> 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/enterprise-knowledge.md).
# Enterprise Knowledge
The **Enterprise Knowledge** chat feature allows users to interact exclusively with their organization’s data within EmpowerGPT. Instead of relying on general AI knowledge, this chat responds strictly using the enterprise content that is uploaded, stored, or linked within the platform.
EmpowerGPT is designed so that **no model retraining** is required when new information is added. The system automatically incorporates updated documents, databases, and knowledge sources into responses.
All answers generated through Enterprise Knowledge chat include **grounded references**, ensuring transparency, traceability, and confidence in every output.
***
### **Key Capabilities**
#### **Enterprise-Only Responses**
All queries sent through this chat are answered **solely from enterprise data**.\
If the system cannot find relevant information within the connected datasets, it will not generate assumptions or unsupported answers.
#### **Automatic Knowledge Integration**
When new data is uploaded or linked, EmpowerGPT immediately makes it available to the Enterprise Knowledge system—no fine-tuning, retraining, or configuration required.
#### **Grounded References in Every Answer**
Each response includes **citations or reference links** back to the original enterprise source.\
This ensures:
* Full traceability
* Auditable reasoning
* Confidence in accuracy
* Compliance with organizational requirements
***
### Chat Interface Features
#### Canvas
The **Canvas** tool provides an interactive workspace within the Enterprise Knowledge chat. It allows users to create, refine, and organize content while leveraging enterprise data. Canvas is designed for tasks that require iterative development.
With Canvas, users can:
* Generate drafts, summaries, analyses, and structured documents
* Edit content directly in the workspace
* Collaborate with EmpowerGPT in a persistent, document-style environment
#### Upload Files or Select files from Workspace
The **Upload Files** feature allows users to add new documents directly into the Enterprise Knowledge system. By uploading a file, you enable empowerGPT to reference that content when generating answers. This ensures responses remain focused, accurate, and grounded in your organization’s latest information.
The **Select Files from Workspace** option lets users choose from existing documents already stored in their workspace. Selecting a file signals to empowerGPT that the chosen document should be used as a primary source for generating a focused and context-aware response.\
This feature is especially useful when you want the system to rely on specific documents rather than the entire enterprise dataset.
---
# 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/enterprise-knowledge.md?ask=&goal=
```
`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.