Anton Chuvakin discusses why AI agents have expensive limits. Token costs add up fast, and when agents fail, humans have to step in to fix things. Automation isn't the whole answer in security work.
This is probably something that's worth discussing. I don't want to say, no, you're wrong. I agree with you. But I'm afraid people would show up with pitchforks and say—
Yeah. And there's certainly a view that once an alert triggers, you can execute an agent and it will work, right? No. Money. The tokens. Tokens. Sorry. Capacity.
We use this euphemistic term tokens, but we really mean money. Yeah. Monetary tokens, listeners.
The cost of that. And then if you think about Like, let's say that agent does not execute the way you want to, and then your human needs to come back in. Your human is going to start back from the beginning at the alert.