Documentation / modules
Eval
Run scenarios through targets, score observations, and persist a safe report projection.
Repository
| Field | Value |
|---|---|
| Repository | github.com/looprig/eval |
| Version | v0.2.0 |
| GitHub | looprig/eval |
Description
Run scenarios through targets, score observations, and persist a safe report projection.
Where it fits
Eval is useful on its own when an application needs to run cases against a target, score observations, and write redacted reports. Within Looprig, it evaluates Inference targets and can observe Harness behavior. Eval defines the evaluation domain; Pluto packages that domain into a complete qualification product.
Dependencies
Dependents
None.