BC-Bench (II): How to get started

This guide provides a comprehensive overview of setting up and utilizing BC-Bench for agent evaluations. It includes the installation process, running evaluations, and interpreting results, emphasizing the necessity of a Windows Server VM for full evaluations. The document outlines the environment setup, agent coding, and evaluation comparisons, while cautioning against common pitfalls. Custom agent profiles can be created for tailored evaluations, with the framework available for adaptation under an MIT license.