronus AI
LLM Evaluation and Monitoring Platform
Discussions
No discussions yet
Be the first to start a discussion about Patronus AI, Inc.
Latest News
Products & Services
A centralized solution for running LLM experiments, logging results, and comparing model performance using automated scoring.
A 70B-parameter hallucination detection model that outperforms GPT-4 on identifying mistakes in LLM outputs.
An AI evaluation copilot for analyzing complex traces in agentic systems, identifying over 20 failure modes.
A benchmark of 10,000 Q&A pairs used to evaluate LLM performance on financial questions using public documents.
Market Position
Leading automated AI evaluation and security platform focused on enterprise reliability and research-backed benchmarks.
Leadership
Founders
Anand Kannappan
Co-founder and CEO. Former machine learning researcher at Meta AI, where he focused on large language model evaluation and safety.
Rebecca Qian
Co-founder and CTO. Former Research Engineer and Machine Learning Engineer at Facebook AI (Meta AI), specializing in agent simulation and LLMs.
Executive Team
Anand Kannappan
Co-Founder and CEO
Former ML Researcher at Meta AI.
Rebecca Qian
Co-Founder and CTO
Former Research Engineer at Meta AI.
Board of Directors
Founding Story
Founded by machine learning experts from Meta AI to address the critical need for automated evaluation tools that detect LLM hallucinations, copyright issues, and safety risks, enabling safe enterprise deployment.
Business Model
Revenue Model
SaaS platform subscription and usage-based API pricing.
Pricing Tiers
Includes 20 pages and 5 pages per project.
Includes 600 pages with add-ons on demand.
Unlimited pages, premium security features (on-prem/VPC), and custom fine-tuning.
Usage-based API pricing for small evaluator calls.
Usage-based API pricing for large evaluator calls.
Target Markets
- Technology
- Financial Services
- Healthcare
- Education
- RAG system evaluation
- AI agent training
- Financial document QA
- Model comparison and benchmarking
- Safety and compliance testing
- AngelList
- Etsy
- Pearson