# Operator Agent

The Operator Agent is an AI-powered assistant that lives inside your Lleverage project. Rather than building a workflow step by step, you talk to the agent in natural language — describe what you need, and it figures out how to get it done using the tools and data available in your project.

### What the Agent Does

The Operator Agent can:

* **Process files** — Upload CSVs, PDFs, images, spreadsheets, and other documents. The agent reads, analyses, and transforms them in a secure cloud sandbox.
* **Use your integrations** — Connected apps (Gmail, Slack, Business Central, etc.) become tools the agent can use on your behalf.
* **Query knowledge bases** — The agent searches your uploaded documents and knowledge bases to find relevant information.
* **Run skills** — Reusable task packages that combine instructions, integrations, and knowledge into repeatable capabilities.
* **Generate output files** — The agent can create documents, spreadsheets, reports, and other files as part of its work.
* **Break down complex tasks** — For larger requests, the agent plans its approach, tracks progress with a visible todo list, and narrates what it's doing in real time.

### Agent vs. Workflows

Workflows and the agent serve different purposes:

|                   | Workflows                                                         | Operator Agent                               |
| ----------------- | ----------------------------------------------------------------- | -------------------------------------------- |
| **Best for**      | Repeatable, structured processes that run the same way every time | Ad-hoc tasks, exploration, complex reasoning |
| **How you build** | Visual canvas with connected action cards                         | Natural language conversation                |
| **Execution**     | Deterministic — follows the path you designed                     | Autonomous — decides its own approach        |
| **Triggers**      | Schedules, API calls, form submissions, integrations              | You ask it something in chat                 |
| **Monitoring**    | Activity log, run history, alerts                                 | Session history, narration, skill cards      |

Many teams use both: workflows for high-volume automated processes, and the agent for tasks that need judgement, flexibility, or one-off analysis.

### Getting Started

The agent is available in any project on a paid plan. Open your project and navigate to the agent chat to start a conversation.

{% content-ref url="/pages/QBgYQ0dlrJa7h7B4EJN3" %}
[Getting Started](/operator-agent/getting-started.md)
{% endcontent-ref %}


---

# 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.lleverage.ai/operator-agent/operator-agent.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.