4 Matching Annotations
  1. Last 7 days
    1. That distinction matters because agents do not act for themselves. They act on behalf of someone or something else: a person, a team, an organization, or a system goal. Their authority should be bounded by that delegation, not by a broad identity-based role that persists beyond the scope and duration of the original delegation.

      This para is where the penny dropped for me. Imagine a a general purpose agent that can do whatever you ask it to. It's meaningless to give that agent a role with fixed permissions outside of the context of a specific task request

    1. Denial does not terminate execution. It becomes feedback that guides what the agent does next.

      This creates a mental picture of an agent banging away at prohibited action to try and find a way round the prohibition - possibly by manipulating the context

    2. context changes.

      As context is a factor in the authorization decision and the agent can set the context, how can we ensure that the agent doesn't manipulate the context to get the decision that it wants to move forward with its plan.