> For the complete documentation index, see [llms.txt](https://docs.lleverage.ai/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.lleverage.ai/get-started/readme.md).

# Introduction

## What Lleverage does

Lleverage automates repetitive back-office processes - order processing, invoice handling, quote generation, document workflows - with AI that works alongside your existing ERP and business systems.

There are two ways to get work done:

* **The Agent** - an AI coworker called Llev that you chat with. Give it tasks, upload files, and let it use your integrations, knowledge bases, and skills. New projects open on the agent by default.
* **Workflows** - repeatable processes you build on a visual canvas, either step by step or by describing what you want to the Copilot, which builds the workflow and connects apps as it goes.

{% @arcade/embed url="<https://app.arcade.software/share/2jNbdjXsZ1LBpQ7taSu9>" flowId="2jNbdjXsZ1LBpQ7taSu9" %}

### How it works

1. **Ask the agent or build a workflow** - chat with Llev for day-to-day tasks, or use the visual canvas and the Copilot for structured processes that run the same way every time
2. **Keep people in control** - route approvals and exceptions to the Request Inbox so someone can review before work continues
3. **Publish and share** - deploy workflows as apps, API endpoints, or scheduled tasks
4. **Monitor and refine** - follow runs in Activity, keep an eye on your project Dashboard, and improve based on real results

> 💡 Each project can open on the agent or use a workflow-focused sidebar instead. Choose the layout and the default landing page in Project Settings under **Navigation**.

### Key areas

* [**The Agent**](/operator-agent/operator-agent.md) - your AI coworker: chat sessions, skills, files, and memory
* [**Workflow Copilot**](/get-started/workflow-copilot.md) - describe a process in plain language and it builds the workflow for you
* [**Tables**](/platform/data-tables.md) - structured business data your agent and workflows can read and update
* [**Request Inbox**](/platform/request-inbox.md) - approvals and inputs that need a human, with assignment, notes, priorities, and SLAs
* [**Activity Monitoring**](/platform/activity-monitoring.md) - run history and detail for everything that happens in your project
* [**Knowledge Bases**](/platform/knowledge-bases.md) - searchable document collections that give the AI context about your business
* [**Publishing**](/publishing-guide/publishing-workflows.md) - share workflows as apps, API endpoints, or schedules
* [**Roles and Permissions**](/roles-and-permissions.md) - control who can build, run, and view
* [**Security & Performance**](/technical/security-and-performance.md) - how Lleverage protects your data

### Getting help

If you need assistance with a specific implementation or run into issues, reach out to your Lleverage contact or visit [Troubleshooting and Support](/support/troubleshooting-and-support.md).


---

# 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.lleverage.ai/get-started/readme.md?ask=<question>&goal=<endgoal>
```

`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.