Foundry

We’re building a platform to design, test, and improve AI agents. It’s hard to build agents, understand how well they’re performing, and know what and how to improve. Our platform unifies design, evaluation, and fine-tuning, making it easier to identify weaknesses, improve reliability, and scale agents for real-world use. Manil and Pranav previously worked at Scale AI, where they helped produce and refine data to evaluate and improve some of the best AI models in the world. Now, we’re bringing that expertise to help companies build AI systems that work better, faster.