Skip to main content
GET
List AI Visibility runs

Authorizations

Authorization
string
header
required

An agent key (rpk_...) created in Settings → API & MCP, sent as Authorization: Bearer rpk_.... Bearer only: a cookie session can never drive this API. An OAuth 2.1 access token obtained from the same host works identically and lands on the same ceiling.

Headers

X-Workspace-Id
string

Which workspace to read. Omit it and you get the account’s home workspace, which on an agency account is often not where the live businesses are. A workspace this credential cannot read is refused with 403 rather than quietly answered from the default.

Query Parameters

q
string

JSON filter object, for example {"needs_response":true}.

sort_by
string

Field to sort on.

limit
integer

Maximum rows to return.

skip
integer

Rows to skip, for paging.

Response

Matching AI Visibility runs.

id
string

Unique id.

tracker_id
string
prompt_id
string
variant_index
integer
prompt_variant
string

The exact phrasing asked for this run — stored verbatim so the UI can show it even if the prompt's variations are regenerated later.

location_id
string
engine
string

Engine registry key, e.g. 'chatgpt' | 'gemini'.

provider
string

Which backend produced this run.

model
string

Exact provider model id used for this run (for reproducibility).

run_date
string

YYYY-MM-DD bucket used for daily rollups and dedup.

run_at
string
answer_text
string

The AI engine's full answer to the prompt.

brand_mentioned
boolean
brand_position
integer

1-based rank of the brand among all brands named in the answer; null when not mentioned.

brand_sentiment
string

'positive' | 'neutral' | 'negative' | 'mixed' — how the answer describes the brand.

brand_sentiment_score
number
competitors_mentioned
object[]

Brands the AI answer recommended as alternatives (discovered, not user-supplied). domain is set only when the answer/its citations contained it.

citations
object[]

Sources the engine cited (url_citation annotations / grounding chunks).

brand_entities
object[]
brand_cited
boolean

True when any citation domain matches the tracker's brand_domain.

competitor_domains_cited
string[]
cost
number

Optional estimated provider cost for this run, in USD.