Santiago (@svpino) says simulations let users test an agent across real production conversations. The feature scores interactions and mocks costly services so the full workflow can be tested end-to-end.
I think Simulations will be huge (and it's probably the best feature of this release).
Basically, this will let you simulate how your agent works across real production conversations. It will score interactions and mock anything that costs money, so you can test everything end-to-end.
Catch it at the first user, not the four-hundredth. A new user’s bank link fails, the agent says “try again later,” and nothing shows up in the logs. Watch a team find the bug and fix it before anyone else hits it, with Agent Learning Services and Agent Data Services, launching today.
Source: Santiago · x.comPublished · added here
