> For the complete documentation index, see [llms.txt](https://ludicore-ai.gitbook.io/ludicore-ai/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://ludicore-ai.gitbook.io/ludicore-ai/context.md).

# Context

LudiCore enables you to specify the context for the AI to focus on, making it easier to provide detailed and relevant information for your queries. To access the context menu, click **+Context** in the chat input field.

#### How to Add Context:

1. Open the **+Context** menu in the chat input field.
2. Select any item in your Unity project and click **"Click here to add selected items"** in the open **+Context** menu.
3. Alternatively, drag and drop items directly into the **+Context** menu for convenience.

#### Important Notes:

* To provide console logs to the AI, you must select them manually from the logs. Drag-and-drop functionality for logs is not currently supported.
* The context window displays all selected items clearly when open, giving you a visual overview of the information being provided.

By leveraging the context feature, you can help LudiCore better understand your project and deliver more accurate, tailored responses.

***

<figure><img src="/files/aRkxOro0aHGcWmXQEEKz" alt=""><figcaption></figcaption></figure>

***

This is what the context window looks like after you have selected a few items.

<figure><img src="/files/nueKLh7w8Ugiag55hx3b" alt=""><figcaption></figcaption></figure>

***

The context you select is provided to the AI with enhanced detail, dynamically processed based on the specific command type you use. This makes it essential to carefully choose the appropriate slash command to ensure your request is fulfilled effectively.\
\
Behind the scenes, LudiCore generates a graph representing the most important elements of your scene, assets, and code. When you send a request, this graph is ranked using a specialized algorithm, prioritizing relevant data within a certain token limit.

***

This system is a temporary solution and will be enhanced in the next patch to enable a deeper and more comprehensive understanding of your entire project.


---

# 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 dynamically by asking a question.

Perform an HTTP GET request on the current page URL with the `ask` query parameter:

```
GET https://ludicore-ai.gitbook.io/ludicore-ai/context.md?ask=<question>
```

The question should be specific, self-contained, and written in natural language.
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.