[serjester]

I feel like the better positioning would be evals for voice agents. It seems just as challenging to figure out all the ways your system can go wrong, as it is to build the system in the first place. Doing this in a way that actually adds value without any domain expertise, seems impossible.

If it did, wouldn't all the companies with production AI text interfaces be using similar techniques? Now being able to easily replay a conversation that was recorded with a real user seems like a huge value add.

[sumanyusharma]

Absolutely agree that creating effective evals requires domain expertise. Right now, we're co-building evals with customers, but we're identifying which aspects can be productized.

Regarding text-based evals — part of testing voice agents involves assessing their core reasoning logic. To do that, we bypass the voice layer and simulate conversations via text. So yes, the core simulation engine is reusable for both conversational text and voice interactions.

We're also excited about shipping the ability to replay a simulated conversation inspired by a real user!