Authoring Dogwood policies from natural language in Amazon Bedrock AgentCore
AWS launches natural language-to-Dogwood policy authoring for AI agent governance in Bedrock AgentCore
“Whatever your technical background, you can import policy documents written in natural language directly into the policy in Amazon Bedrock AgentCore to safeguard your deployed agentic systems.”
AWS expanded Amazon Bedrock AgentCore's Policy feature with AI-driven natural language authoring that converts prose policy documents into Dogwood formal specifications, now supporting temporal constraints, rate limiting, sequential tool-call ordering, and integration with Bedrock Guardrails. The launch lowers the technical barrier for enterprise teams to enforce governance controls over deployed AI agents without writing formal policy code by hand. This matters as agent governance tooling matures into a competitive differentiator for cloud AI platforms targeting regulated industries.