> For the complete documentation index, see [llms.txt](https://docs.workfx.ai/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.workfx.ai/workfx-companion-agent-knowledge/workforce-factory/multi-agent/creation.md).
# Creation
## Start Creating
Navigate to the **Multi-Agent** tab and click **"Create From Blank"**. Enter a name and description, then click **"Create"** to complete the basic setup.
## Add Agents to Supervisor Group
Click on the **Supervisor Node** or its **group**, then select the Agents you need from the list.
> These **Agents** will be autonomously invoked by the Supervisor and will complete tasks according to the Supervisor's prompt.
> These **Agents** are system-controlled and do not support manual configuration.
## Add Agent Nodes
If you prefer to use an **Agent** in a more controlled manner, you can locate the agent node in the node list and import it. It will then function as a standalone node, **independent of the Supervisor**, and you will need to manually configure its input parameters.
## Other Configuration
Apart from the aforementioned methods of referencing agents, other configurations in **Multi-Agent** are the same as those in **AgentFlow**. Please refer to the relevant sections of AgentFlow for details.
---
# 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.workfx.ai/workfx-companion-agent-knowledge/workforce-factory/multi-agent/creation.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.