1/ Today, we are thrilled to announce Generative Simulators, a new class of adaptive, auto-scaling environments for AGI training and evaluation 🤖🧵 Static datasets, hand-authored environments, and human-curated demonstrations do not automatically scale with the learning

At @PatronusAI, we're excited to publish a new article with tutorials and examples for RL Environments. 🚀 In this article, you will learn the core concepts behind reinforcement learning (RL), where AI models and agents learn by trial and error based on feedback in the form of

6/ We have grown 15x in revenue this year. We are scaling quickly across all fronts – research, engineering, operations. We are just scratching the surface of AGI capabilities. In our path to AGI, environments are the new oil. If you are excited about autonomously scaling

5/ We are partnering with model developers to develop frontier RL environments. With generative simulation, we are constructing hyperrealistic, auto-scaling worlds that are complex and learnable, to train agents to perform real world job functions ranging from equity research

4/ Our benchmarks such as FinanceBench are used by thousands of institutions around the world. Models we have trained (Lynx, Glider) are used by Fortune 500s for hallucination detection and rubric-guided evaluation across industries such as banking and healthcare. 🌎 Our past

3/ To address this, we introduce Generative Simulators: adaptive environment generators capable of producing challenging, diverse tasks and tool sets with minimal specification. To achieve this, we train a multi-agent oversight system: - Task Generation: sequentially creates

2/ Today, most RL environments in the industry are fixed collections of tasks, modeled after open source benchmarks like SWEBench. With recent improvements in models, these benchmark environments have come to saturate, such as Tau2-Bench getting nearly saturated by GPT-5.2. This

We're still buzzing from our night at the San Diego Zoo! We had an incredible evening hosting our @NeurIPSConf community. Guests explored the park at sunset and joined us for a private Wildlife Encounter featuring six amazing animals, including a tenrec 🐾 , owl 🦉, opossum 🐀,

We’re excited to support @Meta and @huggingface's OpenEnv launch today! OpenEnv provides an open-source framework for building and interacting with agentic execution environments. This allows researchers and developers to create isolated, secure, deployable, and usable

Our CTO, @rebeccatqian, spoke at the @PyTorch Measuring Intelligence Summit 2025 yesterday! She was on the Beyond the Leaderboard: Practical Intelligence in the Wild panel with @jeremyphoward ( https://t.co/D5I4E5K0dY), and @haifengxu0 (@UChicago/ ProphetArena), moderated by

At @PatronusAI, we're excited to publish a new article with tutorials and examples for AI Guardrails. 🚀 In this article, you will learn about the importance of AI guardrails in ensuring the reliable and ethical use of large language models in various industries, and the

Introducing MEMTRACK, a new benchmark designed to evaluate long-term memory and state tracking in multi-platform agent environments. 🎉 Human memory enables us to achieve complex objectives by taking in, storing, and applying saved information. We wanted to evaluate how LLMs

At @PatronusAI, we're excited to publish a new article with tutorials and examples for AI Agent Tools. 🚀 In this article, you will learn about AI agent tools that allow AI models to interact with external systems and enhance their capabilities through real-time data access to

Introducing Percival Chat, a new way to work with Percival, the first AI agent that can evaluate and fix other agents 🚀 Now, you can Chat with Percival to automatically analyze your agent traces and detect complex failures, making your AI more reliable and secure. Read more in

At @PatronusAI, we're excited to publish a new article on the best practices for Advanced Prompt Engineering. 🚀 In this article, you will learn about advanced prompt engineering techniques that can maximize the potential of large language models, including self-ask

At @PatronusAI, we're excited to publish a new article on the best practices for LLM Observability. 🚀 In this article, you will learn how LLM observability empowers engineering teams by capturing and analyzing various aspects of LLM-based applications—like prompts, responses,

Welcome Josh Weimer to the team! 🎉 Josh joins @PatronusAI as a Forward Deployed Engineer. Previously, he worked in the GovTech space, where he supported agencies including the Department of Defense, Department of Justice, Office of Personnel Management, and Department of the

Evaluators are at the heart of the Patronus AI platform, and clients across industries have found them helpful in evaluating context and answer relevance, detecting hallucinations, and analyzing multimodal content! If you’re new to evaluators, this blog post will give a quick

This past weekend, our Head of Applied Research, Peng Wang, was invited to give a talk on AI Oversight at Scale: Navigating the Challenges of Evaluating LLMs and Agents. Peng shared our vision of scalable AI oversight being the biggest problem facing widespread societal

Introducing Prompt Tester on the Patronus AI platform! Prompt Tester allows you to build more robust prompts across different types of contexts to test out their effectiveness. Prompt. Test. Evaluate. Iterate. Read more here: https://t.co/igwYasCSVn Give it a try and let us