> For the complete documentation index, see [llms.txt](https://help.intangible.ai/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://help.intangible.ai/get-started/take-control.md).

# Take control

Open Build, Compose or Visualize from a card on the canvas when you want to change something yourself, then go back to the canvas.

The agents get you most of the way fast. For the last part, an exact position, a framing, one shot's look, you open the mode and do it by hand. What the agents build in the scene is ordinary scene content, so you can change it by hand in Build or Compose.

## Open a mode from a card

Select a card on the canvas and use its toolbar:

| Card                                | Button                | Opens                                     |
| ----------------------------------- | --------------------- | ----------------------------------------- |
| Scene                               | **Edit in Build**     | The set, to move, add or swap objects     |
| Shot                                | **Edit in Compose**   | The camera, lens and timing for that shot |
| Image or video rendered from a shot | **Edit in Visualize** | That shot in Visualize                    |

You can also switch with the mode switcher at the top of the screen (Canvas, Build, Compose and Visualize), or press **0** for the canvas and **1**, **2** or **3** for Build, Compose and Visualize.

## Build: the set

Move or swap objects, attach reference images, adjust the environment. For exact placement, use the transform tools rather than a prompt. See [Build](https://help.intangible.ai/build/build.md).

## Compose: the cameras

Reframe a shot, change the lens, adjust the camera move or the shot's length. See [Compose](https://help.intangible.ai/compose/compose.md).

## Visualize: one shot your way

Pick a different model, style or lighting for one shot, adjust its prompt, and render it again. In the airbag rover example, shot 04 is opened in Visualize so the rover reference can be added before it renders. See [Visualize](https://help.intangible.ai/visualize/visualize.md).

## Back to the canvas

Press **0** or click the canvas icon at the top. Your changes are already on the cards. The chat panel is in the bottom-right corner on the canvas and in Build, with the same conversation in both, so ask for the next step from either.

Next: [Deliver](https://help.intangible.ai/get-started/deliver.md).

## Related

* [Move the camera](https://help.intangible.ai/get-started/take-control/viewport-navigation.md)
* [Place objects by hand](https://help.intangible.ai/get-started/take-control/place-your-first-objects.md)
* [The agents in each mode](https://help.intangible.ai/chat-agents-intangible/in-the-modes.md)


---

# Agent Instructions
This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com.

## Querying This Documentation
If you need additional information that is not directly available in this page, you can query the documentation by asking a question.

Perform an HTTP GET request on the following URL with the `ask` and `goal` query parameters:

```
GET https://help.intangible.ai/get-started/take-control.md?ask=<question>&goal=<user_goal>
```

`ask` is the immediate question: it should be specific, self-contained, and written in natural language.
`goal` is what the user is ultimately trying to achieve, the reason they need the answer. Sharing it helps GitBook give you a better, more relevant answer. A goal is most helpful when it describes the outcome the user wants rather than restating the question. For example, with `ask=how do I create an API token`, a goal like `automate deployments from our CI pipeline` lets GitBook tailor the answer to that use case.

The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.
