Amazon Web Services (AWS) released an open-source policy language, "Dogwood," on the 13th that can control not only individual actions of AI agents but also the sequences in which multiple actions occur, validating continuous task flows based on an AI agent's past action history. AWS applied a "time-based policy" built on Dogwood to the policy features of Amazon Bedrock Agents Core, which considers the agent's prior actions along with the current request to decide whether to allow the next action, unlike existing policies that judged individual tool calls independently. For example, it can block behaviors such as repeatedly making payments under the approval limit that cumulatively exceed the overall budget, or moving to the next step without going through a specific task, and can require human approval before important tasks. Policies are enforced at the gateway layer, not in the agent code, preventing agents from bypassing policies due to prompt injection or code errors. Dogwood is compatible with the existing open-source policy language "Cedar," is based on temporal logic, and is released under the Apache 2.0 license, usable without rewriting existing policies. AWS also added a "rate limiting" feature to the Agents Core gateway to cap AI usage per user, managed by user, team, tool, and model based on metrics such as requests per minute, tokens processed per minute, and concurrent consolidation. AWS said both features can be applied without redesigning existing AI agents.