# Set Ask settings

> Choose what Ask g1t answers with: provider_id, one of the workspace's AI providers, and model, one of the models it offers or auto for Auto (the default), which picks a model for each question.

<div class="g1t-endpoint"><span class="g1t-method" data-method="put">PUT</span><code>/workspaces/{workspace}/ai/ask</code></div>

Without provider_id, Ask is off. Returns what Ask answers with now. Owners only.

`model` is one of the models the provider offers, or `auto`. Send `provider_id` null to turn Ask off.

- **Authentication:** Required. Send an [access token](/reference/api/#authentication) as `Authorization: Bearer`.
- **MCP tool:** [`ai`](/reference/mcp/#ai) with `action` `set_ask`, and the same inputs
- **Scope:** An access token needs [`workspace:admin`](/guides/authentication/#scopes).

## Path parameters

| Name | Type | Required | Description |
| --- | --- | --- | --- |
| `workspace` | string | Yes | The workspace's slug, e.g. "flagon-io". |

## Body parameters

Send a JSON object. Names are `snake_case`, as in responses; the `camelCase` spelling is accepted too.

| Name | Type | Required | Description |
| --- | --- | --- | --- |
| `provider_id` | string or null | No | The AI provider Ask answers with: one of the workspace's, by id. Null or left out turns Ask off. |
| `model` | string | No | One of the models the provider offers, or auto for Auto: a model of the provider for each question. The provider's own model (an endpoint's, an Azure deployment) when left out. |

## Example request

```sh
curl -X PUT https://api.g1t.sh/workspaces/flagon-io/ai/ask \
  -H "Authorization: Bearer $G1T_TOKEN" \
  -H "Content-Type: application/json" \
  -d '{
    "provider_id": "ai_01kpx4n8r3g9s0v5w7x1z2a3be",
    "model": "claude-sonnet-4-5"
  }'
```

## Example response

A successful request answers `200` with:

```json
{
  "provider_id": "ai_01kpx4n8r3g9s0v5w7x1z2a3be",
  "provider_name": "Anthropic",
  "provider": "anthropic",
  "model": "claude-sonnet-4-5",
  "auto": false,
  "problem": null
}
```

## Errors

A failed request answers with one of these statuses and a body like `{"error": {"code": "not_found", "message": "Repository not found."}}`. See [errors](/reference/api/#errors).

| Status | Code | When |
| --- | --- | --- |
| 401 | `unauthenticated` | A token is required, or the one sent is not valid. |
| 403 | `forbidden` | The token is valid but not allowed to do this, such as a member-only change, or a token without the scope it needs. |
| 404 | `not_found` | It does not exist, or you cannot see it. |
| 409 | `conflict` | The request conflicts with the current state. |
| 422 | `invalid` | The input is not valid. `message` says which field and why. |