Prompt-Level Audit Log
A prompt-level audit log records every prompt sent to an AI model, the user who sent it, the model that received it, the response returned, and any AI Firewall actions applied — at the granularity of a single request.
Workspace-level or session-level logs are not sufficient for regulated environments. A defensible audit trail must answer, for any moment in the past: who asked what, of which model, and what was returned — including whether any sensitive values were substituted.
Prompt-level logging is the substrate for every downstream compliance use case: incident investigation, e-discovery, regulator inquiry, model evaluation, and internal acceptable-use enforcement.
Backplain logs every prompt, every response, and every AI Firewall substitution from seat one, with export to AWS QuickSight or any downstream SIEM at the Business tier and above.