The defining characteristic of an enterprise AI agent isn't its intelligence, but its specific, auditable permissions to perform tasks. This reframes the challenge from managing AI 'thinking' to governing AI 'actions' through trackable access controls, similar to how traditional APIs are managed and monitored.

Simply giving an agent a user account is dangerous. An agent creator is liable for its actions, and the agent has no right to privacy. This requires a new identity and access management (IAM) paradigm, distinct from human user accounts, to manage liability and oversight.

Traditional identity models like SAML and OAuth are insufficient for agents. Agent access must be hyper-ephemeral and contextual, granted dynamically based on a specific task. Instead of static roles, agents need temporary permissions to access specific resources only for the duration of an approved task.

Adopting a comprehensive AI identity model can be done in phases. First, register agents as governable actors with stable identities and roles. Later, add runtime instance linkage and detailed context lineage. This incremental path provides immediate and significant governance gains without requiring a complete overhaul of identity systems from day one.

Todd McKinnon conceptualizes AI agents not as simple tools but as a fundamentally new identity category. This identity possesses attributes of both a human user (roles, permissions) and a system (automation, being headless). This reframing is central to building the next generation of enterprise security and access management.

Current identity standards like OIDC are insufficient for AI agents. The future requires a "three-legged stool" identity combining a service account (the agent's identity), owner role claims, and "on-behalf-of" claims inherited from the user.

Traditional audit logs and screenshots are inadequate for AI agents. To ensure accountability, every agent needs a distinct, machine-readable identity, like a Decentralized Identifier (DID). All agent actions should be cryptographically signed and recorded in a tamper-evident ledger to create a trustworthy audit trail.

The rise of autonomous software agents like Cognition's "Devin" introduces a new, critical security layer: agent identity. Organizations must decide if agents have their own unique identities or inherit them from the deploying user. This is fundamental for creating auditable logs and securing their actions.

Don't let fears of "directory overload" prevent you from creating attributable AI agents. The governance requirement to trace every agent action is non-negotiable. The solution is not infinite directory entries, but a system of stable identities linked to temporal records for a full audit trail. The technical implementation should not compromise the governance requirement.