Prompt cohort

How it is calculated

A brand_defining prompt names your brand, an alternative prompt names only a tracked competitor, and a discovery prompt names neither, so its rate is unprompted visibility. Cohorts are classified from the prompt text against the same matcher that scores a mention, and a prompt naming both your brand and a competitor counts as brand_defining. Problem and market_perception are declared rather than derived: telling a problem-shaped question from a broad discovery one, or a question about how the market sees the category, is a judgement about buyer intent rather than a substring, so those two are chosen at setup and can be changed at any time. Every prompt is classified on the first read that needs it, so an unclassified prompt never reports as a cohort of its own. Cohort is independent of prompt category: the Discovery category is a buyer-journey stage, while the discovery cohort is the absence of any tracked name in the text.

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.