Can you tell us a little bit about what that platform really entails, what it took to get that up and running?

For sure.

And so we called it, we started with managed inference and we're actually calling it managed AI because it's not just inference.

So we started by offering what we call tailored deployments that were these deployments that were suited for large customers that had very bespoke performance needs.

And then we extended that.

We now have a pretty rich product offering.

We have a model marketplace backed by our serverless inference service where you can come in, you can experiment with new models.

What does that really mean for you? And where do you think maybe the legacy providers might fall short compared to, say, a Crusoe?