See how Trussed maps to your regulation in minutes

    No generic demo, just the controls relevant to your program.

    Book Demo

    Check your EU AI Act status

    Get a free risk tier assessment and personalized gap checklist in 5 minutes.

    Take the Assessment

    AI Agent Governance

    Agent Capability Ledger

    An agent capability ledger is a time-stamped, auditable record of the capabilities, permissions, and tool access granted to an AI agent over the course of its operation. It differs from traditional access logs by recording authorization state, not just actions taken, making it possible to reconstruct what an agent was permitted to do at any point in time.

    Explore Runtime Governance Learn About AI Agent Security

    Core Components of a Capability Ledger

    A capability ledger is generally built around a small set of recurring structural elements, regardless of how a specific implementation records or stores them.

    </
    Core elements of a capability ledger and their function
    Element Description
    Capability Grants Discrete events recording when a specific permission or tool access is authorized for an agent.
    Revocations Time-stamped records marking when a previously granted capability is withdrawn or expires.
    Time-Bound Permissions Grants scoped to a defined window rather than indefinite access.