> 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/run-operations/agent.md).

# Agent

Use the Agent for flexible operational work across conversations, files and business systems.

The Agent is the place to work with Lleverage when the job needs interpretation rather than one fixed sequence.

Give it an outcome and the evidence it should use. The Agent can investigate, work with files and connected systems, use reusable Skills, create outputs and bring you in when judgement or approval is needed.

Typical Agent work includes:

* investigating why an order, invoice or production job is blocked;
* turning emails, PDFs or spreadsheets into useful operational output;
* checking facts across business systems and Project context;
* preparing documents, recommendations or follow-up;
* handling work where the next step depends on what the Agent discovers.

For repeatable work that should run the same way every time or in the background, use a Workflow. Most operational processes use both. See [Humans, Agent and Workflows](/understand-lleverage/readme/humans-agent-and-workflows.md).

## Where to start

New to the Agent? Start with [Getting started with the Agent](/run-operations/agent/getting-started.md).

If you want to see the kinds of jobs it can handle, browse [Examples of Agent work](/run-operations/agent/examples.md).

During a task, [Session workspace](/run-operations/agent/session-workspace.md) explains the controls and evidence around the conversation. [Working well with the Agent](/run-operations/agent/tips-and-best-practices.md) covers the habits that produce dependable results.

When you want to understand where the Agent gets its information or abilities, go to [What the Agent can use](/run-operations/agent/agent-context.md).

For common questions about learning, access, control and automation, use the [Agent FAQ](/run-operations/agent/agent-faq.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 by asking a question.

Perform an HTTP GET request on the following URL with the `ask` and `goal` query parameters:

```
GET https://docs.lleverage.ai/run-operations/agent.md?ask=<question>&goal=<user_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.