Skip to main content
POST
Evaluate a pending creative review

Authorizations

Authorization
string
header
required

API key or access token

Path Parameters

creativeId
string
required

Creative review identifier. Use the reviewRef value returned by the queue to select one immutable review. A bare value always selects the AdCP creative-id namespace, including when numeric; creative:<id> is the explicit equivalent.

Minimum string length: 1
Example:

"review:42"

Body

application/json

Request body for advisory AI evaluation of a pending storefront creative review.

acceptance_policy_text
string

Optional storefront acceptance policy text for evaluating whether a buyer-submitted creative can be approved. This may include advertiser/category rules, creative asset rules, and manual-review workflow requirements.

Required string length: 1 - 50000
expected_brand
string

Optional brand the creative is expected to represent. If omitted, the evaluator tries to infer brand evidence from the submitted creative payload.

Required string length: 1 - 200
questions
string[]

Optional specific questions for the evaluator to answer about the creative.

Maximum array length: 8
Required string length: 1 - 300

Response

Evaluate a pending creative review

Advisory AI evaluation for a storefront creative review row. Evaluation does not approve or reject the creative.

creativeId
string
required

AdCP creative id that was evaluated.

Example:

"cr_abc123"

evaluatorId
string
required

Stable evaluator implementation id. Provider-backed evaluators expose the provider here.

evaluatorVersion
string
required

Evaluator implementation version.

status
enum<string>
required

Aggregate advisory status from the evaluator. fail means one or more checks recommend rejection.

Available options:
pass,
warn,
fail
recommendation
enum<string>
required

Advisory operator action. This endpoint never records the decision.

Available options:
approve,
manual_review,
reject
policyDecision
enum<string>
required

Policy confidence for automated creative approval. The safe default is needs_human_approval unless the evaluator has enough evidence to decide the creative is definitely on or off policy.

Available options:
definitely_on_policy,
definitely_not_on_policy,
needs_human_approval
summary
string
required

Short evaluator summary.

checks
object[]
required

Individual policy, brand, readiness, and visual checks supporting the recommendation.

answers
object[]
required

Answers to any requested evaluator questions.