Braintrust allows you to log raw data while you run your AI applications, including inputs, outputs, and prompts. Because of the sensitivity of this data, we support running the logging stack in your AWS account, ensuring that data never leaves your account, and never flows through Braintrust’s infrastructure.
At its core, the deployment works by installing a few AWS Lambda (opens in a new tab) functions in your account, in a VPC (opens in a new tab) (via a CloudFormation template (opens in a new tab)), and connecting that VPC to a Postgres database (opens in a new tab) or data warehouse.
When you log from Braintrust's Typescript or Python library, it sends the events directly to a lambda function, never touching Braintrust's servers. And when you visit the UI (on https://www.braintrustdata.com/app (opens in a new tab)), your browser runs requests against the lambda function directly.