Returns the prompt record identified by the integer
prompt_id (the 1-based position the prompt occupies inside
the universe — 1, 2, 3, …). Optional day and engine
query params pin the lookup to a specific run; without them
the most recent matching row is returned.
Use this when you have a prompt’s position from another
endpoint (for example prompts_rows[*].prompt_id) and want
the full row including response_text.
Generate a key at /dashboard/settings/api-keys. Pass it as
Authorization: Bearer vso_xxx on every request.
Universe UUID — see GET /universes.
1-based position of the prompt inside the universe.
x >= 1Pin the query to a specific day (YYYY-MM-DD). Without this, returns the most recent day.
Filter to a single AI engine. Omit for all.
chatgpt, gemini, grok, claude OK
Single row from the prompts table — one row per
(universe, day, engine, prompt_id). Every column is documented
below as a separate response field. response_text carries the
full AI answer body and my_citations / competitor_citations
carry the actual cited URLs.