> For clean Markdown of any page, append .md to the page URL.
> For a complete documentation index, see https://docs.resemble.ai/llms.txt.
> For AI client integration (Claude Code, Cursor, etc.), connect to the MCP server at https://docs.resemble.ai/_mcp/server.

# Detect Intelligence

Ask natural-language questions about completed deepfake detection reports using the detection's full context.

> **Note**
>
> This is different from the standalone [Intelligence](/detect/intelligence) feature, which analyzes raw media for speaker details, transcription, and emotion. Detect Intelligence asks questions about **already-completed detection reports**.

## Request & Response Schemas

```ts
interface AskDetectQuestionRequest {
  query: string; // natural-language question about the detection
}

interface DetectQuestionItem {
  uuid: string;
  detect_uuid: string;
  query: string;
  answer: string | null;       // null until status is "completed"
  status: "pending" | "processing" | "completed" | "failed";
  error_message: string | null;
  created_at: string;          // ISO 8601
  updated_at: string;          // ISO 8601
}
```

## Async Workflow

1. Ensure the detection status is `completed`.
2. Submit a question via the [Ask a Question](/detect/detect-intelligence/create) endpoint.
3. The API returns `202 Accepted` with the question UUID and `status: "pending"`.
4. Poll the [Get Answer](/detect/detect-intelligence/get) endpoint until `status` is `"completed"` or `"failed"`.
5. Read the `answer` field from the completed response.

## Example Questions

| Category   | Example Query                                          |
| ---------- | ------------------------------------------------------ |
| Summary    | "Summarize the detection results in plain language."   |
| Confidence | "How confident is the model that this audio is fake?"  |
| Comparison | "How do the audio and video detection results differ?" |

## Polling Best Practices

* Use exponential backoff starting at 1 second, doubling up to a maximum of 10 seconds.
* Most answers complete within 5–15 seconds.
* Check the `status` field — stop polling once it reaches `completed` or `failed`.

## Related Endpoints

* [Ask a Question](/detect/detect-intelligence/create) — Submit a question about a detection
* [Get Answer](/detect/detect-intelligence/get) — Poll for the answer
* [Deepfake Detection](/detect) — Submit and manage detection jobs
* [Intelligence](/detect/intelligence) — Standalone media intelligence analysis