Tools #Coding agents#AI agents Nov 1, 2026 · Originally published Oct 30

AWS lays out an end-to-end Bedrock cost playbook: spend attributed to each IAM principal, over-budget users blocked in seconds to minutes, and more than half of coding-fleet calls on cheaper models

A checklist in five stages, attribution, observability, enforcement, optimization and governance, aimed at platform teams rolling out coding agents.

Primary source AWS Machine Learning Blog · aws.amazon.com Read the original ↗

// Key points

  • Bedrock inference costs are attributed to the calling IAM principal in CUR 2.0, in the line_item_iam_principal column; activated principal tags show up in Cost Explorer within 24–48 hours.
  • Behind a gateway, call STS AssumeRole once per user with attributes as session tags and cache credentials for up to an hour, one STS call per user per hour rather than per request.
  • Enforcement comes in three tiers: AWS Budgets alerts only; a Lambda function with DynamoDB counters adds over-budget users to a shared IAM deny policy within seconds to minutes; a gateway returns HTTP 429 synchronously, with the Claude apps gateway or LiteLLM as options.
  • CUR lags about 24 hours, so near-real-time spend needs CloudWatch plus OpenTelemetry; for agentic coding fleets the stated target is more than half of calls on cheaper models.

Builder's takeStart with the cheapest step: put requestMetadata (application, workflow, tenant) on every call, because attribution cannot be added after the fact. For multi-tenant products like AI Cloud Drive and AI Interview I would tag by tenant, add a hard 429 limit at the gateway, and cover the one-day billing lag with real-time logs. Read alongside today's Claude Code pooled budgets, knowing who spent what and how to stop overspend is now a prerequisite for rolling out agents.

// Background · from #Coding agents

Full timeline →
  1. Nov 1 Claude Code 2.1.316 retires fast mode on Opus 4.8 on November 30, adds pooled group budgets to its gateway and a separate effort setting for subagents
  2. Nov 1 Bedrock AgentCore Runtime adds session endpoints: preview a web app in your own browser while a coding agent edits it in the cloud
  3. Oct 31 Claude Code 2.1.314 adds a setting that blocks writes outside the working directories in every permission mode

Every Monday, the week in AI in one email

Every Monday morning: the 6 AI stories that mattered most in the past seven days, with my take, in your inbox.

Your email is only used to send the weekly and is never shared. Every email has a one-click unsubscribe link. See the latest issue →