Amazon Bedrock Guardrails announces a new API targeting agentic AI workflows
News
Amazon Bedrock Guardrails announces the InvokeGuardrailChecks API, a resourceless API for applying safeguards at any point in agentic AI applications without creating guardrail resources.
- Provides granular per-request control over which safeguards to run at each agent loop step
- Returns numeric severity and confidence scores for custom thresholds and actions
- Operates in detect-only mode with no guardrail IDs or versions to manage
- Supports content filters, prompt attack detection, and sensitive information filters
- Exposes prompt attack detection as separate safeguards for independent invocation
- Available in seven AWS regions including US East, US West, Europe, and Asia Pacific
The API enables flexible, scalable safeguarding for agentic AI workflows with different risk profiles at each step.
The AWS News Feed is currently looking for gold sponsors. If you want to support the AWS community and reach a large audience of AWS professionals, consider sponsoring the AWS News Feed.
Related articles
Jun 16
2026
2026
Safeguard your agentic AI applications with the Amazon Bedrock Guardrails InvokeGuardrailChecks API
Jun 17
2026
2026
Amazon Bedrock AgentCore now supports Bedrock Guardrails in policy
Apr 8
2025
2025
Amazon Bedrock Guardrails announces new capabilities to safely build generative AI applications
Mar 18
2025
2025
Amazon Bedrock Guardrails announces IAM Policy-based enforcement to deliver safe AI interactions
The AWS News Feed is currently looking for silver sponsors. If you want to support the AWS community and reach a large audience of AWS professionals, consider sponsoring the AWS News Feed.