> 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/administer-and-govern/control.md).

# Control

Configure the access, systems, credentials and runtime settings that determine what a Lleverage Project is allowed to do.

Use Control when the operational process is clear but Lleverage still needs the right authority and environment around it: access to an ERP or mailbox, people in the right Project, an Agent routed into Teams, a schedule, credentials, or a runtime setting.

Control explains **how Lleverage is configured to operate**. Broader questions about who owns the process, where people remain accountable and how changes reach production live under [Governance](/administer-and-govern/governance.md), [Rollout and operations](/administer-and-govern/rollout-and-operations.md) and [Security and assurance](/administer-and-govern/security-and-assurance.md).

Project Operators do not see Control. Visibility can also vary by role and project configuration.

## Connect the systems the work needs

Use [Connections](/administer-and-govern/control/connections.md) to authorise external accounts and integration actions used by Agents and Workflows.

If people should talk to the Agent through Slack or Microsoft Teams, use [Channels](/administer-and-govern/control/channels.md) instead. Connections provide system capability; Channels route conversations.

## Decide who can access the Project

Use [Members](/administer-and-govern/control/members.md) and [Roles and Permissions](/administer-and-govern/control/members/roles-and-permissions.md) to manage Project membership and current roles.

For organisation-level authentication, see [Enterprise SSO Setup](/administer-and-govern/control/members/sso-setup.md).

## Configure when and how Agent work starts

Use [Schedules](/administer-and-govern/control/schedules.md) for recurring Agent runs.

Use [Settings](/administer-and-govern/control/settings.md) for Project identity, Agent behaviour and navigation configuration.

Workflow schedules are configured through the Workflow publishing path; see [Scheduling workflows](/build-and-improve/automate/test-and-publish/scheduling-workflows.md).

## Provide runtime credentials and configuration

Use:

* [API Tokens](/administer-and-govern/control/api-tokens.md) for Project-scoped API access;
* [AI Models](/administer-and-govern/control/ai-models.md) for model-provider credentials;
* [Databases](/administer-and-govern/control/databases.md) for database-provider connections;
* [Secrets](/administer-and-govern/control/secrets.md) for sensitive values;
* [Variables](/administer-and-govern/control/variables.md) for reusable non-secret configuration.

Do not copy credentials into ordinary Files, Skills, prompts or documentation. Variables are not secret storage. See [Secrets and variables reference](/administer-and-govern/control/secrets/reference.md).

## Measure execution

Use [Metrics](/administer-and-govern/control/metrics.md) to define measurements that Workflows can emit and [Monitoring](/build-and-improve/monitoring.md) can chart or inspect.

## Scope matters

Control is presented inside a Project, but not every configuration object is purely Project-scoped. Read the scope notes on each page before assuming a change affects only the Project you are currently viewing.

## Related documentation

* External systems → [Connections](/administer-and-govern/control/connections.md)
* Slack / Teams Agent routing → [Channels](/administer-and-govern/control/channels.md)
* Membership and roles → [Members](/administer-and-govern/control/members.md)
* Project / Agent configuration → [Settings](/administer-and-govern/control/settings.md)
* Operational ownership and human boundaries → [Governance](/administer-and-govern/governance.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/administer-and-govern/control.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.