> For the complete documentation index, see [llms.txt](https://docs.empowergpt.ai/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.empowergpt.ai/chat/chat-types/world-knowledge.md).

# World Knowledge

The **World Knowledge** chat feature allows users to interact with empowerGPT using broad, internet-scale information. Unlike the Enterprise Knowledge chat—which responds only from your organization’s data—the World Knowledge component draws from globally available information that the underlying AI model has been trained on.

This component is trained on **internet-wide data**, offering general knowledge, explanations, definitions, and insights across a vast range of topics.

<figure><img src="/files/tvlW5Ba5idwP2u7wwJLD" alt=""><figcaption></figcaption></figure>

***

### **World Knowledge Chat — Tools**

The World Knowledge chat provides several tools to extend the model’s capabilities with internet-scale information and multimodal outputs. Below are the available tools and how to use them.

#### **Web Search**

Use Web Search when you need up-to-date facts, breaking news, or sources that the base model may not include.

* Runs a live query of external web sources and returns summarized findings and source citations.
* Best for checking recent events, validating dates/facts, or pulling in references from public websites.
* When Web Search is enabled, the chat will explicitly cite the sources used for each answer so you can verify and follow up.

#### **Search+**

Search+ is a high-capability reasoning tool that combines global knowledge with your enterprise data to produce deep, context-aware answers. It goes beyond simple retrieval by performing multi-step reasoning across all available sources:

* Breaks down complex queries into a plan of steps.
* Pulls from enterprise documents, chat history, integrations, and external web results.
* Synthesizes the most relevant information into a single, structured response with grounded references.
* Ideal for research, comparisons, summaries, and strategic decision-making where depth and accuracy matter.

#### **Canvas**

Canvas in World Knowledge chat is an interactive workspace for turning insights into structured content. Use it when you want to create, edit, or iterate on documents, visual layouts, or multi-part outputs that draw on both world and enterprise knowledge.\
Features:

* Draft summaries, reports, or multi-section documents using combined world + enterprise context.
* Edit and refine content directly inside the workspace with iterative AI assistance.

#### **Image Generation**

Generates images from text prompts to support presentations, documentation, or ideation. Useful for visualizing concepts uncovered during research or for creating illustrative assets.

* Accepts natural language prompts describing the desired image, style, composition, and size.
* All generated images follow platform safety and copyright policies; do not request images that violate content rules.

#### Compare Models

The Compare Models tool inside the World Knowledge tab allows users to compare two AI models side-by-side to evaluate their responses, performance, reasoning style, and output quality.


---

# 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, and the optional `goal` query parameter:

```
GET https://docs.empowergpt.ai/chat/chat-types/world-knowledge.md?ask=<question>&goal=<endgoal>
```

`ask` is the immediate question: it should be specific, self-contained, and written in natural language.
`goal` is optional and describes the broader end goal you are ultimately trying to accomplish on behalf of the user. GitBook uses it to tailor the answer towards what is most useful for that goal.

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.