Saurav Bhattacharya
Building agent-eval, an open-source framework for testing & evaluating AI agent outputs. Also building WinSentinel for Windows security. I write about agent reliability, eval methodology, & AI safety.
Building agent-eval, an open-source framework for testing & evaluating AI agent outputs. Also building WinSentinel for Windows security. I write about agent reliability, eval methodology, & AI safety.
