# Introduction to Agents

{% embed url="<https://www.loom.com/share/20d59478385b4d09986d0ff472f14068?sid=20e1c6b3-2f7f-490d-b6c6-117855be354b>" %}

Agents in Rox are powerful tool-equipped LLMs with the ability to leverage public and private data, purpose-built to track and analyze individual accounts. Each agent is scoped to a specific company and your own domain, enabling them to generate highly personalized and context-aware outputs.

### Add Agents via Search

1. Click on the "+ Add Agent" button in the top right-hand corner of the page
2. Begin typing for the account in the search bar
3. Select an account from one of the results
4. The agent will be deployed to your list, marked with a status of "initializing"
5. Once the agent is ready, it will have a status of "available"
6. Now the agent will track your account 24/7

### Add Agents via Domain

1. Click on the "+ Add Agent" button in the top right-hand corner of the page
2. Begin typing for the account in the search bar
3. If the right result is not there, click on the option to manually add an agent
4. In the new view, type the company's website
5. The agent will be deployed to your list, marked with a status of "initializing"
6. Once the agent is ready, it will have a status of "available"
7. Now the agent will track your account 24/7

### Remove Agents

1. Hover over the agent you want to remove
2. A checkbox should appear next to the name
3. Check the agent(s) you want to remove
4. Click on the "Bulk Actions" button in the top right-hand corner
5. Select "Remove Agents"
6. The selected agents should be removed immediately


---

# Agent Instructions: 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://docs.rox.com/development/product/getting-started/introduction-to-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.
