oso
oso copied to clipboard
Enable evals to run automatically for every deployment
What is it?
Evals should be running for every deployment much like we run tests. This should only happen on pushes to production.
Some questions:
- Should this just run in a separate container (like a job?)
- Should we run this as some endpoint?
Going to deprioritize this for now. We have !run_eval in Discord
I think we need to decide how often we want to run these.