In Production: Multi-Region, Quota, and Failover

The domain’s production capstone: quotas as an architectural force, cross-region serving mechanisms, and failover patterns that survive contact with reality.

Content last verified 2026-09.

Lessons

1. Quotas as Architecture
2. Failover Patterns
3. The Runbook

Sources

• Amazon Bedrock User Guide — cross-Region inference
• Amazon Bedrock User Guide — quotas
• Azure AI Foundry — deployment types (Microsoft Learn)
• Azure AI Foundry — quota and rate limits (Microsoft Learn)
• Vertex AI — generative AI quotas and system limits