Agent ecosystems: Identity, control, and the shadow AI problem
transcript
show notes
AI agents are no longer “features,” they’re becoming enterprise citizens with identities, permissions, runtimes, and a very real need for governance. In this episode of Pop Goes the Stack, Lori MacVittie and Joel Moses unpack Microsoft 365’s emerging agent ecosystem, including the idea of an “agent OS,” execution containers, agent frameworks, and identity initiatives like Entra Agent ID. The promise is clear: give enterprises a structured way to manage autonomous work before it spirals into entropy.
F5's Chief Digital Officer Alvina Antar joins the conversation to challenge a single-vendor worldview. As enterprises operate in hybrid, multi-cloud environments, they need neutrality, model choice, and a shared AI foundation that can evolve as new models and capabilities appear weekly. The discussion highlights why governance can’t be bolted on after the fact, and why security, semantic layers, routing, and prompt protections must be part of the foundation, not an afterthought.
The episode also reframes “shadow AI” and “shadow agents” as a discovery and rationalization problem, not just something to shut down. When everyone can build agents through low-code tooling, IT can’t simply say no. Instead, organizations need visibility, guardrails, and controls that enable safe innovation across the business.
A key takeaway is that agent identity is only the start. Enterprises must treat agents like employees from an IT lifecycle perspective, with structured onboarding, ownership, least-privilege permissions, time-boxed access, approvals for risky actions, and real offboarding to avoid orphaned agents and service-account style breaches. Ecosystems can help you start, but most organizations will still need to build their own path to interoperable, governed autonomy.