Enforcing data residency with single-Region Claude Code on Amazon Bedrock
Regulated enterprises: how to lock Claude inference to a single region without vendor lock-in pain.
Why it matters
Data residency enforcement is becoming table-stakes for regulated AI deployments. This shows practitioners how to operationalize it on Bedrock—a concrete compliance pattern for financial services, healthcare, and government buyers.
The key facts
10 to knowUse case: single-region enforcement for Claude Code on Amazon Bedrock (London)
Two enforcement methods: application inference profile + IAM Region condition, or Mantle endpoint
Compliance verification via AWS CloudTrail
Addresses regulated customer requirement: all inference must stay in-region, not just in-geography
Operational pattern for data residency in multi-region cloud deployments
Claude Code on Amazon Bedrock now supports single-Region pinning via inference profiles
Two enforcement methods: application inference profile or Mantle endpoint + IAM Region condition
Compliance verification available through AWS CloudTrail logs
Use case: regulated customer required all inference in London Region only
Relevant for finance, healthcare, government deployments with data residency mandates
Go to the source
AWS Machine Learning Blogaws.amazon.com
Publisher excerpt: A regulated customer needed all Claude Code inference processed in a single AWS Region (London), not just in-geography. This post shows two ways to pin Claude Code on Amazon Bedrock to one Region: an application inference profile or the Mantle endpoint, paired with an IAM Region condition, plus how…