Perhaps you could describe that in a bit more

detail.

So, yes, and thank you.

We do find it an instructive and practically applicable analogy.

And this is the working dog analogy that Lawrence, yes, you're familiar with.

For anyone listening who isn't familiar with the analogy, it's quite simply that as a human society, we have for centuries been delegating autonomy to non-humans.

But it's not in perhaps the scenario that you might immediately imagine.

Are there other risks then we should consider in the context of agents? We've spoken a bit about some of the setup agents, setup risks, the tool risks, but there are also risks once you've deployed your agent.