Skip to content

Your AI agent’s next tool call may be valid but wrong. AWS’s Dogwood promises to fix that.

7.7 relevance
Score Breakdown
technical depth
8
novelty
9
actionability
7
community
5
strategic
7
personal
9

Scored daily by a customisable AI persona to surface the most relevant engineering leadership news.

AWS Dogwood is a novel open-source policy language for AI agent governance, directly relevant to agent orchestration and infrastructure.

AI/ML thenewstack.io
Your AI agent’s next tool call may be valid but wrong. AWS’s Dogwood promises to fix that.
Summary

AWS open-sourced Dogwood, a policy language and interpreter under Apache 2.0 that governs sequences of AI agent tool calls, extending Cedar's point-in-time authorization with temporal conditions. Dogwood enables policies that check prerequisites, rate limits, and ordering—for example, allowing a stock-trading agent to sell shares only if an approval tool returned positive within the past hour. It is now supported in Amazon Bedrock AgentCore Policy, using Metric First-Order Temporal Logic to evaluate event sequences and parallel calls.

Author

Frederic Lardinois

More from Frederic Lardinois →