> ## Documentation Index
> Fetch the complete documentation index at: https://api.thesapientcompany.com/llms.txt
> Use this file to discover all available pages before exploring further.

# Lenses

> The four brain-response lenses you can score a scan against.

Every scan is read through one or more **lenses**, each a `0–100` score (`50` is neutral) derived from the seven [brain networks](/knowledge-base/the-7-networks). You pick which lenses to score in the [`lenses`](/api-reference/create-scan#param-lenses) array, and each one is returned per second in the [timeline](/api-reference/get-scan). The same lens output shape applies on either [model](/api-reference/models).

## The four lenses

| Lens (API key)    | Measures                                                      | Knowledge Base                                            |
| ----------------- | ------------------------------------------------------------- | --------------------------------------------------------- |
| `attention`       | Whether the viewer is locked in, and where they slip away.    | [Attention](/knowledge-base/lenses/attention)             |
| `memory`          | How likely it is to stick.                                    | [Memory](/knowledge-base/lenses/memory)                   |
| `purchase_intent` | The approach-vs-avoid pull toward buying.                     | [Purchase intent](/knowledge-base/lenses/purchase-intent) |
| `manipulation`    | How much it leans on emotional persuasion vs plain reasoning. | [Manipulation](/knowledge-base/lenses/manipulation)       |

## Requesting a subset

Pass any subset in the `lenses` array. Order is preserved, duplicates are dropped, and unknown values are ignored. When omitted, the default is the top three: `attention`, `purchase_intent`, `manipulation`.

<RequestExample>
  ```bash cURL theme={null}
  curl https://www.thesapientcompany.com/api/v1/scans \
    -H "Authorization: Bearer sk_live_xxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxx" \
    -H "Content-Type: application/json" \
    -d '{
      "input": { "type": "video", "video_url": "https://yourcdn.com/ad.mp4" },
      "lenses": ["attention", "manipulation"]
    }'
  ```
</RequestExample>

<ResponseExample>
  ```json Queued theme={null}
  {
    "scan_id": "mary_run_mq7c8f31_jad6o8tl",
    "status": "queued",
    "lenses": ["attention", "manipulation"]
  }
  ```
</ResponseExample>

Each second of the completed [timeline](/api-reference/get-scan) then carries only those lenses:

```json theme={null}
{
  "second": 0,
  "scores": { "attention": 65, "manipulation": 48 }
}
```