[cadamsdotcom]

Despite the snark I’ll engage.

The “get an immediate agent answer then a human expert’s fast-follow” is I think a great idea for many domains - imagine if you could get legal advice this way; the agent will have already explained the basics and the human expert just has to provide corrections - way less typing by humans.

Also, the corrections are now documented and could become future grounding for the agent.

[Terr_]

I expect the time-limited expert will actually end up being tasked with more pain per request.

They won't just need to understand what problem the requestor has (or thinks they have) but also validate that the "immediate" feedback wasn't subtly horribly wrong.

[dogleash]

> The “get an immediate agent answer then a human expert’s fast-follow” is I think a great idea for many domains

So, like what already happens when my boss asks claude something and I have to pick up the pieces. Except now it's everything he slops about the topic, not just the ones we discuss later?

[i_think_so]

Absolutely zero snark. I'm serious. (About the serious part; obviously not the joke part.)

> a great idea for many domains

I completely agree. This is a great idea. If you don't do something with it I'm stealing it. ;-)