Automated Reasoning checks in Amazon Bedrock Guardrails use formal verification techniques to validate AI model outputs with mathematical rigor, providing a fundamentally different approach from traditional sampling-based testing methods. This capability addresses critical challenges in deploying generative AI applications, including…

Amazon Bedrock Guardrails now offers the InvokeGuardrailChecks API, a new resourceless API that lets you apply individual safeguards at any point in your agentic AI applications without creating guardrail resources. The API provides granular, per-request control over which safeguards to…

You can now create Amazon FSx for Lustre file systems with the Intelligent-Tiering storage class in 13 additional AWS Regions across Africa, Europe, Asia Pacific, and South America. The FSx for Lustre Intelligent-Tiering storage class delivers the lowest-cost and only…

Amazon S3 Vectors can now return up to 10,000 similarity search results per query, a 100x increase from the previous limit. The higher result limit helps you retrieve a larger, more comprehensive set of candidates during similarity queries. This is especially…

Amazon S3 adds annotations, so you can attach custom metadata to your S3 objects at massive scale, giving AI agents and analytics tools the context they need to find and use the right data. Annotations are a new metadata capability…

Amazon S3 Vectors has reduced data processed charges for queries on vector indexes with over 10 million vectors by up to 80%. This reduction lowers costs for customers running similarity search across large-scale AI, RAG, and semantic search workloads. The…