signalLobsters2026-09-28
DogWood: Monitoring Policies using First Order Temporal Logic
Dogwood is an open source governance language for AI agents, based on first-order temporal logic, enabling policies that consider sequences of tool calls. It extends existing Cedar policies with temporal conditions to enforce ordering, rate limits, and prerequisites. Released under Apache 2.0, Dogwood is now supported in Amazon Bedrock AgentCore Policy.
- for who
- Teams building AI agents that need to govern tool usage and enforce safety policies.
- why now
- AWS just released Dogwood, open source temporal policy language for safer AI agent tool use.
- what changes
- They can now express policies over sequences of actions, not just single calls, using temporal logic.
- to do
- Adopt Dogwood to write temporal policies for agent tool use, using its compatibility with Cedar and AgentCore Policy.
key points
- Dogwood is an open source governance language for AI agents.
- It adds temporal conditions to Cedar policies for sequences.
- Released under Apache 2.0 with AgentCore Policy support.
#ai safety#temporal logic#open source#agent governance
score
score 7 out of 10. 0-10: how dense the facts are, multiplied by how much you can do with them after reading. 8+ means the topic's evidence bar is met: benchmarks and availability for a new model, amount and investors for a funding round, revenue figures for a solo-money story. Below 5 an item does not enter the digest. A press release scores 3 or less, a reprint loses 2, anything older than 14 days loses 1, a headline that misleads loses 3.
read the source