# Halluminate

> Halluminate provides fully managed environments and benchmarks so teams can train computer agents with superhuman capabilities. We offer realistic environments of enterprise software, advanced benchmarks for computer use agents, and forward deployed support for custom evaluations.

Halluminate is backed by Y Combinator and focuses on powering a path to safe and productive AI through rigorous evaluation and testing infrastructure. Our platform enables teams to move from building to deploying computer agents by providing the tools needed to unlock frontier capabilities.

Key offerings include:
- **Environments**: Access realistic environments of enterprise software running on fully managed infrastructure
- **Benchmarks**: Measure computer use agents on advanced tasks with proprietary and open-source benchmarks
- **Evaluations**: Receive forward deployed support to design custom evals and improve computer use performance


## Research

- [BrowserBench](https://halluminate.ai/blog/browserbench): Benchmark revealing how bot detection systems impact browser agent evaluation, with analysis of stealth vs non-stealth performance
- [Westworld](https://halluminate.ai/blog/westworld): AI sandbox environments for training and evaluating computer use agents on realistic simulated websites
- [WebBench](https://halluminate.ai/blog/benchmark): Rigorous benchmark for evaluating browser agents on ~2,454 realistic tasks across 452 real-world websites
- [WebBench Dataset](https://eval.skyvern.com/): Full run details and trajectories for WebBench evaluation results

## Case Studies

- [Athena Intelligence](https://halluminate.notion.site/Athena-Intelligence-partners-with-Halluminate-to-improve-performance-of-data-extractor-AI-Agent-17d239940a7480628db9d9dd52fe9cda): Partnership to improve AI agent data extraction performance
- [Amplitech AI](https://halluminate.notion.site/Amplitech-AI-partners-with-Halluminate-to-deploy-CI-CD-testing-pipeline-for-AI-Sales-Assistant-17d239940a74806e8d50ca572aae886c): CI/CD evaluation harness deployment for AI sales agents

## Team

- [Jerry Wu, Founder/CEO](https://www.linkedin.com/in/jerry-wu-7814b0100/): PM lead for first generative AI project at Capital One, Cornell CS/ML
- [Wyatt Marshall, Founder/CTO](https://www.linkedin.com/in/wyatt-marshall-a40797198/): Software and data engineer at two venture backed startups, Cornell CS/ML and Philosophy, Milstein Scholar

## Optional

- [Contact](https://halluminate.ai/contact): Get in touch with the Halluminate team
- [Blog](https://halluminate.ai/blogs): Collection of thoughts, announcements, and case studies
- [GitHub](https://github.com/Halluminate): Open source projects and repositories