> 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/run-operations/agent/agent-in-microsoft-teams.md). # Agent in Microsoft Teams Use the Lleverage Agent from Microsoft Teams, pinning the conversation when work should stay inside one Project. When your organisation has installed the Lleverage Teams app, you can give the Agent operational work directly from Microsoft Teams. Teams is another **foreground surface** for the Agent. It does not turn Teams into a separate automation system: the Agent still uses Lleverage capabilities available to the acting user and the current run. ## Where you can use it The current Teams app supports direct conversations and supported group/channel contexts. A direct conversation with **Llev** is usually the simplest place for individual work. ## What happens when you send work For a normal dispatched Agent run, Teams acknowledges the work and updates the response when the run completes. Detailed execution still belongs to Lleverage even though the conversation starts in Teams. Use the web product when you need the richer session or Activity evidence. ## Project routing: pinned or unpinned A Teams conversation can be pinned to a Project or run without a fixed Project. ### Pinned Pin the conversation when the work should use one Project's specific Skills, context and Connections. This is the clearest choice when: * one operational team owns the conversation; * multiple Projects have overlapping capabilities; * Project-specific policy or context must be unambiguous; * you expect to inspect the work later from that Project. ### Unpinned An unpinned run uses the current speaker's authorised Project access. The Agent can consider Skills from authorised Projects instead of treating the Teams conversation itself as the access boundary. Project-specific capabilities remain tied to the Project that owns them. For Connection-backed capabilities, an unpinned run currently loads capability bundles from at most five authorised Projects. If a Connection or other Project-backed capability you expect is not available, pin the conversation to the Project that owns it. If the Agent has several plausible Project capabilities to choose from, narrow the request or pin the conversation rather than assuming which Project should win. ## Access and identity Being a member of the Microsoft tenant does not automatically grant Lleverage access. The Teams identity must resolve to a Lleverage member with the relevant organisation and Project access. The visible Teams bot identity is currently **Llev** across Projects. Different Projects can still have different instructions, Skills, systems, context and access. Do not rely on the bot name to tell you which Project capability is being used. ## Files Direct file uploads in a **one-to-one Teams conversation**, including ordinary compose-box uploads and inline images, are supported by the current Agent path. Microsoft SharePoint or OneDrive reference attachments can also be ingested through the current channel path when Lleverage can read them as the sharing user through delegated Microsoft access. If that Microsoft sign-in is missing, the user is asked to sign in and share the file again rather than the attachment becoming a dead end. **Workflow channel triggers are different.** The Microsoft Teams new-channel-message Workflow trigger can ingest inline/hosted images and supported channel-folder reference files as Workflow files. That support belongs to the Workflow trigger path and should not be read as equivalent attachment support for every conversational Teams surface. ## When an action needs approval Some connected-system actions can require explicit approval before the Agent executes them. In Teams, an approval can currently hand you to the Lleverage web app for review. Teams does not provide the same inline approval interaction available in Slack. Keep approval enabled where the action warrants it. Do not weaken an authority boundary just to avoid the web handoff. ## Need Teams installed? An organisation Owner can start the Teams connection flow from Lleverage. A Microsoft Teams administrator still needs to upload or approve the current custom app package for the tenant. See [Set up Microsoft Teams](/administer-and-govern/control/channels/set-up-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 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/run-operations/agent/agent-in-microsoft-teams.md?ask=&goal= ``` `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.