Sign in
← AI PulseAug 6, 2026

Policy · news · Single-source brief

Amazon Bedrock AgentCore Introduces Temporal Policies and Rate Limiting

AWS has introduced new capabilities in Amazon Bedrock AgentCore, including temporal policies powered by Dogwood, an open-source policy language, and gateway rate limiting.

By Illumora Editorial

Source · Aug 6, 2026, 4:43 PM · On Illumora · Aug 6, 2026, 4:47 PM

Media from the primary source — shown here so you can stay on Illumora.

Rewritten from one allowlisted primary — not independent enterprise reporting. Lanes →

Brief drafted by Illumora’s editorial model from the linked primary source. Ops desk reviews flagged pieces. How we write →

Read the source →AWS Machine Learning Blog — Control agent behaviors and cost beyond a single action: new capabilities in Amazon Bedrock AgentCore | Amazon Web Services
Save

The AWS Machine Learning Blog has announced new features for Amazon Bedrock AgentCore. These updates include temporal policies, which are powered by Dogwood, a new open-source policy language designed for AI agents. Additionally, Amazon Bedrock AgentCore now offers rate limiting at the gateway level.

Key Points

  • Amazon Bedrock AgentCore now includes temporal policies.
  • These temporal policies are powered by Dogwood, an open-source policy language.
  • Dogwood is specifically designed for AI agents.
  • Amazon Bedrock AgentCore has also implemented rate limiting on the gateway.
  • These features aim to provide deterministic control over agent action sequences.
  • The new capabilities enable the setting of cost ceilings.
  • Cost ceilings are designed to remain effective regardless of agent behavior.

Context

According to the AWS Machine Learning Blog, these new capabilities in Amazon Bedrock AgentCore are intended to provide users with greater control over their AI agents. The introduction of Dogwood as an open-source policy language suggests a focus on transparency and community involvement in defining agent behaviors. The blog highlights that these features offer deterministic control over agent actions and cost management.

Why It Matters

These updates provide builders with mechanisms to manage the operational behavior and expenditure of AI agents deployed through Amazon Bedrock AgentCore. The ability to set deterministic policies and cost ceilings offers a structured approach to agent deployment, potentially reducing unexpected outcomes and costs.

What To Do

  • Review the AWS Machine Learning Blog announcement for details on Amazon Bedrock AgentCore's new features.
  • Investigate Dogwood, the new open-source policy language, to understand its syntax and capabilities for defining agent policies.
  • Explore the documentation for Amazon Bedrock AgentCore to learn how to implement temporal policies and gateway rate limiting.
  • Consider how deterministic control over agent actions and cost ceilings can be integrated into existing or new agent deployments.