Tag: #cedar

Content tagged with "cedar"

Blog Posts

Blog

Agentic AI security starts with treating agents like employees: Unpacking the 7 principles for financial services

A deep dive into the AWS Security Blog's agentic AI security framework for financial services. Reorganizes the 7 design principles into three axes—permissions, traceability, and controls—with Bedrock AgentCore implementation guidance.

March 28, 20264 min read

ai-agents

#bedrock #agentcore #security+2

Blog

Controlling Agent Tool Access with Bedrock AgentCore Policy and Cedar Authorization

Hands-on verification of Bedrock AgentCore Policy: Cedar-based tool access control via Gateway, natural language policy generation, and default deny behavior validated with real API calls.

March 15, 20265 min read

ai-agents

#bedrock #agentcore #cedar+2

TIL

AgentCore Policy rejects Cedar permit without conditions as Overly Permissive

Creating a Cedar permit without a when clause in Bedrock AgentCore Policy fails with CREATE_FAILED due to FAIL_ON_ANY_FINDINGS automated reasoning.

March 15, 20261 min read

#agentcore #bedrock #cedar+1