Skip to main content
A rate tells you how often you were named. It does not tell you who had the answer when you were not, and “named in 0% of answers” reads the same whether a rival took every answer or nobody was named at all. Those are different jobs. State is the word for that difference: one per engine (the cell), and one for the prompt across its engines. State is folded from the same answers as the rates beside it, so a cell and the percentage next to it never come from two different samples.

​
Cell state: one prompt on one engine

A cell is read from the latest reading in the window that has at least one successful answer on that engine. Failed answers do not count; a reading where every answer failed is skipped and the one before it is used. With n successful answers in that reading: The rules are checked in that order, and the first that holds wins.
  • At least half, not at least one. A cell is a label on n answers. At sampling depth 3, a label that one answer in three could flip would move inside the sampling noise. Ties go to you: named in 1 of 2 answers is Named.
  • Lost needs a rival in the words. A competitor counts only when the answer names it in its text. A competitor that appears only among the links is a source, not a name the answer chose. A lost cell says which rival, the one named in the most answers (ties broken alphabetically), and when the reading was taken.
  • Absent is a measurement. It means the answers were read and nobody you track was named in enough of them. Not measured means there was nothing to read. The grid draws them differently, and never one in place of the other.
A cell that is not measured always says why, on hover:

​
Prompt state: one prompt across its engines

The prompt’s state is folded from its cells. Only measured cells count: let M be the number of engines with a measured cell. The precedence is won, then contested, then lost, then absent. A prompt named on one engine and lost on two is Contested, not lost: you are in the answer somewhere. An engine that is not measured is left out of M. It neither helps nor hurts the prompt, because counting it would turn a gap in our coverage into a claim about your brand. A prompt read on four engines, where one failed for the whole window, is judged on the other three. The board also counts the engines a prompt is lost on. That number sorts the losses first, and it is what the analytics overview’s “Where are we losing” block ranks by.

​
Where you see it

  • Prompts: the Standing column is the prompt state, and each engine column is that engine’s cell. You can filter and group by standing; grouped, the groups run worst first (lost, absent, contested, won), with not measured last because “never read” is not a low score. A group’s summary counts its prompts in each state, for example “3 lost · 1 contested · 2 won”.
  • The prompt page: each engine shows its state with the n it was read over and when, from the same rule, so the page and the board never disagree.
  • CSV export: a state and lost_on column per prompt, and a <engine>_state and <engine>_state_n column per engine. An empty cell is not measured, which is not absent.
  • Over MCP: query_evidence counts prompts by state (prompt_state_count) and filters any metric by state. See MCP tools.

​
Reading it

State is a word, not a trend. It describes the latest successful answers in the window, so it moves as soon as one reading moves, and a single reading at sampling depth 1 can only ever be all or nothing. Read the n beside a cell before you act on it, and use the rates and their significance test for whether anything changed. Next: Share of voice for the rate behind Named, and Competitors for the rivals a Lost cell names.