aiqbench takeAI Policy

AWS has open-sourced Dogwood to extend the deterministic Cedar policy framework with temporal logic capabilities. This new capability allows governance rules to evaluate an agent's history of tool calls rather than assessing isolated requests in isolation, enabling complex constraints like running totals and sequential approvals within AI agent workflows. While the reference interpreter is not yet production-ready, this development marks a significant step toward robust control layers for autonomous agents that require stateful reasoning over action sequences.

Source coveringInfoQ

What this isA model's reading of the article and related coverage, written for aiqbench. Not the publisher's words.

AWS Open-Sources Dogwood, Extending Cedar to Govern Sequences of Agent Tool Calls

InfoQAugust 16, 20264 min read

AWS has open-sourced Dogwood, a policy language extending Cedar with temporal conditions so rules can reason about an agent's prior tool calls rather than one request in isolation. It covers approvals, rate limits and running totals, ships under Apache 2.0, and is supported in AgentCore Policy, though the reference interpreter is not production-ready. By Steef-Jan Wiggers

AWS recently open-sourced Dogwood, a policy language for agent tool calls. What makes it different from Cedar is that its rules can look backward at what the agent already did. It ships under Apache 2.0, and AgentCore Policy supports it today. AgentCore Policy launched at re:Invent last year. It sits outside the model as a deterministic control layer. The model proposes a tool call, the policy engine accepts or rejects it, and the model never touches enforcement. Cedar…

Excerpt shown under the publisher's RSS terms · 78 words · full text and figures are on the publisher's site

Read at InfoQ ↗Ask about this article