“LangSmith allows us to get things done scientifically. At a large company, usually multiple teams develop their ideas independently. Some teams find good approaches, while others don’t. By using LangSmith Hub, we could distribute the best prompts and promote collaboration across teams. By using LangSmith Testing and Eval with our custom evaluation metrics, we can run experiments on multiple approaches (models, cognitive architecture, etc.) and measure the results. By combining the benefits of LangSmith and standing on the shoulders of a gigantic open-source community, we’re able to identify the right approaches for using LLMs in an enterprise-setting faster.”