Evaluation & Evidence History

Inspect recent command activity, generated artifacts, model-usage observations, evaluation reports, and compatible run comparisons. Workspai records measured evidence without turning one repository, fixture, or model run into a universal performance claim.

#"Compare this evaluation with the compatible baseline"

Finalize the current privacy-bounded evaluation reportready

optional global install:

Install Free Extension All features

What you get

01Command outcomes and governed artifact paths
02Freshness, provenance, and workspace scope remain visible
03Privacy-bounded model-usage observations
04Compatible baseline-versus-candidate evaluation comparisons
05No universal efficiency claim from one fixture or model run

Workspai CLI · same workspace truth

CLI reference Kits catalog RapidKit Core

Ready to try it

Use Evaluation & Evidence History in your workspace

Start with the open-source CLI, then use the free VS Code extension when you want the same evidence in the sidebar, dashboard, or Studio.

Open CLI reference Install VS Code extension