BriefsWorkflowAvailable now1 min read

AWS details Amazon Bedrock AgentCore governance features for AI agents

AWS published a guide on governing AI agent access at scale using Amazon Bedrock AgentCore Gateway, Cedar policies, and Okta Cross App Access.

AWS details Amazon Bedrock AgentCore governance features for AI agents — image from AWS
Image: AWS

Summary

AWS released a guide on scaling AI agent governance with Amazon Bedrock AgentCore Gateway, Policy, and Observability. The setup routes agents through a single Gateway endpoint, checks tools against Cedar policies, and tracks requests with OpenTelemetry spans and CloudWatch. It also integrates Okta Cross App Access to handle agent permissions without embedding credentials in the runtime.

What changed

  • Amazon Bedrock AgentCore Gateway serves as a single front door for agents, holding the target registry and redeeming Okta grants.
  • Policy in Amazon Bedrock AgentCore evaluates Cedar policies to bind each tool to the agent and delegated scope.
  • Amazon Bedrock AgentCore Observability and CloudWatch collect OpenTelemetry spans for every request hop.
  • A second reporting agent runs on Amazon EKS under its own Okta identity to demonstrate multi-agent support.

Availability

Available now

“The additions take about 90 minutes. The EKS control plane costs $0.10 per hour, plus nodes and the Amazon EKS Auto Mode management fee, and the AgentCore features charge for what you use.”

Pricing

PlanPrice, as statedChecked
EKS control plane$0.10 per hour“The EKS control plane costs $0.10 per hour, plus nodes and the Amazon EKS Auto Mode management fee, and the AgentCore features charge for what you use.” source

Prices as stated by the company; we don’t convert or estimate.

Founder takeaway

Small teams scaling multiple AI agents should route requests through a centralized gateway and use policy engines like Cedar rather than copying access checks into individual tool servers.

Source

Researched and drafted with AI from the official sources above, then checked automatically before publishing. Spotted a mistake? Tell us.

SharePost on XLinkedIn

Related

More briefs

All briefs
  1. AWS releases a responsible AI framework and assessment skill for agentic AI — image from AWS

    WorkflowAvailable now

    AWS releases a responsible AI framework and assessment skill for agentic AI

    AWS introduces a three-phase maturity framework and a portable AI skill to evaluate responsible AI posture for agentic AI platforms and applications.

    AWS1 min read

  2. Zapier adds support for building Telegram AI agent automations — image from Zapier

    WorkflowAvailable now

    Zapier adds support for building Telegram AI agent automations

    Zapier now lets you build and run Telegram automations using an AI assistant and 10,000+ app integrations.

    Zapier1 min read

  3. ElevenLabs details production use cases for ElevenAgents in retail and travel — image from ElevenLabs

    WorkflowAvailable now

    ElevenLabs details production use cases for ElevenAgents in retail and travel

    ElevenLabs outlines how companies use ElevenAgents for voice AI bookings, customer support, and lead qualification across retail, travel, and hospitality.

    ElevenLabs1 min read

One email, every Monday

Briefs are published here through the day. Monday Heist is the email: one useful AI workflow, the files to use it, and the catch. The first issue is being prepared; subscribers get it first. Free, and you can leave in one click.

One email. Every Monday.