New featureMedium

Amazon Bedrock Guardrails announces new API for agentic AI workflows

Amazon Bedrock Guardrails now offers the InvokeGuardrailChecks API, allowing users to apply individual safeguards at any point in agentic AI applications without creating guardrail resources. The API provides granular control over which safeguards to run at each step, returning severity and confidence scores for custom thresholds and actions.

Amazon Bedrock Guardrails now offers the InvokeGuardrailChecks API, a new resourceless API that allows you to 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 run at each step of your agent loop, returning numeric severity and confidence scores so you can implement custom thresholds and actions, whether to block, pass, retry, or log based on your specific requirements. Agentic AI applications operate through iterative loops, and each step carries a different risk profile. The InvokeGuardrailChecks API operates in detect-only mode with no guardrail IDs to track and no versions to manage. You specify which safeguards to run directly in each request. The API supports content filters, prompt attack detection, and sensitive information filters. Prompt attack detection is exposed as a separate safeguard. The InvokeGuardrailChecks API is available in US East (N. Virginia), US East (Ohio), US West (Oregon), Europe (London), Europe (Stockholm), Asia Pacific (Tokyo), and Asia Pacific (Sydney).

Read the original AWS announcement

Related articles and terms

Generative AI Platform - Building an Enterprise AI Foundation with Amazon BedrockLearn how to build generative AI applications using Amazon Bedrock. This guide covers foundation model selection, RAG pattern implementation, safety guardrails, and SageMaker integration for designing enterprise-grade AI infrastructure.Amazon Bedrock GuardrailsA safety mechanism that controls generative AI application inputs and outputs, performing harmful content filtering and personal information maskingThe Layered Architecture of AWS AI/ML Services - Flexibility Through the Three Tiers of SageMaker, Bedrock, and API ServicesThis article organizes AWS AI/ML services into three layers - SageMaker (full control), Bedrock (managed generative AI), and Rekognition/Comprehend/etc. (API-based) - and explains AWS's flexibility through comparisons with GCP Vertex AI and Azure OpenAI Service, including custom silicon integration.Amazon BedrockA fully managed generative AI service providing access to leading foundation models via APIUsing Claude on Amazon Bedrock - Model Selection, Prompt Design, and Cost OptimizationCompares the Anthropic Claude models available on Amazon Bedrock, provides model selection guidelines by use case, and covers prompt design best practices and cost optimization.