> 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/chat-agents-intangible/work-well-with-intangible-agents.md).

# Work well with Intangible agents

Guides to getting more out of Intangible agents: writing a brief they can build, controlling AI output, and how renders read your scene.

Intangible does what you ask, so the way you ask decides what you get. Write requests in camera and lighting language, know what the scene pins down and what the model still decides, and fix a problem where it starts.

| Guide                                                                                                       | What it covers                                                          |
| ----------------------------------------------------------------------------------------------------------- | ----------------------------------------------------------------------- |
| [Brief AI like a DP](https://help.intangible.ai/learn-more/how-to/brief-ai-like-a-dp.md)                    | Writing requests in the language of lenses, light and framing           |
| [Controlling AI output](https://help.intangible.ai/learn-more/concepts/control-ai-output.md)                | What you can pin down with a 3D scene, and what the model still decides |
| [How the visualizer thinks](https://help.intangible.ai/learn-more/concepts/how-the-visualizer-thinks.md)    | How a render reads your scene, so you know what to fix where            |
| [Troubleshooting Intangible agents](https://help.intangible.ai/learn-more/faq/troubleshooting-the-agent.md) | What to do when a run stalls, fails or drifts                           |

## Three habits

* **Name what you mean.** Call a card by the name the canvas gives it ("shot 02's keyframe") and attach images with **+**. See [Chat with Intangible](https://help.intangible.ai/chat-agents-intangible/chat-with-intangible.md).
* **Confirm the brief, then let them run.** The brief is the one decision most runs need. Get it right before the build. You can still edit it later, but nothing rebuilds until you ask in the chat panel. See [The brief](https://help.intangible.ai/canvas/the-brief.md).
* **Take over for precision.** The agents get you most of the way fast. For a particular framing or a change to a single frame, open the mode or the editor and do it by hand.


---

# 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/chat-agents-intangible/work-well-with-intangible-agents.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.
