Access Control
Access control is the security discipline of regulating who or what can view, use, or modify resources in a computing environment. It encompasses the policies, mechanisms, and technologies that determine what actions an authenticated identity is authorized to perform.
Why It Matters
Access control operates at multiple layers: network access control (who can connect), application access control (who can use a feature), data access control (who can read or modify specific records), and action-level access control (who can perform specific operations).
AI agents require action-level access control because their behavior is non-deterministic. The same agent might need read access for one task and write access for another. Authorization evaluated at the action level, per tool call, is what matches that behavior: a decision made once at connection time cannot account for what the agent does next.
The evolution from coarse-grained (network perimeter) to fine-grained (per-action) access control mirrors the progression from on-premises to cloud to agent architectures. Each shift increases the granularity of trust decisions required.