What is a prompt run?

A run is a single answered instance: this prompt, sent to this model, at this time. It stores the answer, the claims extracted from it, the citations attached to each claim, and whether competitors appeared.

Runs are the unit every citation metric is computed over. The word "answer" in those definitions means a run.

Call it

GET/org/analytics/answers/latestOpen in API reference →The most recent run per prompt.

GET/org/analytics/prompts/{promptId}Open in API reference →One prompt over time.

GET/org/run-modelsOpen in API reference →Which models runs execute against.