---
title: "act: deepen"
description: "an observation, and the depth: fetched in full, or given meaning to a deepening"
section: reference
address: /reference/act/deepen
contract: 0476e35e6e275db5
---

# act: deepen

an observation, and the depth: fetched in full, or given meaning to a deepening

[figure: The caller sends DeepenInput to /v1/act/deepen. The platform returns a card whose body is Deepening.]

<span class="op-method">POST</span><span class="op-path">/v1/act/deepen</span><span class="op-note">a task, 202</span>

Ask for depth. The call needs the strategy rung under a token with the act grant, and it is served by the platform.

The route takes [DeepenInput](/concepts/deepeninput) and returns a card whose body is [Deepening](/concepts/deepening).



## Request body
The request body is [DeepenInput](/concepts/deepeninput).



| field | type | required | note |
|---|---|---|---|
| `observation` | `id` | yes |  |
| `depth` | `one of fetch \| embed \| both` | yes |  |
| `asked_by` | [UnitRef](/concepts/unitref) | yes |  |



## Response
The route returns a card whose body is [Deepening](/concepts/deepening). Every card ends with a foot that states the basis of each number, the scope of the call, and the time when the facts were true. This route runs as a long step and returns a task with status 202. `POST /v1/work/status` returns the task's progress, and `POST /v1/work/cancel` stops the task.

## Headers


| header | required | meaning |
|---|---|---|
| `Scale-Scope` | yes | the scope the call runs in: tenant/<id>, then /brand/<id>, then /strategy/<id> |
| `Scale-As-True-On` | no | the date the facts must have been true on; defaults to now |
| `Scale-As-Known-On` | no | the date the facts must have been known on; defaults to now |
| `Scale-Key` | no | for a change, the key made from the input; a repeat under the same key returns the unit held and writes nothing |



A caller needs the strategy rung and a token with the act grant. The platform serves this route.

## Example
The example sends the smallest body that DeepenInput allows. The build validates it against the schema of DeepenInput.

<details class="wire"><summary>Example</summary>





```sh
curl -X POST https://api.scaleintelligence.co/v1/act/deepen \
  -H "Scale-Key: $SCALE_KEY" -H "Scale-Scope: tenant/<id>" \
  -H "content-type: application/json" \
  -d '{ "observation": "…", "depth": "fetch", "asked_by": { "id": "…", "kind": "…" } }'
```




```typescript
import { client } from "@scale/sdk";
const answer = await client.act.deepen({
    "observation": "…",
    "depth": "fetch",
    "asked_by": {
      "id": "…",
      "kind": "…"
    }
  });
// answer.body is a Deepening. answer.foot holds the basis, the scope and the time.
```




```python
import requests
answer = requests.post("https://api.scaleintelligence.co/v1/act/deepen",
    headers={"Scale-Key": KEY, "Scale-Scope": "tenant/<id>"},
    json={
      "observation": "…",
      "depth": "fetch",
      "asked_by": {
        "id": "…",
        "kind": "…"
      }
    }).json()
```




```rust
let answer: Card = client.post("https://api.scaleintelligence.co/v1/act/deepen")
    .header("Scale-Key", key).header("Scale-Scope", "tenant/<id>")
    .json(&DeepenInput { /* the fields of the page */ }).send().await?.json().await?;
```




</details>

## MCP tool
The MCP tool `si.act.deepen` takes the same input and returns the same card. The tool changes data and needs a grant. An MCP host that renders cards draws this card from `ui://scale-intelligence/cards/Deepening`. The [tool's page](/reference/tools/si-act-deepen) describes it.
