Our agents can chain actions across systems—invoking tools, writing to storage, and updating records—and that kind of power carries real risk if the workflows aren’t properly governed. Orcas context makes it clear that agents may touch sensitive data, change configurations, or even reach the public edge, so we can see exactly where strong guardrails and human-in-the-loop checks need to sit. Rather than discovering risky agent behavior only after something breaks, we’re able to put policy in place where it matters most.

Our first wave of AI agents carried broad, long-lived permissions “just in case,” which quietly inflated the blast radius of each workflow. Orca shows effective permissions and actual usage side by side for agents and identities, so we can clearly see which rights are actually exercised and which are dead weight. That context gave us the confidence to move toward just-in-time access.

Teams across the company started spinning up AI agents that could call APIs, trigger workflows, and act on behalf of users, and a few of those agents ended up with far more access than anyone realized. Orca surfaces those agents alongside everything else in our cloud estate, showing which identities they run as, which services they can reach, and what data sits behind those permissions. Seeing that blast radius in a single view made it straightforward to decide which agents were actually needed, where scopes should be tightened, and where guardrails should be added before they caused any trouble.