Public story · 2026-03-10 · source-backed
AWS Bedrock AgentCore Policy GA
Story
AWS shipped the first cloud-native, declarative agent governance layer to general availability. Policy intercepts AgentCore Gateway tool calls before execution, enforcing Cedar policies auto-generated from natural language rules. Automated reasoning validates each policy against tool schemas and flags unsafe conditions. Available across 13 regions with CloudWatch audit logging. AWS Blog
Related stories
Each link below shares sources, entities, or timing with this story.
Shared entities / Same source / Shared topic
AWS Bedrock AgentCore Policy Reaches GA — First Production Agent Governance Primitive
Both cover AWS Blog, Cedar, CloudWatch, Policy; cite the same source (AWS Blog); overlapping topics (agent, agentcore, automated, availability, bedrock).
Shared entity: CloudWatch / Same source domain / Shared topic / What happened next
Bedrock AgentCore hits GA with a two-call deploy model.
Both cover CloudWatch; reported by the same outlet (aws.amazon.com); overlapping topics (agent, agentcore, bedrock, cloudwatch, tool).
Shared entity: Cedar / Shared topic / What happened next / Tension
Cedar Beats OPA for MCP Access Control on Safety-Critical Properties
Both cover Cedar; overlapping topics (against, agent, cedar, policy, tool); picks up the Cedar thread on 2026-03-20.
Same source domain / Shared topic / Tension
Agent Security (Priority: +2.0)
Reported by the same outlet (aws.amazon.com); overlapping topics (against, agent, audit, call, tool); pushes against this story (against).
Shared entity: AWS Blog / Same source domain / Shared topic / What happened next
ReWOO: Static Plan Validation Before Execution.
Both cover AWS Blog; reported by the same outlet (aws.amazon.com); overlapping topics (declarative, tool).
Shared entity: Automated / Shared topic / What happened next
Every Major MCP Client Is Vulnerable to Prompt Injection via Tool Poisoning. All Seven Tested. All Seven Failed.
Both cover Automated; overlapping topics (agent, audit, tool); picks up the Automated thread on 2026-03-26.
Shared entity: Cedar / Shared topic / What happened next
Sondera Hooks: Cedar Policy Language for AI Coding Agents.
Both cover Cedar; overlapping topics (agent, cedar, policy); picks up the Cedar thread on 2026-03-23.
Cedar for MCP Access Control: Formally Verifiable Agent Guardrails.
Both cover Cedar; overlapping topics (agent, cedar, policy); picks up the Cedar thread on 2026-03-20.
Source trail
Entities
Provenance
- Canonical issue
- Ramsay Research Agent — 2026-03-10
- AI generated
- no
- Story unit
- 2026-03-10-aws-bedrock-agentcore-policy-ga
- Labels
- source-backed, canonical briefing excerpt