Exam-style
An auditor wants to read the full text of every prompt and every completion a Bedrock-backed assistant handled last Tuesday. The application logs hold request IDs, token counts, and latency, but no message content. What produces the record the auditor wants?
Reveal the answer
E. Bedrock model invocation logging, enabled per region and delivering request and response payloads to S3 or CloudWatch Logs
Model invocation logging is the only feature that persists the actual prompt and completion payloads, including text, image, and embedding data, and it is off by default and configured per region, so it has to be switched on ahead of the request. CloudTrail records that InvokeModel was called and by whom, but not the message bodies. Container Insights measures the infrastructure, and an evaluation job scores fresh outputs rather than reconstructing last Tuesday’s traffic.
Q. An auditor asks to see every prompt this assistant received last Tuesday. What produces it?
A. Bedrock model invocation logging: off by default, enabled per region, it delivers the full request and response (text, image, embedding) to S3 and/or CloudWatch Logs.
Why? Application logs do not capture prompts and completions; you must switch this on, in every region the model runs.