> For the complete documentation index, see [llms.txt](https://alludium.gitbook.io/alludium-docs/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://alludium.gitbook.io/alludium-docs/administration/2.-agents/2.4-my-agents.md).

# My Agents

My Agents is where you run deployed agents and review their outputs.

**Location:** Administration -> My Agents, where available

Most Members do not see My Agents in the default sidebar. Members usually use agent-assisted workflows through Inbox, Projects, Files, or configured workspace assistants.

Each agent listed here has its own conversation history, tool access, and document context. This is your operational workspace—separate from Agent Builder, which is purely for configuration.

#### How to use My Agents

**Agent detail view**\
When you click an agent in My Agents, the detail view shows a tabbed interface: **Chat**, **Guidelines** (for agents requiring configuration), **Files**, and **Info**. The Chat tab is the default view for ready agents. The Guidelines tab appears for user-created agents that need guideline configuration. Platform agents (like Alludium Navigator) do not show the Guidelines tab.

**Access an agent**\
Click any agent from your list to open its dedicated chat interface.

**Invoke an agent**\
Provide context directly in a new chat—type instructions, upload documents, or reference specific requirements. The agent executes according to its configuration and returns an output.

**Review outputs**\
Every output appears in the chat history alongside the context you provided. Review for quality, accuracy, and alignment with your standards before external use.

**Iterate when needed**\
If output quality isn't sufficient, provide clarification or additional files within the same session. The platform expects iteration; use it rather than manually fixing poor drafts.

**Upload documents during invocation**\
When an agent accepts files, use the paperclip attachment button in the chat input area. Depending on the agent configuration, you can upload a new file or link an existing file. Use this for background materials or reference documents relevant to the specific task. Documents uploaded here are scoped to this agent conversation.

#### Chat history and continuity

Each agent maintains its own conversation record. Previous invocations, files provided, and outputs produced remain accessible in the agent's **Chat Sessions**. This helps you:

* Reference past context and inputs
* Compare outputs across multiple runs
* Understand usage patterns over time

Chat history doesn't transfer to Agent Builder. Configuration and execution environments are deliberately separated.

### Owned vs. Shared Agents

My Agents displays both agents you've created and agents shared with you by other workspace members.

**Ownership and sharing indicators:**\
Ownership information is visible in the agent's **Info tab** (which shows "OWNER" and "SHARING" fields). A shared platform agent shows "Shared with you" under the SHARING field in its Info tab. You can also view and manage agent access via the **Manage Agent Access** dialog, accessible from the cog/gear icon in the My Agents sidebar header.

**Setup status:**\
Agents that require configuration are indicated by an **orange dot** next to the agent name in the sidebar (ready agents show a green dot). When you open an agent that needs setup, you are redirected to its Guidelines tab to complete configuration.

**Key differences:**

* **Owned agents:** Full control over configuration, behavior, and sharing
* **Shared agents:** Use only — configure connections and automations, but cannot modify agent behavior

See **Agent Sharing (in Workspace)** for complete details on accessing and configuring shared agents.


---

# 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://alludium.gitbook.io/alludium-docs/administration/2.-agents/2.4-my-agents.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.