# add_questions (/reference/add-questions)



Before a scoring model is calibrated, the questions you add count right away; after, they're tried at the next calibration. See [Changing questions](/concepts/scoring-models#changing-questions). Free.

## POST https://api.finic.ai/v1/scoring_models/{model_id}/questions

Adds your own yes/no questions about a record to a scoring model, without calibrating it.

- **If it isn't calibrated yet,** the score uses them right away, each with a weight Finic estimates.
- **If it's calibrated,** they're asked on every score call and tried at the next [calibration](/reference/calibrate), which uses them if they help: with examples, or with outcomes once 30 of the records they were asked about have one. Until then they're listed as not used on its page in the Finic Portal.

Up to 20 at a time, 50 of yours per scoring model (used or not), 500 characters each. See [Changing questions](/concepts/scoring-models#changing-questions).

Authorization: `Bearer <API key>` (see [Authentication](/authentication)).
- Path parameter `model_id`: The scoring model's `model_id`.

### Request body (application/json)

| Field | Type | Required | Description |
| --- | --- | --- | --- |
| `questions` | array of string | yes | Your own yes/no questions about a record, such as "Was the account opened less than a week before the payment?". |

Example:

```json
{
  "questions": [
    "Was the account opened less than a week before the payment?"
  ]
}
```

### Responses

- **200**: The scoring model, as [get_scoring_model](/reference/get-scoring-model) returns it, with `added`.

```json
{
  "model_id": "scm_01M4XRC000RT2GZSKYPD8J86G9",
  "name": "Card-not-present payment fraud",
  "status": "ready",
  "criteria": "Card-not-present payments at an online store. Bad: the payment was charged back as fraud within 90 days.",
  "created_at": "2026-10-20T17:04:11Z",
  "calibrated_at": null,
  "archived_at": null,
  "examples": 0,
  "bad_rate": 0,
  "scored": 12,
  "outcomes": 0,
  "questions": [
    {
      "id": "q003",
      "text": "This record is a card payment. Is the IP address in a different country from the billing address?",
      "source": "finic",
      "weight": 1.24
    },
    {
      "id": "q009",
      "text": "Was the account opened less than a week before the payment?",
      "source": "user",
      "weight": 0.93
    },
    {
      "id": "q006",
      "text": "This record is a card payment. Has this card paid this merchant before without a dispute?",
      "source": "finic",
      "weight": -0.71
    }
  ],
  "added": [
    {
      "id": "q009",
      "text": "Was the account opened less than a week before the payment?",
      "used": true
    }
  ]
}
```

- **400**: `invalid_request`: `questions` is missing or has more than 20; a question is blank, over 500 characters or already one of the scoring model's; or it would have more than 50 of yours.

- **401**: `authentication_error`: the API key is missing, unknown, revoked or expired.

- **404**: `scoring_model_not_found`: no scoring model with this `model_id` in your organization.

- **409**: - `scoring_model_not_ready`: the scoring model is still being created, or creating it failed.
  - `scoring_model_archived`: the scoring model is archived.
  - `calibration_in_progress`: it's being calibrated. Add the questions when its job completes.
  - `conflict`: it changed at the same moment. Try again.

- **429**: `rate_limited`: 50 changes to this scoring model in the last 24 hours (question changes, calibrations and creating it), or over the [request rate](/reference#rate-limits).

- **503**: `overloaded`: the questions couldn't be added just now. Try again.