> 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/set-up-microsoft-teams.md).

# Set up Microsoft Teams

Install the Lleverage Agent in Microsoft Teams using the current custom app package, then route conversations into the right Lleverage project.

## Set up Microsoft Teams

Microsoft Teams currently uses a **custom-app installation**. The Lleverage Agent is not installed from the Teams marketplace. A Teams administrator uploads the Lleverage app package to the tenant, then the installation is linked to the Lleverage organisation.

## Before you start

You need a Lleverage organisation Owner who can start the Teams setup, plus a Microsoft Teams administrator who can upload and approve a custom app for the tenant.

Customer organisations can start the current connection flow directly in Lleverage; a Lleverage employee does not need to unlock the setup first.

## Install the Teams app

1. In Lleverage, open **Control → Channels → Microsoft Teams**.
2. Start the Teams setup and obtain the current app package and connection code.
3. In the **Teams admin center**, open **Teams apps → Manage apps** and upload the Lleverage app package.
4. Approve or make the app available according to the tenant's Teams app policy.
5. In Teams, open a conversation with **Llev** and complete the connection step using the code supplied by Lleverage.
6. Return to **Control → Channels** and confirm the Teams installation is connected.

The Teams app installation is organisation-level. It is separate from Microsoft Connections used by Workflows or Agent tools.

## Route the conversation to the right project

A Teams conversation can be routed without a fixed project or pinned to a particular project.

Unpinned organisation-scoped Agent runs can now resolve eligible project-held Connections from the projects the user is authorised to access. Pin a conversation when the work should be constrained to one project's Skills, context and Connections, or when several projects could otherwise supply relevant capabilities.

If a tool behaves differently in the web Agent and Teams, compare the resolved project context and Connection before changing the provider setup.

## User access

Installing the Teams app does not automatically give every Microsoft tenant user Lleverage access. Lleverage still needs to identify the person and resolve the projects they are authorised to use.

## File attachments

There are two relevant Teams file paths:

* **Conversational Agent:** direct compose-box uploads and inline images in a one-to-one Teams conversation can reach the Agent. SharePoint/OneDrive reference-style attachments remain a different conversational path.
* **Workflow channel trigger:** the Microsoft Teams `new-channel-message` trigger can ingest inline/hosted images and supported channel-folder reference files into the Workflow as files. Existing Connections may need the additional Microsoft file-read permission when this path is first used.

Do not assume every Teams file shape uses the same retrieval path. Use Monitoring/support evidence if a particular tenant or surface still fails.

For day-to-day use, see [Agent in Microsoft Teams](/run-operations/agent/agent-in-microsoft-teams.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/channels/set-up-microsoft-teams.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.