AI Security Agents is a great addition, but I feel like the accuracy is lagging behind other competitors. Claude integrations seems still early in development.

There was a recurring problem with shadow data: production data getting copied into staging and dev accounts that were nowhere near as locked down, plus data stores nobody even remembered creating. Orca discovers sensitive data across managed, unmanaged, and shadow stores, including files on VMs, containers, and buckets, and then classifies it against categories like PII and payment data. Seeing a forgotten production snapshot sitting in a loosely controlled dev account, and having that tied to how exposed the account was, makes it obvious which copies are genuinely risky versus intentional.

This is a large organization with dozens of cloud accounts spread across business units, and each unit used to do its own thing. Orca connects to all of them and provides one structured view, while still allowing each account to be viewed on its own. That same view also makes it much easier to see where the AI agents are showing up across accounts and business units, so the agents become part of the same governed picture as everything else. It also makes it possible to compare posture across business units and quickly see which ones are carrying the most exposed, exploitable risk. As a result, reviews with each unit are far more concrete than the generic reports that used to circulate.