> 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/connections.md).

# Connections

Authorise external accounts inside a project, or let the Agent initiate supported and custom connection setup for the systems it needs.

A **Connection** gives Lleverage authorised access to an external account or application used in operational work. Connections provide system authority; Skills describe how to use that authority.

### Choose who owns the connection

Before a connection can be created, the current setup requires an explicit access choice.

![The current shared-versus-personal Connection access choice.](https://3370306531-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2FlgSglJDQZxDZdn20CUcl%2Fuploads%2FrfK8evm0OPU7HMBxo1XS%2Fconnection-access.png?alt=media)

* **Shared connection** — available to everyone in the Project; choose where it can be used.
* **Personal connection** — private to you and **not available on Workflow nodes**.

For shared connections, scope the connection to the Agent, Workflows or both as appropriate. This is an authority boundary, not just a convenience setting.

### Connect the account

For supported providers, the connection dialog offers two common paths:

* **Connect Now** — connect an account you can authorise directly.
* **Send Authentication Link** — send a secure link so someone else can authorise the account.

The Agent can also initiate supported OAuth setup from a session. The human completes provider authorisation; the Agent does not need the account password.

### Restrict actions and approvals

A connection can restrict which actions are enabled and can require approval for selected actions. Use the narrowest actions needed for the operational job.

Connection-level action policy is separate from Skill component approval and from Workflow Request nodes.

### Custom integrations

When no native provider exists, use a [Custom integration](/build-and-improve/overview/custom-integrations.md). The builder can either configure it directly or ask the Agent to guide setup. Credentials are entered through the secure handoff rather than pasted into chat, Skills, files or Workflow payloads.

### Different surfaces with similar names

* **Connections** — system accounts and capabilities used by Agent/Workflow actions.
* **Channels** — Slack/Teams places where people talk to the Agent.
* **AI Models / Databases** — provider credentials managed on their own Control pages.

When troubleshooting access, first confirm the connection owner/scope, enabled actions and the Project the Agent or Workflow is running in.


---

# 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/administer-and-govern/control/connections.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.