> For the complete documentation index, see [llms.txt](https://docs.duplocloud.com/docs/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.duplocloud.com/docs/armor/workspaces.md).
# Workspaces
This is where it all comes together!
A Workspace is the central entity that ties everything together — attach any number of Scopes and Personas to it. You can create multiple Workspaces and invite users to each one, enabling clear separation of responsibilities across your organization.
## Creating a Workspace
1. Navigate to **Workspaces** and click **Add Workspace**.
2. Give the Workspace a **Name** and **Description**.
3. Select the **Persona(s)** to include in the Workspace, and click **Next**.
3. Select the **Agent(s)** that do the work in this Workspace, and click **Next**.
4. For each **Provider** screen, select the **Scopes** to include in the Workspace, then click **Next** until you have reviewed them all.
5. Click **Create**.
**Congratulations!** Your Workspace is now ready to receive assignments, interpret goals, break down work, and provide a transparent audit trail—all with human oversight and control.
## Setting a System Prompt
Each Workspace can define a **System Prompt** — free-text instructions injected directly into the agent's system prompt on every ticket in that Workspace.
Open a workspace and go to the **Prompt** step (the same step where Prompt Suggestions and Prompt Templates are configured). Enter your instructions in the **System Prompt** field and save.
{% hint style="info" %}
This is distinct from [Agent Memories](/docs/armor/agents/agent-memories.md). The System Prompt is a single field that's always injected verbatim into every ticket in the workspace. Memory is a set of files the agent reads on demand, and can be turned off per ticket. If the two conflict, persona instructions take precedence over the System Prompt.
{% endhint %}
---
# 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://docs.duplocloud.com/docs/armor/workspaces.md?ask=&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.
