> 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/understand-lleverage/readme/start-here-by-responsibility.md).

# Documentation by role

Find the part of the documentation that matches what you are trying to do in Lleverage.

Lleverage can be used by people doing operational work, people configuring how that work is executed, and people administering the Project or organisation.

These are documentation paths, not fixed job titles or permission bundles. One person may use more than one path.

If you are new to the product model, start with [Lleverage overview](/understand-lleverage/readme.md). If you already know the operational process you are dealing with, jump directly to the path below.

## Operators

Start with [Run operations](/run-operations/overview.md).

Use this path if you mainly:

* work with the [Agent](/run-operations/agent.md);
* use published Workflow apps;
* respond to Requests assigned to you;
* need to understand the operational area through the Project overview.

If you are unsure which surface matches the task in front of you, use [Project navigation](/run-operations/overview/navigation.md).

## Builders

Start with [Set up a Project](/build-and-improve/overview.md).

Use this path when you need to change:

* repeatable execution in [Automate](/build-and-improve/automate.md);
* Skills, Memory, Tables, Files or Knowledge under [Intelligence](/build-and-improve/intelligence.md);
* testing, publishing and [human handoffs](/build-and-improve/automate/human-handoffs.md);
* execution evidence and recurring issues in [Monitoring](/build-and-improve/monitoring.md).

The builder path assumes you need to understand how the execution is configured, not just how to use it.

## Administrators

Start with [Control](/administer-and-govern/control.md).

Use it for [Connections](/administer-and-govern/control/connections.md), [Channels](/administer-and-govern/control/channels.md), Schedules, [Members](/administer-and-govern/control/members.md), Settings, API Tokens, AI Models, Databases, Secrets, Variables and Metrics.

For broader questions about operational ownership, rollout or assurance, continue to [Governance](/administer-and-govern/governance.md), [Rollout and operations](/administer-and-govern/rollout-and-operations.md) or [Security and assurance](/administer-and-govern/security-and-assurance.md).

## Product model

Start with [Lleverage overview](/understand-lleverage/readme.md).

Useful next pages are:

* [Operational examples](/understand-lleverage/operational-examples.md) for representative processes and language;
* [People, Agents and Workflows](/understand-lleverage/readme/humans-agent-and-workflows.md) for the execution model;
* [Automation levels](/understand-lleverage/readme/from-manual-to-autonomous.md) for the supporting autonomy ladder;
* [Projects and solutions](/understand-lleverage/readme/projects-and-solutions.md) for the Project boundary and Solution language.

The throughline is consistent across all paths: start from the operational work that needs to get done, then configure the right mix of foreground work, background execution and human attention.


---

# 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/understand-lleverage/readme/start-here-by-responsibility.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.