Really liked how you framed the shift from capability to authority here.
An agent being technically able to do something tells us very little about whether it should be allowed to do it. As agents move from calling tools to operating inside real environments, that distinction becomes much harder to ignore.
The visibility gap is only part of it. We also need to know where the authority actually ends.
Exactly. That's where things start getting interesting. Because we all know that agents are capable -- but how do we make sure they do the right thing (and only the right thing)? By designing around authority.
Really liked how you framed the shift from capability to authority here.
An agent being technically able to do something tells us very little about whether it should be allowed to do it. As agents move from calling tools to operating inside real environments, that distinction becomes much harder to ignore.
The visibility gap is only part of it. We also need to know where the authority actually ends.
Exactly. That's where things start getting interesting. Because we all know that agents are capable -- but how do we make sure they do the right thing (and only the right thing)? By designing around authority.