Shashir Mehrotra

Don't do that again.

And so that's what that interface has to feel like.

You give a set of instructions, you give a set of triggers, and then you get feedback.

And you say, this worked, this didn't work.

We call them accept to look rates.

You're going to come back and you're going to look at it and say, yeah, that clearly didn't work.

It didn't work.

Maybe it might be it didn't work for the user.

They ignored my suggestions.

Maybe it didn't work for what you think was good work.

You looked at the output and said that wasn't particularly good work.

And you're going to train it.

And I think the idea of being able to train a custom agent for each person, for each product, I think is really interesting and compelling.

I don't think it's going to be easy to do for everybody, but the people who do it well will be like the prominent YouTube creators of today.

You're going to make a very deep connection with a broad set of people in a way that you're never going to capture with ad dollars or with selling water bottles.

I mean, I think Grammarly is the most obvious one.

Most of the other really good ones.

It's actually interesting.

Grammarly is a stack of models.

The base model is actually spelling.