In this segment from the August 7th episode of Cloud Report, Robbie Belson joined our team to show how AWS continues to make it easier than ever to build, connect, and optimize agents at scale.
It starts with the AgentCore harness: everything an agent needs to run in production, behind two API calls. Point it at your model, tools, skills, and instructions, and AgentCore handles the rest.
From there, the conversation turns to trust. As agents take on more autonomy, temporal policies help close an important gap, a new capability in AgentCore powered by Dogwood, a new open source policy language for AI agents. Instead of judging one tool call in isolation, the gateway looks at what the agent has already done, then permits or denies based on the full sequence of actions. In the demo, two workouts get scheduled and approved. A third that pushes past the daily limit is denied before it fires. Every call was fine on its own. The pattern was not, and the policy caught it.
Get hands-on!
Subscribe to AWS:
Create a free AWS account:
Try AWS for free:
Connect with an expert:
Explore more:
Why AWS?
Amazon Web Services is the world’s most comprehensive and broadly adopted cloud, enabling customers to build anything they can imagine. We offer the greatest choice of innovative cloud capabilities and expertise, on the most extensive global infrastructure with industry-leading security, reliability, and performance.
#AWS #AmazonWebServices #CloudComputing
|
2026/08/11
youtube
