Term · Collection and scoring
Collection unit
Definition
One result for a specific prompt and AI surface within a run.
How it is calculated
A successful unit completed provider collection. For Google AI Overviews, a successful unit may still contain no overview because that is a valid outcome. A unit is also the unit of failure: when a batch of prompts cannot be collected, every unit in that batch is recorded as failed rather than silently absent, which is what lets a run finish and still report a shortfall.
Where to see it
This term describes part of how refd collects and scores AI answers. The methodology page sets out the full contract, and the demo shows the same concepts against a live sample workspace.
The definition above is the one the product uses. It is read directly from the same source the dashboard and the MCP server read, so this page cannot drift from the software.
See your evidence