What happens to the data I share with the language model?

Data shared with the LLM (language model) provider is processed at a location depending on the provider you use. Please see the subprocessors page page for more details on the provider you use. The providers don't use your data for training and keep retention policies for logs to a minimum. We recommend reviewing the privacy policy of the relevant provider for additional details.

Credentials and API keys are never exposed to the LLM. We use multi-layer security, including a separate security agent and code-level guardrails that can't be bypassed via prompts. All actions are logged for audit trails. For full details, see our Security Overview.