Cost attribution and controls for AI developer and productivity tools on Amazon Bedrock
TL;DR
Amazon Bedrock provides built-in, zero-instrumentation cost attribution that traces every inference call back to the IAM principal that made it. This post shows how to attribute per-user Bedrock costs for AI developer and productivity tools using IAM Identity Center, session tags, and CUR 2.0, and how to enforce per-user usage limits.
Nauti's Take
Small teams should test the tagging chain first: Do the IAM principal and session tags survive across every tool in the workflow, and how quickly does the data reach CUR 2.0? Set usage limits only after that check, because delayed or incomplete attribution can produce reports without providing reliable cost control.