We use essential cookies to make our site work. With your consent, we may also use non-essential cookies to improve user experience and analyze website traffic. By clicking “Accept,” you agree to our website's cookie use as described in our Cookie Policy. You can change your cookie settings at any time by clicking “Preferences.”
    See how AI recommends your business — free →

    Delta Report Details

    Partner ProgramAuthentication required

    delta_report_details

    Return per-question, per-model answers from a completed audit, including answer text, expected ground truth, accuracy, and owned versus third-party citations.

    Access: Partner Program or approved access with read_brand permission

    When to use

    Use to understand why a score moved or identify exact claims and sources that need correction.

    Parameters

    Parameter Type Required Description
    run_id string Yes Completed audit run ID from delta_report or delta_report_history.
    limit number No Maximum answers; default and maximum 50.
    offset number No Pagination offset.
    only_grounded boolean No Only include answers with citations.
    brand_slug string No Brand selector for internal superadmin keys. Brand-scoped keys ignore it; OAuth users select an authorized brand with brand_id.

    Try this in Claude

    Which questions did AI answer incorrectly in our latest audit?

    Example request

    {
      "run_id": "run_123",
      "only_grounded": true
    }

    Example response coming soon.

    Related tools