Logan Kilpatrick

You mentioned the live API stuff, the stream real-time mode, and being able to build interactive sort of co-present AI experiences that don't just see text, but they can understand the audio that you're saying.

You can actually share your screen.

And back to this context engineering problem, what makes using AI products so hard in many ways is that you have to do, in most products, you have to do the context engineering yourself.

And this is actually one of the breakthrough projects

product experience things that a lot of these IDs have done that like has made this helpful is that actually all the context most or if not all the context, most of the context you need is in your ID somewhere.

So if you can just traverse through what's in your ID, you will eventually get all the right context to theoretically solve the problem that you have at hand.

That's actually not true on in most products like the the scope of if I'm trying to solve some like

you know, I need to email someone and book a trip and do whatever, et cetera, et cetera.

The context is spread across potentially the entire internet or some like unbounded state space that I by default don't actually know.

And what's cool about the live API and stream real time is basically all this context you need to solve the problem is in some case visible on my screen in some way.

Like during, throughout the day, all the context for me to do my job

you know, however many hours a day shows up on my computer screen.

The AI system doesn't need some other, you know, access to some other tools.

Like all the context is there.

It is connected to my computer.

It's already present.

So there's something really interesting about building infrastructure to do this.

And I think we're still early in like allowing and like building a bunch of products that make use of that.

But I'm excited.

And then the other use case you mentioned was around text to speech.