Amazon Aurora provides cloud-native MySQL and PostgreSQL compatibility with ML integration and automatic optimization. Aurora ML enables direct ML inference in SQL queries by calling Amazon SageMaker endpoints or Amazon Comprehend for sentiment analysis—without data movement. Aurora Serverless v2 automatically scales capacity in fine-grained increments (0.5 ACU) based on workload, eliminating capacity planning. Aurora Optimized Reads improves query performance up to 8x for read-heavy workloads through intelligent caching. Aurora I/O-Optimized pricing bundles I/O costs for predictable billing on I/O-intensive workloads. Performance Insights (same as RDS) provides wait event analysis with 7-day free retention. Aurora Global Database enables cross-region disaster recovery with sub-second replication. PostgreSQL-compatible Aurora adds extensions support including pgvector for vector similarity search. Page should cover: Aurora ML setup with SageMaker, Serverless v2 scaling behavior, Optimized Reads configuration, Standard vs I/O-Optimized pricing analysis, comparison with RDS, pgvector for AI applications, and migration considerations from RDS.