> For the complete documentation index, see [llms.txt](https://docs.tnid.com/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.tnid.com/api-reference/001_user/016_assistant/001__ask_docs_question_as_user.md).

# Ask A Question About Using Tnid

GraphQL endpoint: `/user`

Answers a natural-language question from the published documentation and names the pages the answer drew on. Supplying `navigation` also lets the answer point at where to go: it is answered against exactly the entries supplied, so it never names somewhere the caller wasn't offered.

The answer shown here comes from a stubbed model, so the wording is illustrative rather than something the service guarantees.

## Query

```graphql
mutation ($question: String!, $navigation: [NavigationEntryInput!]) {
  askDocsQuestion(question: $question, navigation: $navigation) {
    answer
    citations {
      path
      title
    }
    destination {
      label
      path
    }
  }
}

```

## Variables

```json
{
  "navigation": [
    {
      "label": "Documents Repository",
      "path": "/docs",
      "section": "Docs"
    },
    {
      "label": "Client Secrets",
      "path": "/client-secrets",
      "section": "Home"
    }
  ],
  "question": "how do I run a user ai task again"
}
```

## Response

```json
{
  "data": {
    "askDocsQuestion": {
      "answer": "Call runUserAiTask with the task id. Omit ids to run it over everything the task watches.",
      "citations": [
        {
          "path": "user/documents/run-user-ai-task",
          "title": "Run a user AI task again"
        }
      ],
      "destination": null
    }
  }
}
```
