Data Agent: Data Protection
Fabricate stores all data agent conversations on Tonic.ai’s servers to preserve context for future data generation. Each conversation is strictly associated with its respective database. Conversations are retained until the associated database is deleted, which occurs automatically when a workspace or account is deleted.
Anthropic
Additionally, Fabricate uses Anthropic’s API to forward user messages to foundation models. Anthropic has committed not to use data sent to the API for model training. Anthropic Data Protection Policy
BYO AWS Bedrock key
Fabricate also allows customers on the Enterprise plan to bring their own AWS Bedrock key. When configured, Fabricate will send all customer messages to their own AWS Bedrock endpoint instead of Anthropic. AWS Bedrock provides the following guidance:
Amazon Bedrock doesn't store or log your prompts and completions. Amazon Bedrock doesn't use your prompts and completions to train any AWS models and doesn't distribute them to third parties.
Amazon Bedrock has a concept of a Model Deployment Account—in each AWS Region where Amazon Bedrock is available, there is one such deployment account per model provider. These accounts are owned and operated by the Amazon Bedrock service team. Model providers don't have any access to those accounts. After delivery of a model from a model provider to AWS, Amazon Bedrock will perform a deep copy of a model provider’s inference and training software into those accounts for deployment. Because the model providers don't have access to those accounts, they don't have access to Amazon Bedrock logs or to customer prompts and completions.
Last updated