> 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/channels.md).

# Channels

Route Slack and Microsoft Teams conversations into Lleverage projects and keep organisation installation separate from project-specific Agent context.

Channels connect conversation surfaces such as Slack and Microsoft Teams to the [Lleverage Agent](/run-operations/agent.md).

They are **not the same thing as** [**Connections**](/administer-and-govern/control/connections.md). Connections authorise external-system tools. Channels decide how a conversation reaches the Agent and which Lleverage context the conversation runs in.

## Organisation installation and project routing are different

There are two administrative layers:

* **organisation/workspace installation** connects the Slack workspace or Microsoft Teams tenant to the Lleverage organisation;
* **conversation/project routing** determines which Project context a conversation uses.

If the app is installed but a tool behaves differently from the web Agent, check routing before reconnecting the external provider.

## Pin conversations that depend on project-specific capability

An unpinned conversation can be dispatched through organisation-level channel resolution rather than the same Project context as a web Agent session. That matters when a Connection, Skill or other capability exists only in a particular Project.

Pin the conversation to that Project when the operational work depends on Project-specific authority or context. This gives the channel run a clear working boundary instead of relying on cross-Project capability resolution.

For how Project boundaries affect available capability more generally, see [Projects and solutions](/understand-lleverage/readme/projects-and-solutions.md).

## Identity and access still apply

Installing the Slack or Teams app does not grant Lleverage access by itself. The person using the Agent still needs to resolve to a Lleverage identity and to the Project access required for the work.

Use [Members](/administer-and-govern/control/members.md) and [Roles and Permissions](/administer-and-govern/control/members/roles-and-permissions.md) for the Lleverage-side access model.

## Supported conversation surfaces

The current channel service handles direct conversations and supported multi-person/channel contexts across Slack and Microsoft Teams. The exact interaction and attachment behaviour depends on the provider.

For operator guidance, see [Agent in Slack](/run-operations/agent/agent-in-slack.md) and [Agent in Microsoft Teams](/run-operations/agent/agent-in-microsoft-teams.md).

## Set up a channel

* [Set up Slack](/administer-and-govern/control/channels/set-up-slack.md)
* [Set up Microsoft Teams](/administer-and-govern/control/channels/set-up-microsoft-teams.md)

If what you need is a Workflow trigger or external-system action rather than conversational Agent access, go back to [Connections](/administer-and-govern/control/connections.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/administer-and-govern/control/channels.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.