Domain expert evaluation

The operating task

Assess model behaviour using specialist judgement and an agreed evaluation rubric. Specialist contribution is shaped around the quality of the signal and its usefulness to model development.

Softinator's contribution

Apply specialist judgement to model behaviour in tasks where generic scoring misses the important distinction. The commissioned output includes evaluation rubric and reviewed output set.

Acceptance in use

Review correctness and usefulness within the expert domain, retaining the context behind the judgement. The engagement defines the baseline, task scope and evidence used to assess the resulting contribution.