We've shipped a new feature to help debug and observe LLM app pipelines by logging function calls and getting useful traces in the Braintrust UI. Additionally, we made the experiment dashboard customizable, allowing users to select which charts they'd like to see for their experiments. Other updates include a new "text-block" prompt type in the playground, increased default rows per page for experiments, and several UI fixes and improvements. These changes aim to reduce uncertainty and tedium in building AI products with Braintrust's enterprise-grade stack.