Amazon Bedrock Guardrails adds InvokeGuardrailChecks API for agentic apps
AWS has launched the `InvokeGuardrailChecks` API for Amazon Bedrock Guardrails, enabling developers to apply individual safety checks at any point in agentic AI applications without needing to create guardrail resources.
Score breakdown
The `InvokeGuardrailChecks` API removes the requirement to pre-create guardrail resources, giving developers more flexible, granular control over where and when safety checks are applied within multi-turn agentic AI workflows.
- 01AWS announced the new `InvokeGuardrailChecks` API for Amazon Bedrock Guardrails.
- 02The API allows individual safeguards (safety checks) to be applied at any point in an agentic AI application.
- 03It does not require creating guardrail resources before applying checks.
AWS announced the `InvokeGuardrailChecks` API as a new addition to Amazon Bedrock Guardrails. The API is designed specifically for agentic AI application development, allowing individual safeguards — also called safety checks — to be applied at any point in an application's workflow without the prerequisite of creating guardrail resources.
The announcement, authored by Sandeep Singh on the AWS AI Blog, focuses on the practical application of this API for multi-turn agentic AI scenarios.
The announcement, authored by Sandeep Singh on the AWS AI Blog, focuses on the practical application of this API for multi-turn agentic AI scenarios. The post describes how the API works and provides guidance on using it to build safer agentic applications, addressing a gap in how safety checks could previously be integrated into complex, multi-step AI workflows.
Key facts
- 01AWS announced the new `InvokeGuardrailChecks` API for Amazon Bedrock Guardrails.
- 02The API allows individual safeguards (safety checks) to be applied at any point in an agentic AI application.
- 03It does not require creating guardrail resources before applying checks.
- 04The API is designed to support safe, multi-turn agentic AI applications.
- 05The post is authored by Sandeep Singh on the AWS AI Blog.
Topics
Summary and scoring are generated automatically from the original article. We always link back to the publisher and never republish images or paywalled content. Last processed Jun 17, 2026 · 10:39 UTC. How this works →