SentinelOne (NYSE: S) announced a planned integration with Amazon Bedrock AgentCore, according to a company press release. The integration will be delivered through SentinelOne's Prompt Security offering and is expected to be available later this year.

Amazon Bedrock AgentCore is a platform for building and managing AI agents at scale. Its policy engine enforces real-time controls at the gateway across agent traffic, including agent-to-tool, agent-to-LLM, and agent-to-agent communications.

Through the integration, SentinelOne's Prompt Security will provide detection signals covering prompt injection detection, personally identifiable information (PII) exposure, tool-use validation, LLM response monitoring, and data leakage prevention. These signals will feed into the AgentCore policy engine, which acts on them outside the agent's reasoning loop to enforce allow-or-deny decisions on agent actions.

"Every organization building and running AI agents on AWS needs the same security controls they rely on across the rest of their infrastructure," said Melissa K. Smith, SVP of Global Strategic Partnerships and Initiatives at SentinelOne. "This upcoming integration applies those guardrails at the AgentCore gateway, where all agent traffic is evaluated."

Customers with existing Prompt Security licenses will be able to apply them through a Bring Your Own License path.