SentinelOne Announces AI Security Integration with Amazon Bedrock AgentCore to Deliver Runtime Guardrails for AI Agents
Prompt Security capabilities will be integrated with AgentCore, delivering runtime guardrails for organizations deploying AI agents at enterprise scale
SentinelOne® (NYSE: S), the AI Security leader, today announced its upcoming integration with Amazon Bedrock AgentCore. The integration will be delivered through SentinelOne’s Prompt Security offering. The integration reflects SentinelOne’s commitment to extending the security controls customers already trust into agentic workflows, empowering enterprises deploying AI on AWS to secure and scale their AI workflows.
Amazon Bedrock AgentCore is the platform to build, connect, and optimize agents at scale. Through its policy engine, AgentCore enforces real-time, deterministic controls at the gateway across all agent traffic including agent-to-tool, agent-to-LLM, and agent-to-agent communications. With this integration, SentinelOne’s Prompt Security will provide detection signals covering prompt injection detection, PII exposure, tool-use validation, LLM response monitoring, and data leakage prevention that feed into AgentCore policy engine. AgentCore acts on those signals at the gateway, outside the agent’s reasoning loop, so enterprise teams can apply SentinelOne’s detection signals alongside deterministic, automated enforcement consistently across all agent activity. Because detection can be probabilistic, but enforcement stays deterministic, customers gain consistent allow-or-deny decisions on every agent action, allowing organizations to adopt agentic AI at enterprise scale with the confidence that existing SentinelOne security controls apply automatically throughout every agentic workflow.
